阅读说明：本技术 用于生理特征推导的系统和方法 (System and method for physiological feature derivation ) 是由 陆颖 韦传敏 彭衡 赵纪伟 邓梓明 黄子建 于 2017-03-15 设计创作，主要内容包括：本申请涉及用于基于生理特征和个性化模型来计算、估计或监测对象的血压的设备、方法和系统。当执行指令时,至少一个处理器可以执行以下操作的一个或以上：可以接收表示对象的脉搏上的时变信息的至少两个第二信号；可以为对象指定个性化模型；可以基于至少两个第二信号确定对象的有效的生理特征,其中,所述有效的生理特征是具有最小交叉验证预测误差的生理特征；可以基于有效的生理特征和为对象指定的模型计算对象的血压。(The present application relates to devices, methods and systems for calculating, estimating or monitoring a blood pressure of a subject based on physiological characteristics and a personalized model. When executing the instructions, the at least one processor may perform one or more of the following operations: at least two second signals representing time-varying information on the subject's pulse may be received; a personalized model may be specified for the object; a valid physiological characteristic of the subject may be determined based on the at least two second signals, wherein the valid physiological characteristic is the physiological characteristic with the least cross-validation prediction error; the blood pressure of the subject may be calculated based on the valid physiological characteristics and the model specified for the subject.)

1. A device for physiological feature derivation, comprising:

a memory storing instructions; and

at least one processor that executes the instructions to perform operations comprising:

receiving at least two second signals representing time-varying information on the subject's pulse;

determining a valid physiological characteristic of the subject based on the at least two second signals, wherein the valid physiological characteristic is the physiological characteristic with the least cross-validation prediction error;

assigning a personalized model to the subject based on at least a cost function and the effective physiological characteristic; and

calculating the blood pressure of the subject based on the valid physiological features and the personalized model specified for the subject.

2. The apparatus of claim 1, wherein the cost function is a standard deviation of prediction error of test data, the test data being a physiological feature having a minimum cross prediction error.

3. The apparatus of claim 1, wherein the personalized model is a model with a minimum standard deviation of prediction errors for test data that is a physiological feature with a minimum cross prediction error.

4. The apparatus of claim 1, wherein the effective physiological characteristic is obtained based on the akabane information content criterion AIC.

5. The apparatus of claim 1, wherein the second signal comprises a plethysmogram waveform.

6. The device of claim 1, further comprising a cuff-based blood pressure monitor configured to communicate with the cuff.

7. The device of claim 6, the cuff-based blood pressure monitor configured to coordinate blood pressure measurement with receiving the at least two second signals.

8. The apparatus of claim 1, 2 or 3, further comprising receiving a first signal representative of a pulse related to heart activity of the subject and determining the effective physiological characteristic based on the first signal.

9. The device of claim 8, the first signal comprising an electrocardiogram waveform or a ballistocardiogram waveform.

10. A system for physiological feature derivation, comprising:

a second acquisition module configured to receive at least two second signals representing time-varying information on the pulse;

a calibration unit configured to acquire a calibration data set;

an analysis module configured to

Determining an effective physiological characteristic of the subject based on the at least two second signals,

wherein the valid physiological characteristic is the physiological characteristic with the least cross-validation prediction error;

assigning a personalized model to the subject based on at least a cost function and the effective physiological characteristic; and

calculating the blood pressure of the subject based on the valid physiological features and the personalized model specified for the subject.

11. The system of claim 10, the second acquisition module comprising a blood oxygen monitor.

12. The system of claim 10, wherein the cost function is a standard deviation of prediction error of test data, the test data being a physiological feature having a minimum cross prediction error.

13. The system of claim 10, wherein the personalized model is a model with a minimum standard deviation of prediction errors for test data that is a physiological feature with a minimum cross prediction error.

14. The system of claim 10, the calibration unit comprising being configured to communicate with a cuff-based blood pressure monitor.

15. The system of claim 14, the cuff-based blood pressure monitor configured to coordinate a blood pressure measurement with the at least two second signals.

16. The system of claim 10, 12 or 13, further comprising a first acquisition module configured to receive a first signal representative of a pulse related to heart activity of the subject.

17. The system of claim 10, the first acquisition module comprising an electrocardiograph.

18. The system of claim 16, the analysis module configured to determine the valid physiological characteristic based on the first signal.

19. The system of claim 16, the first signal comprising an electrocardiogram waveform or a ballistocardiogram waveform.

20. The system of claim 10, further comprising an output module configured to provide an output of the calculated blood pressure.

Technical Field

The present application relates generally to personalization systems and methods applicable in healthcare-related fields. More particularly, the present application relates to systems and methods for physiological feature derivation and blood pressure monitoring.

Background

Conventional blood pressure measurement systems, also known as sphygmomanometers, use korotkoff sounds or oscillometric methods to determine blood pressure based on the relationship of external pressure to the magnitude of the arterial pulse volume. In recent years, techniques have been developed to derive physiological characteristics and estimate blood pressure using pulse signals obtained from photosensors placed on the subject's fingers. Systems utilizing this technology may be portable and continuously monitor the subject's blood pressure. Continuous monitoring of multiple physiological characteristics may be beneficial for example in hypertension management and cardiovascular risk prediction.

Disclosure of Invention

In a first aspect of the present application, an apparatus is provided. The apparatus includes a memory storing instructions and at least one processor executing the instructions to perform operations comprising: receiving a first signal representing a pulse related to heart activity of a subject; receiving at least two second signals representing time-varying information on the subject's pulse; assigning a personalized model to the subject; determining an effective physiological characteristic of the subject based on the at least two second signals; and calculating a blood pressure of the subject based on the valid physiological features and the model specified for the subject.

The apparatus provided above wherein said receiving said at least two second signals comprises communicating with one or more second sensors.

Further, the apparatus provided above wherein the first sensor comprises at least two electrodes and one of the one or more second sensors comprises a photosensor.

Further, the apparatus provided above wherein the first signal or the second signal comprises an optical signal or an electrical signal.

Further, in the device provided above, the effective physiological characteristic is obtained based on an akage information content criterion (AIC).

Further, the apparatus provided above wherein the first signal or the second signal comprises an electrocardiogram waveform, a plethysmogram waveform or a ballistocardiogram waveform.

Further, the apparatus provided above further comprises or is configured to communicate with a cuff-based blood pressure monitor.

Further, the apparatus provided above wherein the cuff-based blood pressure monitor is configured to coordinate blood pressure measurements with the receiving the first signal or the receiving the at least two second signals.

In a second aspect of the present application, a method is provided. The method comprises the following steps: receiving a first signal representing a pulse related to heart activity of a subject; receiving at least two second signals representing time-varying information on the subject's pulse; assigning a personalized model to the subject; determining an effective physiological characteristic of the subject based on the at least two second signals; and calculating the blood pressure of the subject based on the valid physiological features and the model specified for the subject.

Further, the method provided above further includes acquiring the first signal at a first location of the body of the subject.

Further, the method provided above further includes acquiring the second signal at a second location of the body of the subject.

Further, the method provided above wherein at least one of the first signal or the at least two second signals comprises an optical signal or an electrical signal.

Further, the method provided above wherein the effective physiological characteristic is obtained based on an akabane information content criterion (AIC).

Further, the method provided above wherein the first signal or the second signal is obtained in real time or at a first time interval.

Further, the method provided above wherein the calibration data set is obtained at a second time interval.

In a third aspect of the present application, a system is provided. The system includes a first acquisition module configured to receive a first signal representative of cardiac activity of a subject; a second acquisition module configured to receive at least two second signals representing time-varying information on the pulse; the calibration unit is configured to acquire a calibration data set; an analysis module is configured to assign a personalized model to the subject, determine valid physiological characteristics of the subject based on the at least two second signals, and calculate a blood pressure of the subject based on the valid physiological characteristics and the model assigned to the subject.

Further, in the system provided above, the first obtaining module includes an electrocardiograph monitor.

Further, in the system provided above, the second obtaining module includes a blood oxygen monitor.

Further, the system provided above wherein one of the first signal or the at least two second signals comprises an optical signal or an electrical signal.

Further, the system provided above, wherein the calibration unit comprises or is configured to communicate with a cuff-based blood pressure monitor.

Further, the system provided above wherein the cuff-based blood pressure monitor is configured to coordinate a blood pressure measurement with the first signal or the at least two second signals.

Further, the system provided above further comprises an output module configured to provide an output of the calculated blood pressure.

Drawings

The present application will be further described in conjunction with the exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These embodiments are non-limiting exemplary embodiments in which like reference numerals represent like structures throughout the several views of the drawings, and wherein:

fig. 1 illustrates an exemplary system configuration in which a system for monitoring physiological signals may be deployed according to various embodiments of the present application;

FIG. 2 depicts an exemplary diagram of an engine of the system shown in FIG. 1 according to some embodiments of the present application;

fig. 3 is a flow chart of an exemplary process in which a method for estimating physiological signals is deployed, in accordance with some embodiments of the present application;

FIG. 4 is a block diagram of an architecture of an information acquisition module shown in accordance with some embodiments of the present application;

FIG. 5 is a block diagram of an architecture of an analysis module shown in accordance with some embodiments of the present application;

FIG. 6 is a flow chart of a process for determining a personalized model of a subject and calculating blood pressure according to some embodiments of the present application;

FIG. 7 illustrates exemplary personal health management according to some embodiments of the present application;

FIG. 8 provides an exemplary process for calculating a subject's blood pressure based on a subject's effective physiological characteristics according to some embodiments of the present application;

FIG. 9 depicts an architecture that may be used to implement a mobile device that includes the application specific system or a portion thereof;

FIG. 10 depicts an architecture that may be used to implement a computer, including the application specific system or portions thereof.

Detailed Description

In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant disclosure. However, it will be apparent to one skilled in the art that the present application may be practiced without these specific details. In other instances, well-known methods, procedures, systems, components, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.

The present application relates to systems, methods, and programming aspects of physiological feature derivation, e.g., blood pressure monitoring. The system and method relate to improved signal processing and model monitoring. Systems and methods as disclosed herein may monitor a plurality of physiological characteristics. Features of the systems and methods may include, for example, real-time, simultaneity, continuity, non-invasiveness, improved accuracy, or the like, or a combination thereof. In some embodiments, systems and methods as disclosed herein may monitor various cardiovascular activities and related information, including, for example, blood pressure information, Electrocardiogram (ECG) information, blood oxygen information, or the like, or combinations thereof. In some embodiments, the blood pressure may be estimated based on Pulse related information, such as Pulse Transit Time (PTT), Pulse Arrival Time (PAT), fourier spectrum of the Pulse, wavelet decomposition of the Pulse, first and higher order derivatives of the Pulse, and the like, or combinations thereof. In some embodiments, blood pressure and/or blood oxygen levels may be estimated based on a Photoplethysmogram (PPG) signal. The systems and methods as disclosed herein may be used in a healthcare facility (e.g., hospital) or at home. For illustrative purposes, the following description is provided with reference to the derivation and reduction of physiological characteristics associated with blood pressure monitoring, and is not intended to limit the scope of the present application. By way of example only, the systems and methods disclosed herein may monitor blood pressure using one or more other pulse-related processes, such as artificial intelligence, big-data based neural networks, and the like.

These and other features and characteristics of the present application, the method of operation, the function of the elements associated with the structure, the combination of parts, and the economics of manufacture will become apparent upon consideration of the description of the drawings, which form a part of this application. It is to be understood, however, that the drawings are designed solely for the purposes of illustration and description and are not intended as a definition of the limits of the application. As used in the specification and in the claims, the singular form of "a", "an", and "the" include plural referents unless the context clearly dictates otherwise.

Fig. 1 illustrates an exemplary system configuration in which a system 100 may be deployed according to some embodiments of the present application. The system 100 can monitor one or more physiological pulse signals of interest. The system 100 may include a measurement device 110, a server 120, an external data source 130, and a terminal 140. The various components of the system 100 may be connected to each other directly or indirectly via a network 150.

The measurement device 110 may measure the signal. The signal may be a cardiovascular signal. The signals may relate to or be used to calculate or estimate a physiological characteristic of interest. In some embodiments, the signal may be a plethysmogram (PPG) signal. The physiological characteristic may be one or more spatial, temporal, spectral and/or physical quantities associated with the plethysmogram signal. For example, the physiological characteristic may include Pulse Transit Time (PTT). The measurement device 110 may include, for example, a clinical device, a home device, a portable device, a wearable device, etc., or a combination thereof. As used herein, a clinical device may be a device that meets applicable standards and/or specifications for use in a clinical environment including, for example, a hospital, a doctor's office, a nursing home, and the like. The clinical device may be used by or with the assistance of a healthcare provider. As used herein, a home device may be a device that meets applicable standards and/or specifications for use in a home or non-clinical setting. The home devices may be used by professional providers or non-professional providers. The clinical device or the household device or a part thereof may be portable or wearable. Exemplary clinical devices include auscultation devices, oscillographic devices, electrocardiographs, plethysmography monitors, the like, or combinations thereof. Exemplary home devices include oscillometric devices, home electrocardiograph monitors, blood pressure meters, and the like, or combinations thereof. Exemplary portable devices include an oscillometric device, a portable electrocardiograph, a portable plethysmogram monitor, or the like, or combinations thereof. Exemplary wearable devices include glasses 111, shoulder straps 112, smart watch 17, anklets 114, thigh straps 115, arm straps 116, chest straps 117, neck straps 118, finger grips (not shown), or the like, or combinations thereof. The above examples of measurement device 110 are provided for illustrative purposes and are not intended to limit the scope of the present application. The measurement device 110 may be of another form including, for example, a finger cuff, a wrist band, a brassiere, an undergarment, a chest strap, etc., or a combination thereof.

By way of example only, the measurement device 110 is a wearable or portable device that can measure one or more cardiovascular signals. In some embodiments, the wearable or portable device may process at least some of the measurement signals, estimate a physiological characteristic of interest based on the measurement signals, display a result including the physiological characteristic of interest in the form of, for example, an image, an audio alert, perform wired or wireless communication with another device or server (e.g., server 120), etc., or a combination thereof. In some embodiments, the wearable or portable device may communicate with another device (e.g., terminal 140) or a server (e.g., a cloud server). The device or server may process at least some of the measurement signals, estimate a physiological characteristic of interest based on the measurement signals, display a result including the physiological characteristic of interest in the form of, for example, an image, an audio alert, etc., or a combination thereof.

In some embodiments, the operations of processing the measurement signals, estimating physiological characteristics, displaying results, or performing wired or wireless communication may be performed by integrated devices or separate devices connected to or in communication with each other. Such integrated devices may be portable or wearable. In some embodiments, at least some of the individual devices may be portable or wearable, or located in the vicinity of a subject whose signals are measured or whose physiological characteristics of interest are estimated or monitored. As used herein, a subject may refer to a human or animal whose signals or information are acquired and whose physiological characteristics are acquired, estimated, or monitored. For example only, the subject may be a patient for whom cardiovascular signals are acquired, and the blood pressure is estimated or monitored based on the acquired cardiovascular signals. By way of example only, the subject-worn measurement device 110 may measure one or more cardiovascular signals; the measured one or more cardiovascular signals are sent to a smartphone, which may calculate or estimate one or more physiological characteristics of interest based on the measured signals. The calculated one or more physiological characteristics related to the subject may be input into a personalized model of the subject, and a blood pressure of the subject may be calculated based on the one or more physiological characteristics and the personalized model of the subject. In some embodiments, at least some of the individual devices are located remotely from the subject. For example only, the subject-worn measurement device 110 may measure one or more signals; sending the measured one or more signals to a processor, which may calculate or estimate a plurality of physiological characteristics of interest based on the measured signals; the calculated or estimated physiological characteristics of interest may be provided to the subject or to a user other than the subject (e.g., a doctor, a care provider, a family member related to the subject, etc., or a combination thereof).

In some embodiments, the measurement device 110 may include various types of sensors including, for example, electrode sensors, optical sensors, photoelectric sensors, pressure sensors, accelerometers, gravity sensors, temperature sensors, humidity sensors, and the like, or combinations thereof. The measurement device may monitor and/or detect one or more types of variables associated with the subject including, for example, weight, temperature, humidity, user or subject input, etc., or a combination thereof. The measurement device 110 may also include a positioning system, such as a GPS receiver or position sensor, and the position information may be transmitted over the network 150 to the server 120, external data sources 130, terminals 140, etc., or a combination thereof. The location information and the measurement signal may be transmitted simultaneously or consecutively.

The system may include or be in communication with a server configured to store the repository 900 and/or the models 121. The server may be the server 120. The server 120 may be a cloud server. For example only, the server 120 may be implemented in a cloud server that may provide storage capacity, computing capacity, or the like, or a combination thereof. The repository 900 may collect or store personal data. The personal data may include static data, dynamic data, or a combination of both. Exemplary static data may include various information about the subject, including identity, contact information, birthday, health history (e.g., whether the subject has a history of smoking, information about previous surgery, food allergies, medication history, genetic history, family health history, etc., or combinations thereof), gender, nationality, height, weight, occupation, habits (e.g., health-related habits, such as athletic habits), educational background, hobbies, marital status, etc., or combinations thereof. Exemplary dynamic data may include the current health status of the subject, the medication being taken by the subject, the medical treatment being performed by the subject, the diet, etc., or a combination thereof. The repository 900 may also include personal calibration data about the subject. For example, physiological signals or characteristics associated with the subject at multiple points in time or over a period of time (e.g., Pulse Transit Time (PTT), Systolic Blood Pressure (SBP), Diastolic Blood Pressure (DBP), etc., or combinations thereof.

The repository 900 may be stored locally on the measurement device 110 or the terminal 140. The repository 900 may include different portions (e.g., personal data, general data, etc.) with different levels of access control. For example, personal data may record data and information associated with each individual user, but objects may have different access permissions to different portions of the personal data. For example, the personal data of object 1, the personal data of object 2, and the personal data of object N may be stored in the repository 900, but object 1 may only have full access to his/her personal data and limited access to the personal data of other users.

Personal data may further include, but is not limited to, data headers, history, and preferences. In addition, the data header may have basic information of the subject and medical records. The data header may include, but is not limited to, the subject's age, gender, occupation, health status, medical history, lifestyle, marital status, and other personal information. The history may record measurement data (M), calibration values (C) (or calibration data), results (systolic blood pressure, DBP, blood pressure), and additional information related to previous measurements and/or calibrations. Furthermore, the additional information may be any internal or external variable occurring when the object is measured and/or calibrated. External variables may include room temperature, humidity, air pressure, weather, climate, time and date, etc. Internal variables such as body temperature, metabolic rate, mood, activity level, activity type, diet, and health status, etc. The above examples of additional information are merely to provide a better illustration, and the additional information associated with each measurement and/or calibration may be other types of information, such as the viscosity and other rheological data of the subject's blood. In some embodiments, the additional information recorded in the header and the concept of the information are interchangeable. When some information originally recorded in the data header changes with each measurement, it can also be considered as additional information.

The preferences may have information associated with the models, such as favorite models and coefficients of the object and favorite model applicability indicating which favorite models to use under what conditions or what additional information to use. The history data of the object may refer to all information stored under the history. The preferences may also include a rating of the object that rates the reliability of the personal data of the object and may be considered a weight factor when screening the personal data of the object as peer-to-peer data. For example, a subject that uploads the calibration value (C) weekly may have a better rating than another subject that is calibrated only once per year. Examples of the information recorded in the preferences and preferences described above may include other information, such as which portion of personal data an object is willing to share with other users or organizations.

The generic data may include some non-private or non-personalized data that may be accessed by other users or objects. The generic data may include a record of a database of all models, logical and common data, such as models and coefficients, logical decisions on screening peer data from personal data, and statistical results related to calibration values. Peer data may be filtered from personal data of multiple subjects and a logical decision to filter peer data from personal data is used to find the most closely related data based on the subject's data header and additional information in the history. The logical decision on filtering peer data from personal data may also weigh data obtained from different objects taking into account ratings in preferences. The above examples of information recorded in the generic data are merely intended to provide a better illustration, and the generic data may also include other information, such as errors (E, E', E ") associated with each regression analysis. More description can be found in, for example, international application with application number PCT/CN2015/083334 filed on 3/7/2015 and international application with application number PCT/CN2015/096498 filed on 5/12/2015, which are incorporated herein by reference.

As described elsewhere in this application, one or more models 121 in server 120 may be applied to data processing or analysis. The above description of server 120 is provided for illustrative purposes, and is not intended to limit the scope of the present application. The server 120 may have a different structure or configuration. For example, model 121 is not stored in server 120; rather, the model 121 may be stored locally at the terminal 140. Further, the repository 900 may also be stored at the terminal 140.

The external data sources 130 may include various organizations, systems, devices, and the like, or combinations thereof. Exemplary data sources 130 may include medical institutions 131, research facilities 132, databases 133, and peripherals 134, among others, or combinations thereof. The medical facility 131 or research facility 132 may provide, for example, personal medical records, clinical test results, experimental study results, theoretical or mathematical study results, models suitable for processing data, and the like, or combinations thereof. The database 133 may store various data related to the subject, such as physiological characteristics and personal data related to the subject. Peripheral device 134 may monitor and/or detect one or more types of variables including, for example, temperature, humidity, user or object input, etc., or a combination thereof. The examples of external data sources 130 and data types provided above are for illustrative purposes and are not intended to limit the scope of the present application. For example, the external data sources 130 may include other sources and other types of data, such as genetic information related to the object or its family. The terminal 140 in the system 100 may be configured to process at least some of the measured signals, estimate a physiological characteristic of interest based on the measured cardiovascular signals, display the results of the included physiological characteristic of interest in the form of, for example, an image, stored data, control access to the system 100 or a portion thereof (e.g., access to personal data stored in the system 100 or accessible from the system 100), manage input-output from or related to the subject, and the like, or combinations thereof.

The terminal 140 may include, for example, a mobile device 141 (e.g., a smart phone, a tablet computer, a laptop computer, etc.), a personal computer 142, other devices 143, or the like, or a combination thereof. The other devices 143 may include devices that can operate independently, or processing units or processing modules that are assembled in another device (e.g., a smart home terminal). For example only, the terminal 140 includes a CPU or processor in the measurement device 110. In some embodiments, the endpoint 140 may include an engine 200 as described in fig. 2, and the endpoint 140 may also include a measurement device 110.

The network 150 may be a single network or a combination of different networks. For example, the network 150 may be a Local Area Network (LAN), a Wide Area Network (WAN), a public network, a private network, a Public Switched Telephone Network (PSTN), the Internet, a wireless network, a virtual network, or any combination thereof. Network 150 may also include various network access points, e.g., wired or wireless access points, such as base stations or internet switching points (not shown in fig. 1), through which data sources or any components of system 100 may connect to network 150 as described above to transmit information via network 150.

The various components of system 100 or accessible from system 100 may include memory or electronic storage media. These components may include, for example, the measurement device 110, the server 120, the external data source 130, the terminal 140, the peripheral devices 134 discussed in conjunction with FIG. 2, and the like, or combinations thereof. The memory or electronic storage media of any component of system 100 can include one or both of system memory (e.g., a disk) that is integral to (i.e., substantially non-removable) the component, and removable memory that is removably connectable to the component via, for example, a port (e.g., a USB port, a firewire port, etc.) or a drive (e.g., a disk drive, etc.). The memory or electronic storage media of any component of system 100 may include or may operate in connection with one or more virtual memory resources (e.g., cloud memory, virtual private network, and/or other virtual memory resources).

The memory or electronic storage medium of System 100 may include a dynamic storage device that may store information and instructions that may be executed by a processor of a System-on-Chip (SoC, chipset including processor), other processors (or compute units), the like, or combinations thereof. The memory or electronic storage medium may also be used for storing temporary variables or other intermediate information during execution of instructions by the processor. Part or all of the Memory or electronic Memory medium may be implemented as Dual In-line Memory modules (DIMMs) and may be one or more of the following types of Memory: static Random Access Memory (SRAM), burst SRAM or synchronous Burst SRAM (BSRAM), Dynamic Random Access Memory (DRAM), fast page mode DRAM (FPM DRAM), Enhanced Dynamic Random Access Memory (EDRAM), extended data output random access memory (EDO RAM), extended data output dynamic random access memory (EDO DRAM), burst extended data output dynamic random access memory (BEDO DRAM), Enhanced Dynamic Random Access Memory (EDRAM), Synchronous Dynamic Random Access Memory (SDRAM), JEDECSRAM, PCIOO SDRAM, double data rate synchronous dynamic random access memory (DDR SDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Synchronous Link Dynamic Random Access Memory (SLDRAM), Interface dynamic random access memory (DRDRAM), Ferroelectric Random Access Memory (FRAM), or any other type of memory device. The memory or electronic storage medium may also include a Read Only Memory (ROM) and/or another static storage device, which may store static information and instructions for the processor and/or other processors (or computing units) of the system-on-chip. Further, the memory or electronic storage medium may include a magnetic disk, optical disk, or flash memory device to store information and instructions.

In some embodiments, the system-on-chip may be part of the core processing or computing unit of the system 100 or a component accessed from the system 100. The system on chip may receive and process input data and instructions, provide outputs, and/or control other components of the system. In some embodiments, a system on a chip may include a microprocessor, a memory controller, a memory, and peripheral components. The microprocessor may further include a cache memory (e.g., SRAM), which along with the memory of the system on chip may be part of a memory hierarchy to store instructions and data. The microprocessor may also include one or more logic modules, such as a Field Programmable Gate Array (FPGA) or other logic Array. The memory controller (or chipset) may facilitate communication between the microprocessor and the memory in the system-on-chip, which may also facilitate communication with peripheral components, such as counters, real-time timers, power reset generators, etc., or a combination thereof. The system on a chip may also include other components including, for example, timing sources (e.g., oscillators, phase-locked loops, etc.), voltage regulators, power management circuits, etc., or a combination thereof.

Merely by way of example, the system 100 may comprise a wearable or portable device. A wearable or portable device may include a system-on-chip and at least two sensors. Exemplary sensors may include photoelectric sensors, conductivity sensors, and the like, or combinations thereof. The system-on-chip may process signals acquired by at least some of the at least two sensors. The acquired signals may be various physiological signals including, for example, a plethysmogram (PPG), an electrocardiogram (electrocardiogram), etc., or a combination thereof. The system-on-chip may calculate the physiological characteristic of interest based on the acquired signal. Exemplary physiological characteristics of interest may be blood pressure, blood oxygen level, electrocardiographic information, heart rate, or the like, or combinations thereof.

In some embodiments, the external data source 130 may receive data from the measurement device 110, the server 120, the terminal 140, etc., or any combination via the network 150. For example only, the external data source 130 (e.g., a medical facility or smart home system, etc.) may receive information related to the subject (e.g., location information, data from a cloud server or terminal, etc., or a combination thereof) based on data received from the measurement device 110 or the terminal 140. In some embodiments, the measurement device 110 may receive data from the server 120, the external data source 130, the like, or any combination via the network 150. By way of example only, measurement device 110 may receive information related to the subject (e.g., a current/historical health status of the subject, a drug being taken by the subject, a medical treatment being performed by the subject, a current/historical diet, a current emotional state, historical physiological characteristics related to the subject (e.g., pulse transit time, systolic blood pressure, DBP), etc., or a combination thereof). Further, the terminal 140 can receive data from the measurement device 110, the server 120, the external data source 130, the like, or a combination thereof.

Fig. 1 is a specific example of the system 100, and the configuration of the system 100 is not limited to the configuration shown in fig. 1. For example, the server 120 may be omitted and all of its functions may be migrated to the terminal 140. For another example, the server 120 and the terminal 140 may be omitted and all functions thereof may be migrated to the measurement apparatus 110. The system may comprise various devices or combinations of devices in different embodiments.

In an example, the system may include a wearable or portable device and a mobile device (e.g., a smartphone, a tablet, a laptop, etc.). Wearable or portable devices may be used to acquire physiological signals, environmental information, and the like, or combinations thereof. The mobile device may be used to receive signals or information acquired by the wearable device or the portable device. The mobile device may calculate one or more physiological characteristics of interest based on the acquired signals or information and related data retrieved from another source (e.g., from a server, memory incorporated in a wearable or portable device, memory incorporated in the mobile device, etc.). The retrieved relevant data may include, for example, current/historical information stored on the server. Exemplary current/historical information may include a current/historical health status of the subject, current/historical medications the subject is/was taking, current/historical medical treatments the subject is/was taking, current/historical meals, current/historical emotional states, current/historical physiological characteristics related to the subject (e.g., pulse transit time, systolic blood pressure, diastolic blood pressure, electrocardiographic information, heart rate, blood oxygen level), and the like, or combinations thereof. The wearable or portable device or mobile device may display or report or store at least some of the acquired signals, information, the retrieved relevant data, the calculated one or more physiological characteristics of interest, or the like, or a combination thereof. The display or report may be provided to the object, a user other than the object, a third party, a server, or another device.

In another example, the system may include a wearable or portable device that may perform functions including: acquiring physiological signals or environmental information; retrieving relevant data from another source (e.g., from a server, memory incorporated in a wearable or portable device, etc.); calculating one or more physiological characteristics associated with the subject based on the acquired signals, information or retrieved related data; determining a personalized model of the subject; calculating a blood pressure of the subject based on the personalized model and one or more physiological characteristics associated with the subject; displaying, reporting, or storing at least some of the acquired signals, information, retrieved relevant data, calculating one or more physiological characteristics of interest, the subject's blood pressure, or the like, or combinations thereof. The display or report may be provided to the object, a user other than the object, a third party, a server, or another device.

In further examples, the system may include a wearable or portable device that may perform functions including: acquiring physiological signals and environmental information related to a subject; communicating with the server to transmit at least some of the acquired signals or information to the server so that the server can calculate one or more physiological characteristics of the subject; determining a personalized model of the subject; calculating a blood pressure of the subject based on the personalized model and one or more physiological characteristics associated with the subject; receiving the calculated one or more physiological characteristics and/or the blood pressure of the subject from the server; displaying, reporting, or storing at least some of the acquired signals, information, the calculated one or more physiological characteristics, the subject's blood pressure, or the like, or a combination thereof. The display or report may be provided to the object, a user other than the object, a third party, a server, or another device. In some embodiments, communication between the wearable or portable device and the server may be implemented by the wearable or portable device connected to a network (e.g., network 150). In some embodiments, communication between the wearable or portable device and the server may be implemented via a communication device (e.g., a mobile device such as a smartphone, tablet, laptop, etc.) that communicates with the wearable or portable device and the server.

In further examples, the system may include a wearable or portable device, a mobile device (e.g., a smartphone, a tablet, a laptop, etc.), and a server. Wearable or portable devices may be used to acquire physiological signals, environmental information, or the like, or a combination thereof. The mobile device may be used to receive signals or information acquired by the wearable or portable device, and may calculate one or more physiological characteristics of interest based on the signals and/or information received from the wearable or portable device and related data retrieved from, for example, a server, a memory incorporated in the wearable or portable device or incorporated in the mobile device. The mobile device may display, report, or store at least some of the acquired signals, information, the retrieved relevant data, the calculated one or more physiological characteristics of interest, or the like, or a combination thereof. The display or report may be provided to the object, a user other than the object, a third party, a server, or another device.

In further examples, the system may include an integrated clinical device or a home device. The integrated device may be wearable or portable. The integrated device may be used to acquire physiological signals, environmental information, and the like, or a combination thereof. The integrated device may further include an output device that may display, report, or output at least some of the acquired signals, information, retrieved relevant data, the calculated one or more physiological characteristics of interest, or the like, or a combination thereof. The display or report may be provided to the object, a user other than the object, a third party, a server, or another device. The integrated device may perform one or more measurements to calibrate the integrated device.

In further examples, the system may include an integrated clinical or home device and server. The integrated device may be wearable or portable. The integrated device may perform the following functions: acquiring physiological signals and environmental information; communicating with a server to transmit at least some of the acquired signals or information to the server so that the server can calculate one or more physiological characteristics of interest; receiving the calculated one or more physiological characteristics of interest from a server; displaying, reporting, or storing at least some of the acquired signals, information, the calculated one or more physiological characteristics of interest, or the like, or a combination thereof. The display or report may be provided to the subject, a user other than the subject, a third party, a server, or another device. The integrated device may perform one or more measurements to calibrate the integrated device. In some embodiments, communication between the integrated clinical device or home device and the server may be implemented by the integrated clinical device or home device connecting to a network (e.g., network 150). In some embodiments, communication between the integrated device and the server may be implemented via a communication device (e.g., a mobile device such as a smartphone, tablet, laptop, etc.) that communicates with the wearable or portable device and the server.

In some embodiments, the system may provide a user interface to allow objects, users other than objects, or entities to exchange information (including input to or output from the system) with the system disclosed herein. The user interface may be implemented on a terminal device, including, for example, a mobile device, a computer, etc., or a combination thereof. The user interface may be integrated in the system, for example a display device of the system. Persons with appropriate access rights may be allowed to access the system. Access rights may include, for example, privileges to read some or all information related to the object, update some or all information related to the object, etc., or a combination thereof. The access rights may be associated with or linked to a set of login credentials. By way of example only, the system may provide three levels of access. The first layer may include full access rights with respect to information related to the object, allowing reception and updating of the information related to the object. The second layer may include partial access rights with respect to information related to the object, allowing reception and updating of a portion of the information related to the object. The third layer may include a minimum access right with respect to the information related to the object, allowing a portion of the information related to the object to be received or updated. Different login credentials may be associated with different access rights to information in the system related to the object. As used herein, updating may include providing information that does not exist in the system, or modifying pre-existing information with new information.

For example only, the system may receive information related to an object provided via a user interface. The information related to the object may include basic information and optional information. Exemplary basic information may include height, weight, age (or date of birth), gender, arm length, nationality, occupation, habit (e.g., habits related to health, such as athletic habits), educational background, hobbies, marital status, health-related history (e.g., whether the subject has a smoking history, food allergies, drug allergies, medical history, family health history, genetic medical history, information regarding previous surgeries, etc., or combinations thereof, contact information, emergency contacts, etc., or combinations thereof An emotional state at or near the time of acquisition, a level of stress at or near the time of acquisition, etc., or a combination thereof. The system may receive one or more options or instructions via a user interface. In some embodiments, the options or instructions may be provided by an object or user other than an object that answers questions or prompts of a person response system. For example, the options or instructions may include a measurement frequency (e.g., weekly, monthly, twice weekly, twice monthly, once daily, twice daily, etc.), a preferred format for presenting information to the object or a user other than the object (e.g., email, voice message, text message, audio alert, haptic feedback, etc., or a combination thereof). As another example, the options or instructions may include information related to the computational features of interest, such as rules on how to select models, functions, calibration data, and the like, or combinations thereof.

In some embodiments, the system may provide information to the object or a user other than the object via the user interface. Exemplary information may include alerts, recommendations, reminders, and the like, or combinations thereof. For example, if a triggering event occurs, an alert may be provided or displayed to the object or a user other than the object. An exemplary triggering event may be at least some of the acquired information or physiological characteristic of interest exceeding a threshold. For example only, a triggering event may be the captured heart rate exceeding a threshold (e.g., greater than 150 times per minute, less than 40 times per minute, etc.). As another example, the triggering event may be a physiological characteristic of interest, such as an estimated blood pressure, exceeding a threshold. As another example, recommendations may be provided or displayed to the object or to a user other than the object. An exemplary recommendation may be a request to enter specific data (e.g., basic information, optional information, update features of interest, update models, update functions, update options and instructions, etc., or a combination thereof). The reminder may be provided or displayed to the object or to a user other than the object. Exemplary reminders may include extracting prescription drugs, resting, measuring physiological characteristics of interest, or the like, or combinations thereof.

In some embodiments, the system may communicate with the object, a user other than the object, and/or a third party through the user interface. Exemplary third parties may be doctors, healthcare workers, medical institutions, research institutions, peripheral devices of the subject, or users who are well connected to the subject, and so forth. Exemplary communications may relate to a subject's health status, eating habits, exercise habits, prescription drugs, instructions or steps for taking measurements, and the like, or combinations thereof. In some embodiments, the user interface accessible by or accessed by the third party may be the same or different than the user interface accessible by the object. For example, the output or data may be transmitted to a third party (e.g., a computer, a terminal at a doctor's office, a hospital where a healthcare provider is located and the health condition of the subject is monitored, etc., or a combination thereof). The third party may provide feedback information or instructions related to the output information via the user interface. By way of example only, a third party may receive information regarding one or more physiological characteristics related to the subject and accordingly provide a recommendation of an action to be taken by the subject (e.g., extract a prescribed medication, rest, contact or access a third party, etc., or a combination thereof); the system may then pass the recommendation to the object.

Fig. 2 shows an exemplary diagram including an engine 200. The engine 200 may be configured to acquire one or more signals related to the subject and calculate or estimate the blood pressure of the subject based on one or more physiological characteristics derived from the acquired signals. As shown, engine 200 may be connected to or otherwise in communication with, for example, measuring device 110, database 133, and server 120. The engine 200 may include an information collection module 210, an analysis module 220, and an output module 230. The information acquisition module 210 may be configured to acquire signals or information related to the subject, such as physiological signals, information related to the health condition of the subject, and the like, or a combination thereof. The analysis module 220 may be configured to analyze the acquired signals or information, or to determine or estimate a physiological characteristic of interest, or to determine a personalized model of the subject, or to determine a blood pressure of the subject based on the personalized model. The output module 230 may be configured to output the acquired signals or information, the physiological characteristic of interest, the subject's blood pressure, or the like, or a combination thereof. As used herein, a module may have a separate processor or use a processor that is shared by the system. The processor may perform functions in accordance with instructions associated with the various modules. For example, based on the relevant instructions, the analysis module 220 can retrieve the acquired signals and perform calculations to obtain one or more physiological characteristics of interest.

The information acquisition module 210 may be configured to acquire signals or information from one or more subjects. As used herein, acquisition may be implemented by receiving signals or information sensed, detected, or measured by, for example, a sensor, or by receiving input from a subject or a user other than a subject (e.g., a doctor, a care provider, a family member associated with a subject, etc., or a combination thereof). For the sake of brevity, the acquired signals or information may be referred to as acquired information. As used herein, information may include signals related to an object acquired by a device including, for example, a sensor, environmental information acquired by a device including, for example, a sensor, information otherwise acquired by, for example, a user including input from an object or other than an object, processed or pre-processed information acquired as described, or the like, or combinations thereof. Exemplary sensors may include electrode sensors, optical sensors, photoelectric sensors, pressure sensors, accelerometers, gravity sensors, temperature sensors, humidity sensors, and the like, or combinations thereof.

Exemplary acquired information may include physiological information. In an exemplary context of determining blood pressure, the physiological information may include cardiovascular signals. Exemplary cardiovascular signals may include a plethysmogram (PPG) signal, an Electrocardiogram (ECG) signal, a Ballistocardiogram (BCG) signal, Blood Pressure (BP), Systolic Blood Pressure (SBP), Diastolic Blood Pressure (DBP), Pulse Rate (Pulse Rate, PR), Heart Rate (Heart Rate, HR), Heart Rate variability (real Rate Variation, HRV), Heart murmur, Blood oxygen saturation, Blood density, Blood pH, borborygmus, brain waves, fat content, Blood flow Rate, and the like, or combinations thereof. Exemplary acquired information may include information about the subject, such as height, weight, age, gender, body temperature, arm length, disease history, or the like, or a combination thereof. Exemplary acquired information may include information from or relating to the environment surrounding the object at or near the time of acquisition (referred to as environmental information). Exemplary environmental information may include temperature, humidity, air pressure, air flow rate, ambient light intensity, or the like, or combinations thereof. As used herein, the time of acquisition may refer to a point in time or a period of time at which information related to the subject is acquired, such as physiological information of the subject.

The information acquisition module 210 may receive or load information from the measurement device 110, the server 120, the database 133, or other devices (not shown) including, for example, electrocardiographs, plethysmography, respiration monitors, brain wave monitors, blood oxygen monitors, blood glucose monitors, and devices with similar functionality. In the present disclosure, the term "monitor" and the term "sensor" may be used interchangeably. Examples of measurement device 110 may include a smart watch, finger grips, earphones, glasses, bracelets, keyrings, and the like, or a combination thereof. The measurement device 110, server 120, database 133, or other device may be local or remote. For example, the server 120 and the engine 200 may be connected through a Local Area Network (LAN) or the Internet. The measurement device 110 and the engine 200 may be connected via a local area network or the internet. Other devices and engines 200 may be connected through a local area network or the internet. The transfer of information between the information collection module 210 and the measurement device 110, the server 120, the database 133, or such other devices may be via a wired connection, a wireless connection, etc., or a combination thereof.

The information collection module 210 may receive information provided by the object or a user other than the object via, for example, an input device. The input devices may include, but are not limited to, a keyboard, a touch screen (e.g., with haptic or tactile feedback), a voice input device, an eye tracking input device, a brain monitoring system, etc., or a combination thereof. Information received through the input device may be transmitted to the processor for further processing, e.g., via a bus. The Processor Digital Signal Processor for further processing information obtained from the input device may be a Digital Signal Processor (DSP), a system on chip (SoC), a microprocessor, or the like, or a combination thereof. Other types of input devices may include a cursor control device, such as a mouse, a trackball, or cursor direction keys to communicate information regarding direction and/or command selections to a processor, for example.

The description of the information collection module 210 is intended to be illustrative, and not to limit the scope of the present application. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. For example, a storage unit (not shown in fig. 2) may be added to the information collection module 210 for storing the acquired information.

The analysis module 220 may be configured to analyze the acquired information. Analysis module 220 may be connected to or otherwise in communication with one or more information acquisition modules 210-1, 210-2. The analysis module 220 may be configured to perform one or more operations including, for example, preprocessing, computing, calibration, statistical analysis, and the like, or a combination thereof. Any of the operations may be performed based on at least some of the acquired information or an intermediate result from another operation (e.g., training data, or an operation performed by analysis module 220, or another component of system 100). For example, the analysis may include one or more operations including preprocessing at least a portion of the acquired information related to the subject, identifying characteristic points or features of the acquired information or the preprocessed information, determining a personalized model of the subject, calculating a blood pressure of the subject, analyzing information about the subject provided by a user other than the subject or the subject, analyzing information about an environment surrounding the subject at or near the time of acquisition, and the like, or a combination thereof.

Some operations of the analysis may be performed in parallel or in series. As used herein, parallel execution may refer to some analysis operations that may be performed at or near the same point in time; serial execution may refer to some analysis operations that begin or are performed after other operations have begun or ended. In some embodiments, the serial execution of two operations may indicate that one operation begins after the other operation completes. In some embodiments, the serial execution of two operations may indicate that one operation begins after the other operation begins, and that the two operations partially overlap. In some embodiments, at least two operations of the analysis may be performed in parallel. In some embodiments, at least two operations of the analysis may be performed in series. In some embodiments, some operations of the analysis may be performed in parallel and some operations may be performed in series.

The analysis or some of the operations of the analysis may be performed in real time, i.e., at or near the time of acquisition. The analysis or some of the operations of the analysis may be performed after a delay after the information is acquired. In some embodiments, the acquired information is stored for analysis after a delay. In some embodiments, the acquired information is pre-processed after a delay and stored for further analysis. The delay may be seconds, or minutes, or hours, or days, or longer. After the delay, the analysis may be triggered by instructions from the subject or a user other than the subject (e.g., a doctor, a care provider, a family member associated with the subject, etc., or a combination thereof), instructions stored in the system 100, or the like, or a combination thereof. For example only, instructions stored in system 100 may specify a duration of delay, a time to perform an analysis, a frequency to perform an analysis, a triggering event to trigger execution of an analysis, and the like, or a combination thereof. The instructions stored in the system 100 may be provided by the object or a user other than the object. An exemplary triggering event may be at least some of the acquired information or physiological characteristics of interest exceeding a threshold. For example only, the triggering event may be the acquired heart rate exceeding a threshold (e.g., above 150 beats per minute, below 40 beats per minute, etc.). As used herein, "exceeding" may be greater than or less than a threshold. As another example, the triggering event may be a physiological characteristic of interest, such as an estimated blood pressure exceeding a threshold.

The analysis module 220 may be centralized or distributed. The centralized analysis module 220 may include a processor (not shown in fig. 2). The processor may be configured to perform operations. The distributed analysis module 220 may include at least two operation units (not shown in fig. 2). The operation units may be configured to collectively perform operations of the same analysis. In a distributed configuration, the execution of at least two operating units may be controlled or coordinated by, for example, server 120.

The information acquired, intermediate results of the analysis, or results of the analysis (e.g., physiological characteristics of interest) may be analog or digital. In the exemplary context of blood pressure monitoring, the acquired information, intermediate results of the analysis, or results of the analysis (e.g., physiological characteristics of interest) may include, for example, a plethysmogram signal, an electrocardiogram signal, a ballistocardiogram signal, blood pressure, systolic blood pressure, diastolic blood pressure, pulse rate, heart rate, HRV (heart rate variability), heart murmurs, blood oxygen saturation (or referred to as blood oxygen level), blood density, pH of the blood, bowel sounds, brain waves, fat content, blood flow rate, or the like, or combinations thereof.

The results of the analysis, for example, regarding the physiological characteristics of interest of the subject, may be influenced by various factors or conditions, including, for example, environmental factors, factors due to the physiological state of the subject, factors due to the psychological state of the subject, and the like, or combinations thereof. One or more of these factors may affect the accuracy of the information obtained, the accuracy of intermediate results of the analysis, the accuracy of the analysis results, etc., or a combination thereof. For example, the physiological characteristic of interest may be estimated based on correlation with the acquired information; factors due to physiological conditions may lead to deviation from correlation; this factor may affect the accuracy of the physiological characteristic of interest estimated based on the correlation. For example only, cardiovascular signals associated with a subject may change with, for example, time, mental state of the subject, etc., or a combination thereof. The correlation between the cardiovascular signal and a physiological characteristic of the subject (e.g., the correlation between the PPT value and the blood pressure) may vary with, for example, the physiological state of the subject, the psychological state of the subject, the environment surrounding the subject, etc., or a combination thereof. This effect can be balanced or compensated for in the analysis.

In the analysis, information on the influencing conditions (e.g., environmental information, physiological state, psychological state, etc.) may be acquired, and correction or adjustment may be performed accordingly in the analysis process. For example only, the correction or adjustment may be by a correction factor. For example, an environmental correction factor may be introduced into the analysis based on environmental information acquired from or related to the environment surrounding the object at or near the time of acquisition. Exemplary environmental information may include one or more of temperature, humidity, barometric pressure, air flow rate, ambient light intensity, and the like. Exemplary environmental correction factors may include one or more of a temperature correction factor, a humidity correction factor, an air pressure correction factor, an air flow rate correction factor, an ambient light intensity correction factor, and the like. As another example, the correction or adjustment can be by performing a calibration (e.g., a calibrated model, a calibrated function, etc.) for estimating a correlation of the physiological characteristic of interest. As another example, the correction or adjustment may be based on information related to the influencing condition by selecting a correlation from at least two correlations for estimating the physiological characteristic of interest.

The description of the analysis module 220 is intended to be illustrative, and not to limit the scope of the present application. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. For example, a cache unit (not shown in FIG. 2) may be added to the analysis module 220 for storing intermediate results or real-time signals or information during the above-described process.

The output module 230 may be configured to provide an output. The output may include the physiological characteristic of interest, at least some of the acquired information (e.g., acquired information used to estimate the physiological characteristic of interest), the subject's blood pressure, etc., or a combination thereof. The transmission of the output may be via a wired connection, a wireless connection, etc., or a combination thereof. Once the output is available for transmission, the output may be transmitted in real time. The output may be transmitted after a delay after the output is available for transmission. The delay may be seconds, or minutes, or hours, or days, or longer. After the delay, the output may be triggered by instructions from the object, a user other than the object or an associated third party, instructions stored in the system 100, or the like, or a combination thereof. For example only, instructions stored in system 100 may specify a duration of delay, a time to transmit an output, a frequency to transmit an output, a trigger event, etc., or a combination thereof. The instructions stored in the system 100 may be provided by the object or a user other than the object. An exemplary triggering event may be the physiological characteristic of interest or at least some of the acquired information exceeding a threshold. For example only, the triggering event may be the captured heart rate exceeding a threshold (e.g., greater than 150 beats per minute, less than 40 beats per minute, etc.). As another example, the triggering event may be that a physiological characteristic of interest (e.g., estimated blood pressure) exceeds a threshold.

The output for transmission may be, for example, in analog form, digital form, etc., or a combination thereof. The output may be in a format such as graphics, code, voice messages, text, video, audio alerts, haptic effects, and the like, or combinations thereof. The output may be displayed on the local terminal, or output to a remote terminal, or both. The terminal may include, for example, a Personal Computer (PC), a desktop Computer, a laptop Computer, a smart phone, a smart watch, etc., or a combination thereof. By way of example only, the output may be displayed on a wearable or portable device worn by the subject and also sent to a computer or terminal of a doctor's office or hospital where the healthcare provider is located and monitors the health condition of the subject.

Output module 230 may include or be in communication with a display device that may display output or other information to the object or a user other than the object. The Display device may include a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) based Display, or any other flat panel Display, or may use a Cathode Ray Tube (CRT), a touch screen, or the like. The touch screen may include, for example, a resistive touch screen, a capacitive touch screen, a plasma touch screen, a vector pressure sensing touch screen, an infrared touch screen, or the like, or combinations thereof.

In some embodiments, a memory module (not shown in fig. 2) or memory unit (not shown in fig. 2) may be integrated in the engine 200. In some embodiments, a storage unit (not shown in fig. 2) may be integrated in any of the information collection module 210, the analysis module 220, or the output module 230. A storage module (not shown in fig. 2) or storage unit (not shown in fig. 2) may be used to store the intermediate results or analysis results. A memory module (not shown in fig. 2) or a memory unit (not shown in fig. 2) may be used as the data cache memory. The memory modules (not shown in fig. 2) or memory units (not shown in fig. 2) may include hard disks, floppy disks, flash memory, RAM, DRAM, SRAM foam, thin film memory, magnetic plate line memory, phase change memory, and the like, or combinations thereof. The memory module (not shown in fig. 2) or the memory unit (not shown in fig. 2) may include a memory or an electronic memory medium as described in fig. 1 and elsewhere in this application.

In some embodiments, engine 200 does not include a storage module or unit, and measurement device 110 or server 120 may serve as a storage device accessed by engine 200. The server 120 may be a cloud server providing cloud storage. As used herein, cloud storage is a model of data storage, where digital data is stored in logical pools, with physical storage spanning multiple servers (and typically located in multiple locations). The physical environment includes, for example, a logical pool, and the physical storage across multiple servers may be owned and managed by a hosting company. The hosting company may be responsible for keeping data available and accessible, and the physical environment protected and running. Such cloud storage may be accessed through a cloud service, a web services Application Programming Interface (API), or an Application program that utilizes an API. Exemplary applications include cloud desktop storage, cloud storage gateways, Web-based content management systems, and the like, or combinations thereof. The server 120 may include a public cloud, a personal cloud, or both. For example, the obtained information may be stored in a personal cloud that may be accessed after authorization by authentication, e.g., username, password, or the like, or a combination thereof. Non-personalized information including, for example, methods or computational models, may be stored in the public cloud. No authorization or authentication is required to access the public cloud. The information collection module 210, analysis module 220, and output module 230 may retrieve or load information or data from a public cloud or a personal cloud. Any of these modules may send signals and data to a public cloud or a personal cloud.

The connection or transmission between any two of the information collection module 210, the analysis module 220, and the output module 230 may be via a wired connection, a wireless connection, etc., or a combination thereof. At least two of these modules may be connected to different peripheral devices. At least two of these modules may be connected to the same peripheral device. The measurement device 110 may be connected to one or more modules by a wired connection, a wireless connection, etc., or a combination thereof. It should be understood by those skilled in the art that the above-described embodiments are only intended to describe the present disclosure in the present application. There are numerous modifications and variations of this application without departing from its spirit. For example, the information collection module 210 and the output module 230 may be integrated in separate modules configured to acquire and output signals or results. The standalone module may be connected to the analysis module 220 via a wired connection, a wireless connection, etc., or a combination thereof. The three modules in engine 200 may be partially integrated in one or more separate modules or share one or more units.

The connections or transmissions between modules in the system 100, or between a module and the measurement device 110, or between the system and the server 120 should not be limited to the above description. All connections or transmissions may be used in combination or may be used independently. The modules may be integrated in a stand-alone module, i.e. the functionality of the modules may be implemented by separate modules. Similarly, one or more modules may be integrated on a single measurement device 110. Any of the above connections or transmissions may be through a wired connection, wireless connection, etc., or a combination thereof. For example, a wired connection or a wireless connection may include, for example, wires, cables, satellites, microwaves, bluetooth, radio, infrared, and the like, or a combination thereof.

The engine 200 may be implemented on one or more processors. The modules or units of engine 200 may be integrated in one or more processors. For example, the information collection module 210, the analysis module 220, and the output module 230 may be implemented on one or more processors. One or more processors may utilize storage devices (not shown in fig. 2), peripheral devices 240, and server 120 to send signals or data. The one or more processors may retrieve or load signals, information, or instructions from a storage device (not shown in fig. 2) or server 120, and process the signals, information, data, or instructions, or a combination thereof, to compute one or more physiological characteristics of interest. The one or more processors may also be connected or in communication with other devices related to the system 100 and transmit or share signals, information, instructions, physiological characteristics of interest, etc. with such other devices, e.g. through a mobile phone APP, a local or remote terminal, etc., or a combination thereof.

Fig. 3 is a flow chart illustrating an exemplary process for deriving physiological characteristics of a subject and estimating blood pressure of the subject, according to some embodiments of the present application. Information about the object may be obtained at step 310. Information acquisition may be performed by the information collection module 210. The acquired information may include physiological information of the subject, environmental information related to the surroundings of the subject at or near the time of acquisition, information provided by the subject or a user other than the subject. The acquired information may include a plethysmogram signal, an electrocardiogram signal, pulse rate, heart rate variability, blood oxygen saturation, respiration, muscle status, bone status, brain waves, blood lipid level, blood glucose level, height, weight, age, gender, body temperature, arm length, medical history, room temperature, humidity, air pressure, air flow rate, ambient light intensity, etc., or combinations thereof. At least some of the acquired information may be analyzed in 320. By analyzing, various characteristics of at least some of the acquired information may be identified. For example, the acquired information may include a plethysmogram signal and an electrocardiogram signal; the identified characteristics of these signals may include, for example, waveforms, characteristic points, peak points, valley points, amplitudes, time intervals, phases, frequencies, periods, and the like, or combinations thereof. An analysis based on the identified features may be performed at step 320. For example, a physiological quantity of interest may be calculated or estimated based on the identified features. The physiological quantity of interest estimated based on the acquired plethysmogram signals and electrocardiogram signals may include, for example, a mean, absolute mean, variance, standard deviation, and/or median of blood pressure, systolic blood pressure, diastolic blood pressure, blood oxygen level, or the like, or combinations thereof. The physiological quantity of interest may be used to select a personalized model for the subject. The model may be used to calculate the blood pressure of the subject. Information about the subject's blood pressure, such as blood pressure, systolic blood pressure, diastolic blood pressure, blood oxygen level, or the like, or a combination thereof, may then be output at step 330. Some of the acquired information may also be output at step 330. The output may be displayed to the user of the object or in addition to the object, printed, stored in a storage device or server 120, sent to a device for further processing, etc., or a combination thereof. It should be noted that after the analysis of step 320, a new acquisition step may be performed in step 310.

The above description is intended to be illustrative, and not to limit the scope of the application. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. For example, a pre-processing step may be added between step 310 and step 320. In the preprocessing step, the acquired signal may be preprocessed in order to reduce or eliminate noise or interference in the originally acquired signal. For example, complex real-time digital filtering may be used to reduce or remove high frequency noise from the plethysmogram or electrocardiogram signal, thereby allowing the characteristics of the plethysmogram or electrocardiogram signal to be accurately identified. Exemplary preprocessing methods may include low pass filtering, band pass filtering, wavelet transforms, median filtering, morphological filtering, curve fitting, hilbert-yellow transforms, and the like, or combinations thereof. Description of methods and systems for reducing or eliminating noise in physiological signals, such as plethysmogram signals or electrocardiogram signals, may be found in, for example, international patent application No. PCT/CN2015/077026 filed on 20/4/2015, international patent application No. PCT/CN2015/077025 filed on 20/4/2015, and international patent application No. PCT/CN2015/079956 filed on 27/5/2015, each of which is incorporated by reference. One or more other optional steps may be added between step 310 and step 320, or elsewhere in the exemplary process shown in fig. 3. Examples of such steps may include storing or caching the retrieved information.

Fig. 4 is a block diagram illustrating an architecture of an information collection module according to some embodiments of the present application. Information collection module 210 may be connected to or otherwise in communication with, for example, peripheral device 240, analysis module 220, output module 230, and server 120 via network 150. Information collection module 210 may be configured to acquire information related to the subject, information provided by the subject, a user other than the subject, and/or an associated third party (e.g., a doctor, a medical professional, a medical institution, a research institution, a peripheral of the subject, or a user in good connection with the subject, etc.), environmental information from the surrounding environment surrounding the subject at or near the time of acquisition, or the like, or combinations thereof. The information collection module 210 may include a first acquisition unit 410 and a second acquisition unit 420. The first acquisition unit 410 may be configured to acquire the first signal or first information including the first signal related to the object. The second acquisition unit 420 may be configured to acquire the second signal or second information including the second signal related to the object. The first acquisition unit 410 and the second acquisition unit 420 may acquire signals in real time. The first signal and the second signal may be acquired at or near the same time. In some embodiments, the information collection module 210 may include one or more other acquisition units (not shown in fig. 4) in addition to the first acquisition unit 410 and the second acquisition unit 420. In some embodiments, the first acquisition unit 410 and the second acquisition unit 420 may be integrated in separate modules or units.

In some embodiments, the first acquisition unit 410 may be configured to acquire an electrocardiogram signal of the subject. The first acquisition unit 410 may comprise an electrocardiograph (not shown in fig. 4). The electrocardiograph (not shown in fig. 4) may be of any type, such as a clinical device, a home device, a wearable device, a portable device, and the like. The electrocardiograph (not shown in fig. 4) may comprise at least two electrodes for recording potential changes related to cardiovascular activity of the subject. The electrodes may be arranged in a 12-lead format, a 5-lead format, a 3-lead format, and the like. The electrodes may be located on one or more limbs and/or on the chest of the subject. For example, in a 5-lead version, the electrodes may be located on the chest of the subject. In some embodiments, the first obtaining unit 410 may include a control unit (not shown in fig. 4). A control unit (not shown in fig. 4) may be configured to control features of the acquisition process. The characteristics may include sampling frequency, sampling time interval, etc., or a combination thereof. In some embodiments, the first obtaining unit 410 may include a storage unit (not shown in fig. 4). The storage unit (not shown in fig. 4) may be used to store the acquired first signal, the characteristic, etc., or a combination thereof. In some embodiments, the acquired signals, features may be stored in any storage device disclosed anywhere in this application.

In some embodiments, the second acquisition unit 420 may be configured to acquire a vessel volume map signal or to acquire information comprising a vessel volume map signal. In some embodiments, the second acquisition unit 420 may include a blood oxygen monitor (not shown in fig. 4). The blood oxygen monitor (not shown in fig. 4) may be configured to acquire blood oxygen information of the subject using a photosensor. Blood oxygenation information may be estimated based on two or more vascular plethysmogram signals. In some embodiments, at least one of the acquired plethysmogram signals together with the electrocardiogram signal may be used to calculate physiological characteristics, which may be used to estimate blood pressure values based on an individualized model.

In some embodiments, the blood oxygen monitor (not shown in fig. 4) may include a single photoelectric sensor, or a sensor array including at least two photoelectric sensors. The photosensor may include one or more transmitting ends and one or more receiving ends. The transmitting end may include one or more light sources. The light source may emit one or more of ultrasound, radio, microwave, millimeter wave, infrared, visible, ultraviolet, gamma, or X-ray electromagnetic radiation. As used herein, light may also include any wavelength within the radio, microwave, Infrared (IR), visible, Ultraviolet (UV) or X-ray spectra, and electromagnetic radiation of any suitable wavelength may be suitable for use with the systems, devices or apparatus disclosed herein. By way of example only, the Emitting end may include two Light sources, a red Light Emitting Light source, such as a red Light Emitting Diode (LED), and an infrared Light Emitting Light source, such as an IR LED; the transmitting end may emit light into the tissue of the subject at a wavelength used to calculate a physiological characteristic of interest (e.g., blood oxygenation information) of the subject. As used herein, for the sake of brevity, a particular wavelength may also include wavelengths within a particular range of wavelengths. For example, the red wavelength may be between about 600nm and about 700nm, and the infrared wavelength may be between about 800nm and about 700 nm. In embodiments using an array of sensors, each sensor may emit a single wavelength. The receiving end may be used to receive a signal generated by the emitted light passing through the object. In some embodiments, the second obtaining unit 420 may be configured to obtain a vascular volume map signal of the subject from a plurality of body locations (e.g., head, neck, chest, abdomen, upper arm, wrist, waist, upper leg, knee, ankle, or the like, or a combination thereof). In some embodiments, one or more photoelectric sensors may be placed in any of a plurality of body positions. In some embodiments, one or more photosensor arrays may be placed in any of a plurality of body positions.

In some embodiments, the second obtaining unit 420 may include a control unit (not shown in fig. 4) and/or a storage unit (not shown in fig. 4). Similarly, the control unit (not shown in fig. 4) may be configured to control the acquisition process of the second signal or the second information. A storage unit (not shown in fig. 4) may be configured to store the acquired signals and/or information.

The information collection module 210 may include one or more other collection units (not shown in fig. 4). For example, the acquisition unit may be configured to acquire basic information related to the subject, such as height, weight, age (or birth date), gender, arm length, nationality, occupation, habits (e.g., health-related habits such as athletic habits), educational background, hobbies, marital status, health-related history (e.g., whether the subject has a history of smoking, food allergy, drug allergy, treatment, family health, genetic medical history, previous surgery information, or the like, or a combination thereof), contact, emergency contact, or the like, or a combination thereof. The basic information about the subject may be provided by the subject, a user other than the subject, or a third party (e.g., a doctor, a medical professional, a medical facility, a research facility, a peripheral device of the subject, or a user who is well-connected to the subject, etc.).

In another example, the acquisition unit may be configured to acquire environmental information surrounding the object, including temperature, humidity, air pressure, air flow rate, ambient light intensity, or the like, or a combination thereof. The environmental information may be acquired in real-time mode (e.g., at or near the acquisition time) or may be acquired at some time interval (e.g., independent of the acquisition time).

In further examples, the one or more acquisition units may be configured to acquire EMG signals of the subject by a pressure sensing method, to acquire body temperature data of the subject by a temperature sensing method, or the like, or a combination thereof. In further examples, the obtaining unit may be configured to obtain ballistocardiogram signals, blood density information, pH information of the blood, or the like, or a combination thereof.

The one or more acquisition units may communicate with the one or more sensors to acquire information sensed, detected, or measured by the one or more sensors. Exemplary sensors include electrode sensors, optical sensors, photoelectric sensors, conductivity sensors, pressure sensors, accelerometers, gravity sensors, temperature sensors, humidity sensors, and the like, or combinations thereof.

For example only, the optical sensor may include an integrated photodetector and light source. The optical sensor may further comprise an amplifier. The light source may emit radiation having a wavelength, for example, in the visible, infrared region, or the like, or combinations thereof. The photodetector may detect radiation generated by light (in wavelength or range of wavelengths) impinging on or entering and/or being reflected by tissue and reaching the photodetector (or referred to as reflected radiation). An optical sensor may be placed at a body position of a subject to detect pulse-related signals of the subject. For example, the optical sensor may be a vessel volume map sensor. In some embodiments, the optical sensor may comprise at least two light sources, wherein the light sources may emit light at a wavelength or within a range of wavelengths. Thus, the at least two light sources may emit light of various wavelengths, or light in respective wavelength ranges. For example, the light source may emit red and infrared light. In some embodiments, the optical sensor may comprise at least two photodetectors, wherein the photodetectors may be used to detect reflected radiation generated by light of a wavelength or within a range of wavelengths. In some embodiments, a photodetector may be used to detect reflected radiation resulting from emitted light of various wavelengths or within respective wavelength ranges. For example, a photodetector may be used to detect reflected radiation produced by red and infrared light.

In some embodiments, at least two plethysmogram sensors may be assembled into one device. One of the at least two plethysmogram sensors may comprise a light source and a photodetector; the light source may emit light at a wavelength, or within a range thereof; a photodetector may be used to detect reflected radiation produced by the emitted light (wavelength or range of wavelengths). The at least two plethysmogram sensors may comprise a plethysmogram sensor comprising a red light emitting light source and a photodetector which can detect reflected radiation produced by red light, and a plethysmogram sensor comprising an infrared light emitting light source and a photodetector which can detect reflected radiation produced by infrared light. In some embodiments, at least two of the at least two plethysmogram sensors may be placed at different locations on the subject's body. For example, one vessel volume map sensor may be placed on the upper arm of the subject and another vessel volume map sensor may be placed on the finger of the subject. In some embodiments, at least two of the at least two plethysmogram sensors may be placed at or near the same location on the subject's body. For example, two plethysmogram sensors may be placed at the upper arm of the subject. For another example, two plethysmogram sensors may be placed at the subject's finger. In some embodiments, the device may include a plethysmogram sensor; the plethysmogram sensor may comprise at least two light sources and a photodetector; the light sources may emit light at various wavelengths or within respective wavelength ranges; photodetectors may be used to detect reflected radiation produced by emitted light of various wavelengths or within respective wavelength ranges.

The device may be a wearable or portable device including, for example, a T-shirt, a smart watch, a wrist band, and the like, or a combination thereof. The apparatus may also include one or more processors or processing units. The processor or processing unit may be configured to control the process of information acquisition or may be configured to perform one or more operations of any module. Signals or data may be transmitted between sensors placed at different locations. The transmission may be via a wireless connection (e.g., WiFi, bluetooth, Near-Field Communication (NFC), etc., or a combination thereof), a wired connection, etc., or a combination thereof. For example, the signals received by the sensors may be sent over a Body Sensor Network (BSN) or Intra-Body Communication (IBC).

The above description is intended to be illustrative, and not to limit the scope of the application. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. For example, the acquisition unit may be integrated into a separate unit configured to acquire more than one information or signal related to the object. At least some of the acquisition units may be integrated into one or more separate units. One or more of the acquisition units may share a common control unit (not shown in fig. 4) and/or a common storage unit (not shown in fig. 4).

Fig. 5 is a block diagram illustrating an architecture of an analysis module according to some embodiments of the present application. Analysis module 220 may be connected to or in communication with, for example, peripheral device 240 and server 120 via network 150. The analysis module 220 may estimate or calculate a blood pressure associated with the subject based on the acquired information. The analysis module 220 may comprise a pre-processing unit 510, a feature recognition unit 520, a calculation unit 530, and possibly a calibration unit 540.

The pre-processing unit 510 may be configured to pre-process the acquired information. Preprocessing may be performed to reduce or remove noise or errors in the original signal. In some embodiments, the correction of the standard deviation of the vessel volume map waveform may be performed by the preprocessing unit 510. For example, for a plethysmogram waveform consisting of tens of heart beat cycles, the mean, median and/or standard deviation of the maxima/minima of the plethysmogram waveform over each heart beat cycle may be calculated. A threshold may be specified to specify an outlier within the plethysmogram waveform. For example, a value of 0.1 may be set as the threshold. If the standard deviation of the maxima/minima of the plethysmogram waveform over each heart beat cycle is less than a threshold, the plethysmogram waveform may be flagged as outliers and discarded. Similarly, the preprocessing unit 510 may process personal data of the subject. A trusted interval of values of personal data may be set. Any personal data outside of the trusted interval may be marked as suspect and needs to be corrected. For example, if the height of the object is 5cm, and/or the weight of the object is 5 kilograms, the personal data of the object may be flagged as problematic and need to be corrected. Exemplary methods for preprocessing may include low pass filtering, band pass filtering, wavelet transform, median filtering, morphological filtering, curve fitting, hilbert-yellow transform, and the like, or any combination thereof. Description of methods and systems for reducing or eliminating noise in physiological signals, such as plethysmogram signals or electrocardiogram signals, may be found in, for example, international patent application No. PCT/CN2015/077026 filed on 20/4/2015, international patent application No. PCT/CN2015/077025 filed on 20/4/2015, and international patent application No. PCT/CN2015/079956 filed on 27/5/2015, each of which is incorporated by reference.

In some embodiments, the physiological characteristics obtained in the characteristic identification unit 520 may be transmitted to the preprocessing unit 510 for correction of outliers. For example, a subject's plethysmogram waveform may be designated as training data. The set of training data may be stored in a database 133. The physiological characteristics of the plethysmogram waveform may be obtained in the characteristic identification unit 520 and transmitted to the preprocessing unit 510. The preprocessing unit 510 can calculate the cuk distance of the physiological characteristic of the plethysmogram waveform. If the Cockian distance is greater than C/N, the plethysmogram waveform as training data may be discarded. Where N is the number of training data and C is a preset value. In some embodiments, C may be selected as an integer greater than or equal to 4.

The pre-processing unit 510 may include one or more pre-processing sub-units (not shown in fig. 6). The pre-processing subunit may (not shown in fig. 6) perform one or more pre-processing steps in series (e.g., one pre-processing step is performed after another pre-processing step is started or completed) or in parallel (e.g., some pre-processing steps are performed at or near the same time) for pre-processing the acquired signal. The pre-processing unit 510 may control or coordinate the operation of pre-processing sub-units (not shown in fig. 6). The control or coordination may be performed by, for example, a controller (not shown in FIG. 6) within the pre-processing unit 510 or a controller external to the pre-processing unit 510. The pre-processing subunits may be arranged in series or in parallel.

The above description is intended to be illustrative, and not to limit the scope of the claims. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. For example, the pre-processing sub-units may be combined differently to achieve a better pre-processing effect. It should be noted that the preprocessing subunit is not necessary for the functional implementation of the system. Similar modifications are intended to fall within the scope of the claims.

The identification unit 520 is configured to analyze the acquired information to identify or determine a feature. In some embodiments, the acquired information may have been pre-processed before being processed in the identification unit 520. In the exemplary context of blood pressure monitoring, the acquired information may include a plethysmogram signal, an electrocardiogram signal, a ballistocardiogram signal, or the like, or a combination thereof; exemplary characteristics of the acquired information may include characteristic points, peaks, valleys, amplitudes, time intervals, phases, frequencies, periods, ratios, maximum slopes, start times, end times, Direct Current (DC) components, Alternating Current (AC) components, and the like, or any combination thereof, of a function of the plethysmogram waveform. The function of the waveform may be the same function, or a first derivative or higher derivative of the waveform.

The recognition unit 520 may be configured to analyze different types of information or different portions of information. The analysis may be performed by, for example, one or more identifying subunits (not shown in fig. 6). For example, the acquired information includes various types of physiological signals (e.g., a plethysmogram signal and an electrocardiogram signal), and may be analyzed by different recognition subunits. Exemplary methods employed in recognition unit 520 may include threshold methods, syntactic methods of pattern recognition, gaussian function suppression, wavelet transformation, QRS complex detection, linear discriminant analysis, quadratic discriminant analysis, decision trees, decision tables, neighbor classification, wavelet neural network models, support vector machines, genetic expression programming, hierarchical clustering, mean clustering analysis, bayesian network models, principal component analysis, kalman filtering, gaussian regression, linear regression, hidden markov models, association rules, inductive logic methods, and the like, or any combination thereof. The various methods may be used in parallel, or may be used in combination. For example only, the identification unit may use two different methods when processing two types of signals. As another example, the identification unit may use two different methods when processing one type of signal, e.g., one method after another.

The above description is intended to be illustrative, and not to limit the scope of the application. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. For example only, the analyzed features may be uploaded to a public cloud or a personal cloud and may be used in subsequent calculations or calibrations. As another example, an identification subunit (not shown in fig. 6) is not necessary for the functional implementation of the system. Similar modifications are intended to fall within the scope and ambit of this application.

The calculation unit 530 may be configured to perform various calculations to determine coefficients of a model or function, e.g., related to a physiological characteristic of interest, a mean, a median, and/or a standard deviation of the calculated blood pressure, etc., or a combination thereof. In some embodiments, the calculation unit 530 may attempt to reduce the number of physiological characteristics based on the personalized model of the subject. For example, the calculation unit 530 may calculate an akage information content criterion (AIC) value based on the physiological characteristic and the model selected for the subject. If the akabane information criterion value decreases after removing the physiological characteristic F1 from the group of physiological characteristics, the physiological characteristic F1 may be processed from the group of physiological characteristics. The process of processing physiological characteristics may be stopped when the akabane information criterion value increases. The physiological characteristic that remains after the process of processing the physiological characteristic may be referred to as an "effective physiological characteristic". The calculation unit 530 may include one or more calculation subunit (not shown in fig. 6) to perform the calculation. The physiological characteristic of interest may include, for example, Pulse Transit Time Variation (PTTV), blood pressure, systolic blood pressure, diastolic blood pressure, pulse rate, heart rate variability, heart murmur, blood oxygen saturation, blood density, blood oxygen level, or the like, or any combination thereof.

Exemplary methods that may be employed in the calculation unit 530 may include direct mathematical calculations, indirect mathematical calculations, compensation calculations, vector operations, function operations, wave velocity estimations, equation feature estimations, strain estimations, and the like, or any combination thereof. One or more computing models may be integrated in the computing subunit, or the computing models may be placed in the server 120, or the computing models may be placed in a public cloud. When different coefficients or physiological characteristics are to be calculated, different models may be loaded. For example, a linear calculation model in a calculation subunit may be used to calculate the systolic blood pressure, while another non-linear calculation model in another calculation subunit may be used to calculate the diastolic blood pressure. The initial data or intermediate results for calculating the physiological characteristic of interest may be retrieved or loaded from the information collection module 210, the analysis module 220, the server 120, the external data source 130, the peripheral device 240, or the like, or any combination thereof. External data sources 130 may include information from medical institutions 131, research facilities 132, databases 133, and peripherals 134. The initial data and the intermediate results may be combined in various ways in the calculation unit 530.

The above description is intended to be illustrative, and not to limit the scope of the application. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. In one embodiment, the calculated coefficients or the calculated physiological characteristics may be used as intermediate results for further analysis. In another example, an individual physiological characteristic of interest or a set of related physiological characteristics of interest may be calculated by the computing unit.

The calibration unit 540 may be configured to perform calibration. Calibration (also referred to as a calibration process or calibration step) may include one or more steps of retrieving calibration data (or calibration values) for a subject; acquiring a set of information of a subject using a device to be calibrated or used in a subsequent process (e.g., a wearable or portable device); a calibration model, or a portion thereof, or the like, of the calibrated device relative to the object, or a combination thereof, is determined. The set of acquired information may include information provided by the subject or a user other than the subject, or information acquired by using the device to be calibrated, or the like, or combinations thereof. The calibration data set may include a particular physiological characteristic of interest obtained during a calibration procedure, and the acquired set of information relates to the particular physiological characteristic of interest during the same calibration procedure.

For example only, the device to be calibrated may calculate blood pressure (including systolic and diastolic blood pressures) based on a personalized model selected for the subject and the effective physiological characteristics. In some embodiments, the device to be calibrated may be part of a system other than the calibration unit 540. The calibration data set may include systolic and diastolic blood pressures, both measured by a healthcare provider in the hospital, as well as corresponding electrocardiogram waveforms and corresponding plethysmogram waveforms acquired using the device to be calibrated. The corresponding electrocardiogram waveform and the corresponding plethysmogram waveform acquired using the device to be calibrated may correspond to systolic and diastolic blood pressures measured by a healthcare provider. The corresponding electrocardiogram waveform and the corresponding plethysmogram waveform may be acquired using the device to be calibrated at or near the time that the healthcare provider measures systolic and diastolic blood pressure.

In some embodiments, the calibration data set may include systolic blood pressure, diastolic blood pressure, and corresponding electrocardiogram and corresponding plethysmogram waveforms, all of which are acquired using the device to be calibrated. For example, the calibration unit 540 may include or communicate with a cuff-based blood pressure monitor. The cuff-based blood pressure monitor may be integrated into or as part of a system or device (e.g., a computing unit, an information collection module, etc.). For example, a cuff-based blood pressure monitor, an electrocardiograph monitor that can obtain electrocardiographic information, and one or more plethysmogram sensors can be packaged into or as part of a device, system, or the like. Cuff-based blood pressure monitors can measure systolic and diastolic blood pressure at certain time intervals (e.g., 15 minutes, 30 minutes, 1 hour, 2 hours, one day, etc.). The calibration data set may be automatically acquired based on default settings of the system or preset by the subject or a user (also referred to as a third party) other than the subject. An exemplary third party may be a doctor, a healthcare worker, a medical institution, a research institution, a peripheral to the subject, or a user in good connection with the subject, etc. The calibration data set acquired by the calibration unit 540 may be transmitted to the calculation unit 530 or other modules or units in real time. The calibration data set may be stored in a storage device disclosed anywhere in this application, or may be stored in the server 120. The calibration data set may be automatically loaded from a storage device or server 120 if desired.

One or more calibration data sets may be used to determine the coefficients of the calibration model or some other part of the calibration model. The calibration model may be used in a subsequent procedure to calculate the physiological characteristic of interest based on another set of information acquired using the calibration device. In a subsequent process, the calibration apparatus may acquire the same or similar set of information as that acquired for calibration. For example, another set of information may include information acquired using the same device as used in the calibration (e.g., a device including one or more sensors), information of the same type as the information obtained in the calibration (e.g., age of the subject, time of day of acquisition, physiological or psychological state of the subject, etc., or a combination thereof), etc., or a combination thereof. The calibrated model may be used to calculate or estimate the physiological characteristic of interest accordingly. Exemplary methods that may be used in calibration to obtain the calibration model may include regression analysis, linear analysis, functional operations, reconstruction, fourier transform, laplace transform, and the like, or combinations thereof.

In the calibration process, the calibration data set may include specific physiological characteristics of interest obtained based on measurements using one or more devices other than the device to be calibrated. By way of example only, the particular physiological characteristic of interest may be obtained based on measurements performed on the subject by the calibration unit 540 (e.g., cuff-based blood monitor). As another example, the particular physiological characteristic of interest may be obtained based on measurements performed on the subject by a healthcare professional in a hospital or doctor's office. As another example, the particular physiological characteristic of interest may be obtained based on measurements performed on the subject by the subject or others using a clinical device or a home device. For example, the physiological characteristic of interest may be measured using a device including, for example, an auscultation device, an oscillometric device, an electrocardiogram management device, a plethysmogram management device, or the like, or any combination thereof.

During the calibration process, the calibration data set may include specific physiological characteristics previously calculated or estimated by the system or a portion of the system. By way of example only, the physiological characteristic of interest that the system calculates based on the acquired set of information and the calibration function in the system may be used for a next calibration to update or generate a calibrated model, and the updated calibration model may subsequently be used to calculate the physiological characteristic of interest (first aspect of the calibration process described above). As another example, the physiological characteristic of interest calculated by the system based on the acquired set of information and the calibration function in the system may be used in the next measurement of the physiological characteristic of interest (the second aspect of the calibration process described above). The calculated physiological characteristics of interest of the subject may be stored in a storage device or server 120 disclosed anywhere in the application for later use in conjunction with the subject or other subjects.

In an exemplary context of estimating a subject's blood pressure (including systolic and diastolic blood pressures), based on pulse transit time, a correlation between BP and pulse transit time may be represented by a model including a mathematical process and a factorial function, and the factorial function may include a function (f) and a coefficient (B). As used herein, calibration may include at least two aspects. A first aspect is to determine a model based on one or more sets of calibration data (or calibration values). The determined model may be referred to as a calibration model. To use the calibration model in a particular measurement, signals need to be acquired to provide the pulse transit time and calibration data set including PTT0, SBP0, and DBP 0. In addition to pulse transit time, the correlation between blood pressure and pulse transit time may depend on other elements. For example only, the correlation between blood pressure and pulse transit time may depend on heart rate variability, pulse transit time variations, in addition to pulse transit time. To use the calibrated model in a particular measurement, signals need to be acquired to provide pulse transit time, heart rate variability and pulse transit time variation, as well as calibration data sets including PTT0, SBP0, DBP0, HRV0 and PTTV 0.

The first aspect of calibration may be performed using individualized calibration data related to object or peer-to-peer data or empirical data. This aspect of calibration may be performed in real time as the particular measurement is being performed. A model for estimating blood pressure based on pulse transit time in a particular measurement may be derived based on one or more calibration data sets. The selection of one or more calibration data sets may be based on the pulse transit time in a particular measurement. This aspect of calibration may be performed off-line, independent of the particular measurement.

A second aspect of the calibration comprises acquiring a calibration data set to be applied in a calibration model, such that the blood pressure can be estimated based on the pulse transit time acquired in a particular measurement, from the model and the calibration data set shown. In some embodiments, the calibration data set to be used in a particular measurement may be selected from, for example, at least two calibration data sets. The at least two calibration data sets may include individualized data relating to the subject, peer-to-peer data, or empirical data. At least two calibration data sets may be stored in the system, for example, in the repository 900 (see fig. 1). The at least two calibration data sets may be stored in a server that is part of the system or accessible from the system. In some embodiments, the calibration data set may be selected based on the pulse transit time in a particular measurement.

The calibration model for a particular object may be based on calibration data for the same object. The calibration model for a particular object may be based on a combination of calibration data for the same object and calibration data from a set of objects (e.g., peer-to-peer data discussed elsewhere in this application). The calibration model for a particular object may be based on calibration data from a set of objects (e.g., peer-to-peer data or empirical data discussed elsewhere in this application). The specific object may be included in the group or excluded. The calibration data may be stored in a storage device or server 120, etc., disclosed anywhere in this application, or a combination thereof. Personalized calibration data for different objects may be stored in the server 120 or in respective personal accounts for each object in the personal cloud. Calibration data from various subjects may be stored in a non-personalized database for future use. For example, calibration data from various objects may be partitioned based on one or more characteristics of the respective objects. Exemplary characteristics may include, for example, age, gender, height, weight, percentage of body fat, skin color, family health history, lifestyle, exercise or other habits, diet, mental condition, health condition, educational history, occupation, and the like, or combinations thereof. In some embodiments, a portion of the calibration data so partitioned (e.g., peer-to-peer data discussed elsewhere in this application) may be used for calibration purposes by a set of objects sharing the same or similar characteristics.

The above description is intended to be illustrative, and not to limit the scope of the application. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. For example, a memory unit (not shown in fig. 6) may be added to the calibration unit 540 or the calculation unit 530, or a combination thereof. The storage unit in the calibration unit 540 may store calibration data or historical data related to the calibration process. The storage unit related to the calculation unit 530 may store calculation models or data related to calculation processing. In addition, peer-to-peer data may be used as initial data or intermediate results during calibration.

The analysis module 220 may be implemented on one or more processors. The various units of the analysis module 220 may be implemented on one or more processors. For example, the pre-processing unit 510, the identifying unit 520, the calculating unit 530, and the calibrating unit 540 may be implemented on one or more processors. One or more processors may utilize storage devices (not shown in fig. 6), information acquisition modules 1, 2, and 3, peripheral devices 240, and server 120 to transmit signals or data. The one or more processors may retrieve or load signals, information, or instructions from a storage device (not shown in fig. 6), the information acquisition modules 1, 2, and 3, the peripheral device 240, or the server 120, and process the signals, information, data, or instructions, or a combination thereof, to perform preprocessing, calculate one or more physiological characteristics of interest, calibration, or the like, or a combination thereof. The one or more processors may also be connected or in communication with other devices related to the system 100 and transmit or share signals, information, instructions, physiological characteristics of interest, etc. with such other devices through, for example, a mobile phone APP, a local or remote terminal, etc., or a combination thereof.

Fig. 6 is a flow diagram of an exemplary process for estimating blood pressure according to some embodiments of the present application. Beginning at step 610, information including a first signal and a second signal may be obtained. For example, the first signal may be an electrocardiogram signal and the second signal may be a plethysmogram signal. The first signal and the second signal may be associated with an object. Acquisition of the signal may be performed by the information acquisition module 210. In some embodiments, the first and second signals may be acquired simultaneously at or near the same time. In some embodiments, one signal may be acquired before another signal. In some embodiments, information comprising or relating to the first signal or the second signal may be obtained at step 610. For example, information about the subject's personal data, such as age, weight, height, and historical medical history, may be obtained. For another example, basic information related to the object and/or environment information may be acquired.

For example only, the first signal or the second signal may be a physiological signal, such as an electrocardiogram signal, a pulse-wave-related signal (e.g., a plethysmogram (PPG)), a Phonocardiogram (PCG) signal, an impedance electrocardiogram (ICG) signal, or the like, or any combination thereof. In some embodiments, the first signal and the second signal may be of different types. For example, the first and second signals may be a combination of an electrocardiogram signal and a plethysmogram signal, a combination of an electrocardiogram signal and an phonocardiogram signal, a combination of an electrocardiogram signal and an impedance electrocardiogram signal, and the like. In some embodiments, the first signal and the second signal may be of the same type. For example, the first and second signals may be two vessel volume map signals, which may be detected at different locations on the body of the subject. Exemplary locations on the subject's body may include, for example, fingers, radial arteries, ears, wrists, toes, or locations more suitable for movement monitoring in current sensor designs.

At step 620, at least some of the acquired information may be pre-processed. In some embodiments, the acquired first and second signals may be pre-processed. Preprocessing may be performed to reduce or remove noise or errors in the signal or signal-related data. Exemplary methods that may be used in the pre-processing may include low pass filtering, band pass filtering, wavelet transforms, median filtering, morphological filtering, curve fitting, hilbert-yellow transforms, and the like, or any combination thereof. In the course of the pretreatment, the methods mentioned in the present application can be used in parallel or can be used in combination. Description of methods and systems for reducing or eliminating noise in physiological signals, such as plethysmogram signals or electrocardiogram signals, may be found in, for example, international patent application No. PCT/CN2015/077026 filed on 20/4/2015, international patent application No. PCT/CN2015/077025 filed on 20/4/2015, and international patent application No. PCT/CN2015/079956 filed on 27/5/2015, each of which is incorporated by reference. Additionally, a real-time transformation of the time or frequency domain may also be implemented in step 820, and the signal or related information may be used in the time domain, frequency domain, wavelet domain, or all of these.

At step 630, characteristics of the first and second signals may be identified or determined. In the exemplary context of blood pressure monitoring, the first signal or the second signal may comprise a plethysmogram signal, an electrocardiogram signal, a ballistocardiogram signal, or the like; exemplary characteristics of the first signal or the second signal may include characteristic points, peak points, valley points, amplitudes, time intervals, phases, frequencies, periods, ratios, maximum slopes, start times, end times, Direct Current (DC) components, Alternating Current (AC) components, and the like, or any combination thereof, of a function of a vessel volume map waveform. The function of the waveform may be the same function, or the first derivative or higher derivative of the waveform. For example, one feature point may be a peak or valley of the first signal, e.g., a peak or valley of an R-wave of an electrocardiogram signal, a fastest rising point of a plethysmogram signal, a higher moment or higher derivative of a plethysmogram signal, a pulse area of a plethysmogram signal, a maximum positive peak of S2 of a phonocardiogram signal, or a peak of an impedance electrocardiogram signal, etc.

At step 640, the data set including the identified physiological characteristic and the personal data of the subject may be purged. By cleaning the data set, outliers within the data set may be removed or corrected. For example, for a plethysmogram waveform consisting of tens of heart beat cycles, the mean, median and/or standard deviation of the maxima/minima of the plethysmogram waveform over each heart beat cycle may be calculated. A threshold may be specified to specify an outlier within the plethysmogram waveform. If the standard deviation of the maxima/minima of the plethysmogram waveform over each heart beat cycle is less than a threshold, the plethysmogram waveform may be flagged as outliers and discarded. Similarly, the personal data of the subject may be cleansed. A trusted interval of values of personal data may be set. Any personal data outside of the trusted interval may be marked as suspect and needs to be corrected. For example, if the height of the object is 5cm, and/or the weight of the object is 5 kilograms, the personal data of the object may be marked as suspicious and needs to be corrected.

A preprocessing step may be performed to evaluate the acquired signal (e.g., an electrocardiogram signal, a plethysmogram signal, etc.) before one or more features of the signal are identified. For example, the acquired electrocardiogram signal may be accessed prior to identifying one or more features of the signal. An evaluation may be performed to assess whether a valid electrocardiogram signal was acquired. The evaluation may be performed by, for example, a pattern recognition process. For example, the R peak of the acquired electrocardiogram signal may be determined by a pattern recognition process. In some embodiments, the system may identify an abnormal signal or waveform (e.g., an abnormal sinus rhythm R-wave, another physiological signal, etc.) that may not be suitable for deriving a physiological characteristic; such an abnormal signal or waveform may be discarded to avoid its participation in subsequent calculations or analyses. In some embodiments, the acquired electrocardiogram signal may be compared to a reference signal to determine whether the acquired electrocardiogram signal includes abnormal R-waves. The reference signal may be a normal sinus rhythm electrocardiogram signal or may be retrieved from a database having historical data.

The electrocardiogram and plethysmogram waveforms are cyclic signals, i.e., the characteristic points occur substantially cyclically or periodically. Thus, during the identification of feature points of the vessel volume map waveform, a threshold value may be set with respect to a time window or segment within which feature points on the vessel volume map waveform may be identified and used for determining physiological features. In one example, the time window may be tens of heart beat cycles. By way of example only, the analysis for identifying fiducial points on the plethysmogram waveform is performed on segments of the plethysmogram waveform occurring within 2 seconds of the time point at which the maximum point on the electrocardiogram waveform is identified, in order to obtain the physiological characteristic. As another example, the analysis to identify fiducial points on the plethysmogram waveform is performed on segments of the plethysmogram waveform that occur between two consecutive peak points on the electrocardiogram waveform in order to approximate the pulse transit time. As a further example, the time window may be set based on the heart rate of the subject. For example, the time window may be set based on the heart rate of the subject at or near the time of acquisition, or the average heart rate of the subject over a period of time, or the average heart rate of a group of people (e.g., a subset of people having the same or similar characteristics as the subject); exemplary characteristics may include age, gender, country, height, weight, percentage of body fat, family health history, lifestyle, athletic or other habits, diet, occupation, medical history, educational background, marital status, etc., or any combination thereof.

The circulation of the electrocardiogram or the circulation of the vascular volume map may vary. As an example, the circulation of an electrocardiogram or the circulation of a vessel volume map of different subjects may be different. As another example, the circulation of an electrocardiogram or a plethysmogram of the same subject may vary in different circumstances (e.g., when the subject is moving or sleeping at different times of the day, at the same or similar times on different days), etc., or a combination thereof. In one example, the time window threshold may be set based on the heart rate of the subject (e.g., the heart rate of an average person is approximately 60-120 times per minute). The heart rate may be an average over a period of time (e.g., one week, one month, one year, etc.). The heart rate may be a heart rate measured at or near the time of acquisition. The heart rate may be measured based on, for example, an electrocardiogram signal, a plethysmogram signal, etc. The time window may be set or updated based on the measured heart rate. In another example, the time window may be set by, for example, the system, the subject, or a user other than the subject, based on physiological information of the subject. For example, the physiological information may include exercise or not, whether to take medication, mood, emotional stress, or the like, or a combination thereof. As another example, the time window may be a fixed value defined by the system, the subject, or a user other than the subject (e.g., his physician, healthcare provider, etc.).

At step 650, at least two models and a cost function may be obtained. The model to be selected may be of one of the following forms:

where Sbp is systolic pressure and Dbp is diastolic pressure. gsbp (), gdbp (), gbpdiff (), glnsbp (), glndbp (), are structural components (non-random) of a prediction function of the demographic information of the subject, inputting the physiological characteristics, such as characteristic points of the vascular volume map signal. The functional relationship may be linear, non-linear, regression tree, or a random forest determined by a cost function. An example of a linear function takes the form: g (X)₁，X₂，..)＝β₀+β₁X₁+β₂X₂.. betai is the model coefficient to be determined, xi is the valid physiological characteristic, i 1, 2,. M, where M is the number of selected physiological characteristics and id is the personal variable associated with the subject. The structural components gsbp (), gdbp (), gbpdiff (), glnsbp (), glndbp (), are set to be constant in the general population, while r (id) represents the individual-specific prediction functionThe random component of (a). In some embodiments, the structural components gsbp (), gdbp (), gbpdiff (), glnsbp (), glndbp (), may depend on training data and/or calibration data. The cost function to be selected may be the mean, median, standard deviation of the prediction error of the test data.

At step 660, feature extraction for each model may be performed by probability-based principles such as the Akabane Information Criterion (AIC), the Bayesian Information Criterion (BIC), by cross-validation methods, or by shrinkage-based methods. The optimal subset of physiological features that will result in the least cross-validation prediction error can be determined using the methods described above. As a data-driven approach, the elements of the optimal subset may vary according to population (e.g., gender and/or age), blood pressure measurement location, and so forth.

At step 670, a personalized model may be determined based on the cost function and the valid physiological characteristics obtained at step 660. For example, a cost function may be selected as the standard deviation of the prediction error of the test data. Based on the behavior of the models listed in step 650, the model with the smallest standard deviation of the prediction error of the test data may be designated as the personalized model for the subject.

At step 680, a Blood Pressure (BP) value of the subject may be calculated based on the personalized model and effective physiological characteristics, such as a maximum and minimum value of a slope of a plethysmogram pulse wave, a Direct Current (DC) component of the plethysmogram pulse wave, a plethysmogram pulse wave Alternating Current (AC) component, a determined Pulse Transit Time (PTT), a Pulse Transit Time Variation (PTTV), a heart rate variability, and the like, or combinations thereof. The personalized models may include linear function based models, non-linear function based models, regression tree/random forest based models.

While what has been described above is considered to constitute this application and/or other examples, it is to be understood that various modifications may be made thereto, and that the subject matter disclosed herein may be implemented in various forms and examples, and that the disclosure may be applied in numerous applications, only some of which have been described herein. Those skilled in the art will appreciate that various modifications and improvements may be made to the disclosure herein. For example, the pre-processing step 530 may not be necessary. In addition, if necessary, a third signal may be acquired, and the third signal may be a signal having the same type as the first signal or the second signal or may be a signal different from the first signal or the second signal.

Fig. 7 illustrates an example monitoring device 700 according to some embodiments of the present application. Monitoring device 700 may include measurement module 710, electrodes 720, finger grips 730, and/or terminals 740. The monitoring device 700 may be connected or otherwise in communication with a terminal 740.

The measurement module 710 may be configured to obtain information, such as an electrocardiogram signal, a plethysmogram signal, blood oxygenation information, or the like, or a combination thereof. The measurement module 710 may also be configured to analyze and process the acquired information, or to determine or estimate a physiological characteristic of interest, or to determine blood pressure, etc.

According to an embodiment, the measurement module 710 includes: an electrocardiogram acquisition unit configured to acquire an electrocardiogram signal by an electrical sensing method, and a plethysmogram signal acquisition unit configured to acquire plethysmogram signal-related information by an electro-optical sensing method. The acquired signals or information may be stored in server 120, or in a memory device (not shown in fig. 7) integrated in measurement module 710, or any memory device disclosed anywhere in this application.

The monitoring device 700 may be a wearable device, a portable device, a medical monitoring device in a hospital, or a medical monitoring device in a home, etc. As can be seen, at least two electrodes 720 are located on the chest of the subject, and the electrodes are configured to record one or more potential changes of the subject. The change in electrical potential may constitute an electrocardiogram waveform, and the electrocardiogram waveform may be transmitted to the measurement module 710 via one or more wires. It can also be seen that one or more photoelectric sensors 730 are located on the subject's finger, and that the photoelectric sensors are configured to detect one or more plethysmogram signals or pulse related signals. The detected signal may be transmitted to the measurement module 710 by wire or wirelessly. In this embodiment, one or more photosensors are located on a finger of the subject, and the arrangement or positioning is for illustration purposes only. In one example, one or more photosensors may be located on an upper arm of the subject.

According to an embodiment, the calibration module 740 may include a cuff-based blood pressure monitor. The cuff-based blood pressure monitor may be configured to acquire systolic and diastolic blood pressure values, which may be used as calibration data (e.g., SBP0, DBP0, PTT0, etc., or a combination thereof) during one or more measurement procedures of measurement module 710. As shown, the cuff-based blood pressure monitor may include a cuff, a pneumatic device (not shown in fig. 7), a connection cord (not shown in fig. 7), a transceiver (not shown in fig. 7), and/or a controller (not shown in fig. 7). The cuff may have an internal airtight pocket that may be secured to a portion of the subject to apply pressure. For example, the cuff may encircle the upper arm of the subject to apply pressure. The pneumatic devices may include pumps, valves, analog/digital converters, and the like. In acquiring the calibration data, the pneumatic device may inflate the cuff and acquire at least two data (e.g., SBP0, DBP0, etc., or a combination thereof). The acquired data may be sent by connection 750 to a transceiver (not shown in fig. 7) for subsequent processing.

The acquired electrocardiogram signal, plethysmogram signal, calibration data (e.g., SBP0, DBP0, PTT0, or the like, or a combination thereof) may be sent to the measurement module 710 for calculating the subject's blood pressure value. The calculation may be performed by the measurement module 710 or may be performed by an analysis module (not shown) integrated in the measurement module 710. In some embodiments, as shown in fig. 7, measurement module 710 may be a wearable or portable device separate from and capable of communicating with one or more photosensors 730, electrodes 720, and/or calibration module 740. In some embodiments, measurement module 710 may be packaged with calibration module 740. For example, the measurement module 710 may be attached to a cuff of the calibration module 740.

Prior to the calculation, one or more operations may be performed, such as preprocessing, feature identification, feature estimation, calibration, and the like, or a combination thereof. Further description of the analysis can be found in international patent application No. PCT/CN2015/083334 filed on 3/7/2015 and international patent application No. PCT/CN/2015/096498 filed on 5/12/2015. The details may be displayed in the terminal 740 or may be transmitted to an associated third party (e.g., a medical facility). The details may be displayed in a display device of the measurement module 710 (see fig. 7).

Monitoring device 700 may also include one or more additional components, including WIFI devices, bluetooth devices, NFC devices, GPS devices, the like, or combinations thereof. For example, a WIFI device may be used to connect to a wireless network. Bluetooth devices may be used for data transformation between some wired or wireless terminals within a certain distance. NFC devices may be used to enable terminals to establish radio communication over short distances (10cm or less). The GPS device may allow the object to find its own location, or the GPS device may be used for navigation, etc., or a combination thereof. Additional components may be connected or otherwise in communication with measurement module 710, calibration module 740, terminal 740, and server 120.

The monitoring device 700 may be used in a healthcare facility (e.g., a hospital), or may be used at home. The monitoring device 700 may be used for real-time physiological characteristic monitoring. The acquired signals, information, data or calculated physiological characteristics of interest may be displayed in real time in a display device (not shown) or terminal 740. The subject, a user other than the subject (e.g., a doctor), can view the relevant information anytime and anywhere. In some embodiments, if the monitoring device 700 is used at home, the monitoring device 700 may communicate with a healthcare provider located at a location remote from the subject. The communication may be performed directly by the monitoring and monitoring device 700 or indirectly through, for example, a terminal 740 carried by the subject. The physiological characteristics of the subject as well as the location information may be sent to the healthcare provider in real time, periodically, or upon the occurrence of a triggering event. Exemplary triggering events are described elsewhere in this application. When an emergency occurs, for example, a physiological characteristic exceeds a threshold, a healthcare provider may be notified, an object may be located based on location information from a GPS or location sensor, and medical services may be provided accordingly.

Fig. 8 is a flow chart of an exemplary process for estimating blood pressure using the disclosed methods according to some embodiments of the present application. Beginning at step 810, calibration data for a subject can be obtained. The calibration data may be an electrocardiogram waveform and a plethysmogram waveform, along with blood pressure (including systolic and diastolic blood pressure) measured using conventional korotkoff sounds or oscillometry. Calibration data for the subject may be stored in the database 133. In some embodiments, calibration may be performed while the subject is standing, sitting, or lying in bed. The calibration may be performed at different times of the day, which may be the same or different. For example, the calibration may be performed in the morning, noon, and/or evening of a day.

At step 820, information including information related to the first signal and the second signal object may be obtained, along with a personalized model of the object. The personalized models may be predetermined, one model being selected among the models 123 shown in fig. 1. The first signal may be an electrocardiogram signal. The second signal may be a vessel volume map signal. In some embodiments, personal data about the subject may also be obtained at step 820.

At step 830, at least some of the acquired information may be pre-processed to handle exception signals. For example, a portion of the vessel volume map signal may be abnormal and need to be discarded. At step 840, the first signal, the second signal, and the personalized model of the subject may be used to obtain an effective physiological characteristic. The valid physiological characteristics can be used as model variables and the personal data of the subject can be used as the personal variable id of the personalized model.

At step 850, a blood pressure may be calculated based on the effective physiological characteristics of the first and second signals using the specified personalized model and the subject's likely personal data. The subject's blood pressure may be output at step 860.

FIG. 9 depicts an architecture that may be used to implement a mobile device that includes the application specific system of the present application. In this example, the device on which the information related to blood pressure monitoring is presented and interacted with (e.g., terminal 140) is a mobile device 900, including but not limited to smartphones, tablets, music players, process game consoles, Global Positioning System (GPS) receivers, wearable computing devices (e.g., glasses, watches, etc.), and the like. The mobile device 900 in this example includes one or more Central Processing Units (CPUs) 940, one or more Graphics Processing Units (GPUs) 930, a display 920, memory 960, a communication platform 910, such as a wireless communication module, memory 990, and one or more input/output (I/O) devices 950. Any other suitable components, including a system bus or controller (not shown), may also be included in mobile device 900. As shown in fig. 9, a mobile operating system 970 (e.g., iOS, Android, Windows Phone, etc.) and one or more application programs 980 may be loaded from storage 990 into memory 960 for execution by CPU 940. Application 980 may include a browser or any other suitable mobile application for receiving and presenting information on mobile device 900 related to blood pressure monitoring or other information from engine 200. User interaction with the information flow may be implemented via the I/O device 950 and provided to the engine 200 and/or other components of the system 100, e.g., via the network 150.

To implement the various modules, units, and functions thereof described herein, a computer hardware platform may serve as a hardware platform for one or more elements described herein (e.g., engine 200, and/or other components of system 100 described in fig. 1-8). The hardware elements, operating systems, and programming languages of such computers are conventional in nature, and it is assumed that one skilled in the art would be familiar with these techniques and would be able to apply these techniques to the blood pressure monitoring described herein. The Computer containing the user interface elements may be used as a Personal Computer (PC) or other type of workstation or terminal device, suitably programmed, and may also be used as a server. It is believed that one skilled in the art will be familiar with the structure, programming, and general operation of such computer devices, and thus the drawings should not be self-explanatory.

FIG. 10 depicts an architecture that may be used to implement a computing device that includes the application specific system of the present application. This particular system of the present application has a functional block diagram illustration of a hardware platform that includes user interface elements. The computer may be a general purpose computer or may be a special purpose computer. Both computers can be used to implement the particular system of the present application. The computer 1000 may be used to implement any of the components of the presently described blood pressure monitoring. For example, the engine 200, etc. may be implemented on a computer such as the computer 1000 by hardware, software programs, firmware, or a combination thereof of the computer. Although only one such computer is shown, for convenience, the computer functions related to blood pressure monitoring described herein may be implemented in a distributed manner on a plurality of similar platforms to distribute the processing load.

The computer 1000 includes, for instance, a communication port 1050 for connecting to a network to facilitate data communication. The computer 1000 also includes a Central Processing Unit (CPU)1020 in the form of one or more processors for executing program instructions. The exemplary computer platform includes an internal communication bus 1010, a program storage device, and various forms of data storage, such as a disk 1070, Read Only Memory (ROM)1030, or Random Access Memory (RAM)1040, for various data files to be processed and/or transmitted by the computer, and program instructions that may be executed by the CPU. The computer 1000 also includes I/O components 1060 that support input/output between the computer and other components therein, such as user interface elements 1080. The computer 1000 may also receive programs and data through network communication.

Thus, as described above, aspects of the methods of blood pressure monitoring and/or other procedures may be embodied in programming. The procedural aspects of the technology may be considered an "article of manufacture" or an "article of manufacture" typically in the form of executable code and/or associated data executed or embodied in a machine-readable medium. Tangible, non-transitory "storage" type media include any or all of the memory or storage used by a computer, processor, or similar device or associated module, such as various semiconductor memories, tape drives, disk drives, etc., any of which may provide storage for software programming.

All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication may, for example, load software from one computer device or processor to another, e.g., from a management server or host computer of the engine 200 to a hardware platform of a computing environment, or other system implementing a computing environment, or a system implementing similar functionality related to blood pressure monitoring.

Thus, another type of medium that may carry software elements includes optical, electrical, and electromagnetic waves, for example, through physical interfaces between local devices, through wired and optical land line networks, and through the use of various air links. The physical elements carrying such waves, e.g. wired or wireless links, optical links, etc., may also be considered as media carrying software. As used herein, unless limited to a tangible "storage" medium, other terms referring to a computer or machine "readable medium" refer to media that participate in the execution of any instructions by a processor. Thus, a machine-readable medium may take many forms, including a tangible memory medium, a carrier wave medium, or a physical transmission medium. Non-volatile storage media include, for example, optical or magnetic disks, such as any storage device in any computer or similar device, which may be used to implement the system as shown in the figures or any component thereof. Volatile storage media includes dynamic memory, such as the main memory of a computer platform. Tangible transmission media include coaxial cables; copper wire and fiber optics, including the wires that form a bus within a computer system. Carrier-wave transmission media can take the form of electrical or electromagnetic signals, or acoustic or light waves, such as those generated during Radio Frequency (RF) and Infrared (IR) data communications. Common forms of computer-readable media include a hard disk, floppy disk, magnetic tape, any other magnetic medium; CD-ROM, DVD-ROM, any other optical medium; punch cards, any other physical storage medium containing a pattern of holes; RAM, PROM, EPROM, FLASH-EPROM, any other memory chip or cartridge; a carrier wave transmitting data or instructions, a cable or a connection device transmitting a carrier wave, any other program code and/or data which can be read by a computer. These computer-readable media may take the form of instructions, or other data, which can be executed by a processor to cause a series of operational steps to be performed on the processor.

Those skilled in the art will appreciate that various modifications and improvements may be made to the disclosure herein. For example, while the implementation of the various components described above may be embodied in a hardware device, it may also be implemented as a software-only solution-e.g., installation on an existing server. Further, the blood pressure monitoring systems disclosed herein may be implemented as firmware, a firmware/software combination, a firmware/hardware combination, or a hardware/firmware/software combination.

Having thus described the basic concepts, it will be apparent to those of ordinary skill in the art having read this application that the foregoing disclosure is to be construed as illustrative only and is not limiting of the application. Various alterations, modifications and improvements will readily occur to those skilled in the art, though not expressly described herein. Such alterations, modifications, and variations are suggested in the present application and are intended to be within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific terminology to describe embodiments of the application. For example, the terms "an embodiment," "an embodiment," and/or "some embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics may be combined as suitable in one or more embodiments of the application. Additionally, the term "logic" represents hardware, firmware, software (or any combination thereof) to perform one or more functions. For example, examples of "hardware" include, but are not limited to, an integrated circuit, a finite state machine, or even combinatorial logic. The integrated circuit may take the form of a processor, such as a microprocessor, an application specific integrated circuit, a digital signal processor, a microcontroller, or the like.

Moreover, those of ordinary skill in the art will understand that aspects of the present application may be illustrated and described in terms of several patentable species or contexts, including any new and useful combination of processes, machines, articles, or materials, or any new and useful modification thereof. Accordingly, aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of software and hardware implementations, which may all generally be referred to herein as a "circuit," unit, "" module, "" component, "or" system. Furthermore, aspects of the present application may be presented as a computer program product having computer-readable program code embodied in one or more computer-readable media.

A computer readable signal medium may comprise a propagated data signal with computer program code embodied therewith, for example, on baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including electromagnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable signal medium may be transmitted using any appropriate medium, including wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, conventional programming languages such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy, or other programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer, partly on a remote computer or entirely on the remote computer or server. In the latter case, the remote calculator may be connected to the user calculator through any form of network, for example, a Local Area Network (LAN) or a Wide Area Network (WAN), or connected to an external calculator (e.g., through the internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

Furthermore, unless explicitly stated in the claims, the order of processing elements and sequences, the use of numbers, letters, or other designations in the present application is not intended to limit the order of the processes and methods in the present application. While various presently contemplated embodiments have been discussed in the foregoing disclosure by way of example, it should be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments of the disclosure. For example, while the implementation of the various components described above may be embodied in a hardware device, it may also be implemented as a software-only solution-e.g., installation on an existing server or mobile device. Further, the systems disclosed herein may be implemented as firmware, a firmware/software combination, a firmware/hardware combination, or a hardware/firmware/software combination.

Similarly, it should be appreciated that in the foregoing description of embodiments of the invention, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the various embodiments disclosed. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed subject matter requires more features than are expressly recited in each claim. Rather, embodiments of the invention should possess fewer features than the single embodiment described above.