阅读说明：本技术 在脊柱疾病技术领域中用于客观结果评估的可穿戴传感器设备和分析平台 (Wearable sensor device and analysis platform for objective outcome assessment in the field of spinal disease technology ) 是由 N·M·本森 R·L·布朗 N·H·梅特卡夫 C·B·诺加德 S·D·格拉斯曼 S·伯奇 于 2019-09-12 设计创作，主要内容包括：用于评估脊柱病症的系统包括具有一个或多个传感器的可穿戴电子设备和评估系统。可穿戴电子设备被配置为位于穿戴者的下背部的一部分上,并且一个或多个传感器被配置为获取与穿戴者相关的患者数据。该系统从一个或多个传感器接收患者数据,其中患者数据包括与穿戴者的下背部的运动相关联的运动数据；将运动数据分类为初始分组；进一步将运动数据的至少一部分分类为多个活动类别之一；基于运动数据被分类到的活动类别,生成与运动数据的至少一部分相对应的分数；并且使该分数经由客户端电子设备显示。(A system for assessing a spinal disorder includes a wearable electronic device having one or more sensors and an assessment system. The wearable electronic device is configured to be positioned on a portion of a lower back of a wearer, and the one or more sensors are configured to acquire patient data related to the wearer. The system receives patient data from one or more sensors, wherein the patient data includes motion data associated with motion of a lower back of a wearer; classifying the motion data into an initial group; further classifying at least a portion of the athletic data into one of a plurality of activity categories; generating a score corresponding to at least a portion of the athletic data based on the activity category into which the athletic data is classified; and cause the score to be displayed via the client electronic device.)

1. A system for assessing a spinal disorder, the system comprising:

a wearable electronic device comprising one or more sensors, wherein the wearable electronic device is configured to be positioned on a portion of a wearer's lower back and the one or more sensors are configured to acquire patient data related to the wearer,

an evaluation system, comprising:

a computing device, and

a computer-readable storage medium comprising one or more programming instructions that, when executed, cause the computing device to:

receiving patient data from the one or more sensors over a period of time, wherein the patient data includes motion data related to lower back motion of the wearer,

classifying at least a portion of the motion data into an initial grouping, wherein the initial grouping is associated with a plurality of activity categories corresponding to different types of motion,

further classifying at least a portion of the motion data into one of the plurality of activity categories,

generating a score corresponding to at least a portion of the athletic data based on the activity category into which the athletic data is classified,

causing the score to be displayed by a client electronic device.

2. The system of claim 1, wherein the one or more sensors comprise one or more of:

an inertial measurement unit;

an electrocardiogram sensor;

an altimeter;

a barometer;

a photoplethysmogram;

a thermometer; or

A microphone.

3. The system of claim 1, wherein the patient data comprises measurements relating to one or more of:

electrical activity information;

sound information; or

Temperature information.

4. The system of claim 1, wherein the one or more programming instructions that, when executed, cause the computing device to classify at least a portion of the motion data as an initial grouping comprise one or more programming instructions that, when executed, cause the computing device to compare one or more parameter values of the motion data to one or more parameters associated with one or more possible initial groupings.

5. The system of claim 1, wherein the one or more programming instructions that, when executed, cause the computing device to classify the at least a portion of the athletic data as one of the plurality of activity categories comprise one or more programming instructions that, when executed, cause the computing device to compare at least a portion of the athletic data to a trained data set to determine a probability that the at least a portion of the athletic data corresponds to a pattern associated with one of the plurality of activity categories.

6. The system of claim 5, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the computing device to use the at least a portion of the athletic data to train or augment the trained dataset with respect to an athletic specific to the wearer.

7. The system of claim 1, wherein the plurality of activity categories include one or more of:

sleeping;

driving;

sitting;

standing; or

And (5) walking.

8. The system of claim 1, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the computing device to:

determining a suggested diagnosis for said wearer, an

Causing the suggested diagnosis to be displayed by the client electronic device.

9. The system of claim 8, wherein the one or more programming instructions that, when executed, cause the computing device to determine a suggested diagnosis for the wearer comprise one or more programming instructions that, when executed, cause the computing device to:

the score is sent to a diagnostic system that,

wherein the diagnostic system is configured to:

retrieving diagnostic information related to a condition from a data storage device, wherein the diagnostic information includes a known score related to the condition,

in response to the score corresponding to the known score, identifying the condition as the suggested diagnosis, and

sending an indication of the condition to the computing device.

10. A method of assessing a spinal disorder, the method comprising:

by a computing device of an evaluation system:

receiving patient data from one or more sensors of a wearable electronic device located on a portion of a wearer's lower back over a period of time, wherein the patient data includes motion data related to lower back motion of the wearer,

classifying at least a portion of the motion data into an initial grouping, wherein the initial grouping is associated with a plurality of activity categories corresponding to different types of motion,

further classifying the at least a portion of the motion data as one of the plurality of activity categories,

generating a score corresponding to the at least a portion of the athletic data based on the activity category into which the athletic data is classified,

and causing the score to be displayed by the client electronic device.

11. The method of claim 10, wherein the one or more sensors comprise one or more of:

an inertial measurement unit;

an electrocardiogram sensor;

an altimeter;

a barometer;

a photoplethysmogram;

a thermometer; or

A microphone.

12. The method of claim 10, wherein the patient data comprises measurements relating to one or more of:

electrical activity information;

sound information; or

Temperature information.

13. The method of claim 10, wherein classifying at least a portion of the motion data as an initial grouping comprises comparing one or more parameter values of the motion data to one or more parameters associated with one or more possible initial groupings.

14. The method of claim 10, wherein classifying the at least a portion of the motion data as one of the plurality of activity categories comprises comparing the at least a portion of the motion data to a trained data set to determine a probability that the at least a portion of the motion data corresponds to a pattern associated with one of the plurality of activity categories.

15. The method of claim 14, further comprising using the at least a portion of the motion data to train or augment the trained data set with respect to motion specific to the wearer.

16. The method of claim 10, wherein the plurality of activity categories include one or more of:

sleeping;

driving;

sitting;

standing; or

And (5) walking.

17. The method of claim 10, further comprising:

determining a suggested diagnosis for said wearer, an

Causing the suggested diagnosis to be displayed by the client electronic device.

18. The method of claim 17, wherein determining a suggested diagnosis for the wearer comprises:

the score is sent to a diagnostic system that,

wherein the diagnostic system is configured to:

retrieving diagnostic information related to a condition from a data storage device, wherein the diagnostic information includes a known score related to the condition,

in response to the score corresponding to the known score, identifying the condition as the suggested diagnosis, and

sending an indication of the condition to the computing device.

Background

A patient's spinal condition is typically assessed using a combination of patient feedback, imaging techniques, and clinician assessment. For example, Oswestry Dysfunction Index (ODI) is used by many clinicians to assess the dysfunction of patients caused by low back pain. ODI includes questions that require the patient to assess the contribution of lower back related symptoms to his or her pain level with respect to certain activities (e.g., sitting, standing, sleeping, and traveling).

However, the data collected by these methods may be erroneous and in some cases misleading the true condition of the patient. For example, the patient's response to the ODI question (or other description or characterization of the patient's pain level that the patient provides) may be inaccurate or incomplete. Furthermore, the problem posed by ODI may not adequately describe the nature of the patient's condition.

Since data relating to patient motion may contain valuable information about the patient's neurological health and skeletal muscle health, it is desirable to obtain this information in an objective, rather than subjective, manner. Furthermore, ODI and similar clinical measurement tools are difficult to incorporate into daily clinical practice, often requiring the addition of full-time staff for distribution, tabulation and management.

Disclosure of Invention

In one embodiment, a system for assessing a spinal disorder includes a wearable electronic device having one or more sensors. The wearable electronic device is configured to be positioned on a portion of a lower back of a wearer, and the one or more sensors are configured to acquire patient data related to the wearer. The system comprises: an evaluation system having a computing device; and a computer readable storage medium having one or more programming instructions. The programming instructions, when executed, cause the computing device to receive patient data from one or more sensors over a period of time, wherein the patient data includes motion data associated with motion of a lower back of a wearer, classify at least a portion of the motion data into an initial grouping, wherein the initial grouping is associated with a plurality of activity categories corresponding to different types of motion, further classify at least a portion of the motion data into one of the plurality of activity categories, generate a score corresponding to at least a portion of the motion data based on the activity category into which the motion data was classified, and cause the score to be displayed via a client electronic device.

The one or more sensors may include one or more of: an inertial measurement unit; an electrocardiogram sensor; an altimeter; a barometer; photoplethysmograms (photoplethysmograms); a thermometer; or a microphone. The patient data may include measurements relating to one or more of: electrical activity information; sound information; or temperature information.

In one embodiment, the system may classify at least a portion of the motion data as an initial grouping by comparing one or more parameter values of the motion data to one or more parameters associated with one or more possible initial groupings.

The system may classify at least a portion of the motion data into one of a plurality of activity categories by comparing the at least a portion of the motion data to a trained data set to determine a probability that the at least a portion of the motion data corresponds to a pattern associated with one of the plurality of activity categories. The system may use at least a portion of the motion data to train or augment a trained data set relating to a particular motion of the wearer.

In one embodiment, the activity categories may include one or more of: sleeping; driving; sitting down; standing; or walking.

In various embodiments, the system may determine a suggested diagnosis for the wearer and cause the suggested diagnosis to be displayed via the client electronic device. The system may determine a suggested diagnosis for the wearer by sending the score to a diagnostic system, wherein the diagnostic system is configured to retrieve diagnostic information related to the condition from a data storage device, wherein the diagnostic information includes a known score related to the condition, identify the condition as a suggested diagnosis in response to the score corresponding to the known score, and send an indication of the condition to a computing device.

Drawings

FIG. 1 illustrates an example spinal diagnostic system according to an embodiment.

Fig. 2 illustrates an example wearable electronic device, according to an embodiment.

Fig. 3 illustrates an example method of evaluating patient data, according to an embodiment.

Fig. 4 depicts a block diagram of an example of internal hardware that may be used to contain or implement program instructions, according to an embodiment.

Detailed Description

In some embodiments, as used in this specification and including the appended claims, the singular forms "a/an" and "the" include the plural, and reference to a particular numerical value includes at least that particular value, unless the context clearly dictates otherwise. Ranges may be expressed herein as from "about" or "approximately" one particular value, and/or to "about" or "approximately" another particular value. When such a range is expressed, another embodiment includes from the one particular value and/or to the other particular value. Similarly, when values are expressed as approximations, by use of the antecedent "about," it will be understood that the particular value forms another embodiment. It should also be understood that all spatial references (e.g., horizontal, vertical, top, upper, lower, bottom, left, and right) are for illustrative purposes only and may be varied within the scope of the present disclosure. For example, references to "upper" and "lower" are relative and are only used with respect to each other in context, and need not be "high" and "low". In general, similar spatial references to different aspects or components indicate similar spatial orientations and/or positions, i.e., each "first end" is located or pointed at the same end of the device. Furthermore, the use of various spatial terms herein should not be construed to limit the various insertion techniques or orientations of the implant relative to a position in the spinal column.

For the purposes of this application, the following terms shall have the respective meanings given below:

"computing device," "electronic device," or "computer" refers to a device or system that includes a processor and memory. Each device may have its own processor and/or memory, or the processor and/or memory may be shared with other devices, such as in a virtual machine or virtual container arrangement. The memory will contain or receive programming instructions that, when executed by the processor, cause the electronic device to perform one or more operations in accordance with the programming instructions. Examples of electronic devices include personal computers, servers, mainframes, virtual machines, containers, mobile electronic devices such as smartphones, internet connected wearable devices, tablet computers, laptop computers, and appliances and other devices that may communicate in an internet-of-things configuration. In a client-server arrangement, the client devices and servers are electronic devices, with the servers containing instructions and/or data that the client devices access via one or more communication links in one or more communication networks. In a virtual machine arrangement, a server may be an electronic device, and each virtual machine or virtual container may also be considered an electronic device. In the following discussion, a client device, server device, virtual machine, or virtual container may be referred to simply as a "device" for brevity. Additional elements that may be included in the electronic device will be discussed below in the context of fig. 4.

The terms "memory," "computer-readable medium," and "data storage device" each refer to a non-transitory device on which computer-readable data, programming instructions, or both are stored. The terms "memory," "computer-readable medium" and "data storage device" encompass both singular and plural embodiments, as well as portions of such devices, e.g., memory sectors, unless the context clearly dictates otherwise that a single device is required or that multiple devices are required.

FIG. 1 illustrates an example spinal assessment system, according to an embodiment. As shown in fig. 1, system 100 may include one or more wearable electronic devices 102a-N, one or more client electronic devices 104a-N, and an evaluation system 106. The wearable electronic devices 102a-N may be in communication with the client electronic devices 104a-N and/or the evaluation system 106 via one or more communication networks 108, 112. Similarly, the client electronic devices 104a-N can communicate with the evaluation system 106 via one or more communication networks 110. The communication networks 108, 110, 112 may be Local Area Networks (LANs), Wide Area Networks (WANs), mobile or cellular communication networks, extranets, intranets, the internet, short-range communication networks, and the like. Although fig. 1 shows separate communication networks 108, 110, 112, it should be understood that these networks, or some combination of these networks, may be implemented as a single communication network.

Evaluation system 106 can include one or more electronic devices, such as a server and/or one or more data storage devices. For example, as shown in fig. 1, the evaluation system 106 may include a data storage device 114 for storing measured patient data received from one or more sensors, such as athletic data, electrical activity information, sound information, temperature information, and/or the like. The data storage device 114 may store the data such that it is relevant to a particular patient.

The evaluation system 106 can include an activity recognition system 116, which can be implemented using one or more electronic devices and/or data storage devices. The activity recognition system 116 may translate at least a portion of the measured patient data into a particular activity performed by the wearer of the wearable electronic device, as described in more detail below. The activity recognition system 116 may include or may have access to a data store 120 that includes patterns associated with one or more activities and/or a data store 122 that includes historical information (e.g., movement data or patterns of movement) related to the wearer's patient data.

In an embodiment, the evaluation system 106 may include a diagnostic system 118. The diagnostic system 118 can be implemented using one or more electronic devices and/or data storage devices. The diagnostic system may analyze and compare measured patient data related to a particular wearer of the wearable electronic device with data related to various spinal or other back conditions or disorders to suggest possible diagnoses for the wearer that are subject to review and confirmation by clinicians, as described in more detail below. As shown in fig. 1, the diagnostic system may include or have access to a data storage device 124 that includes information related to one or more spinal or back conditions.

Fig. 2 illustrates an example wearable electronic device 200, according to an embodiment. The wearable electronic device 200 may be configured to be worn by an individual across at least a portion of the torso of the individual, e.g., a portion of the individual's lower back, a portion of the individual's upper back, or a front of the individual's chest.

As shown in fig. 2, wearable electronic devices 102a-N may include circuitry 202 and one or more sensors 204 a-N. Example sensors 204a-N may include, but are not limited to, Inertial Measurement Units (IMUs), Electrocardiogram (ECG) sensors, Electromyography (EMG) sensors, accelerometers, barometers, thermometers or other thermal sensors, microphones, photoplethysmography (PPG), and/or the like. In some embodiments, the wearable electronic device may be secured to the patient by one or more straps, bands, or other fasteners. In other embodiments, the wearable electronic device may be a component of a wearable article, such as a harness, sleeve, and/or the like, or may be secured on the patient or wearer, for example, in the form of a subcutaneous implant or external patch that may be adhered or otherwise fixedly connected to the patient. In one embodiment, the adhesive used to secure the wearable electronic device to the patient may be electrically conductive to allow electrical signals to flow from the patient's skin to one or more sensors (e.g., ECG integrated circuits).

In various embodiments, one or more sensors 204a-N may be configured to measure one or more characteristics of a wearer's motion or action while the wearer is wearing the wearable electronic device. The movement or motion may be of the spinal axis, lower extremities, etc. of the wearer. For example, one or more sensors may measure rotation about an x, y, or z axis (e.g., pitch, roll, and/or yaw). In various embodiments, the x-axis can be defined as the intersection of the midsagittal plane and the axial plane. The y-axis may be defined as the intersection of the coronal plane and the axial plane. The z-axis may be defined as the intersection of the midsagittal plane and the midsagittal plane.

One or more sensors may measure angular velocity, gravity, pressure, acceleration, gyroscopic and/or rotational orientation, direction of motion, heave, surge, sway, position, and/or the like. Additional and/or alternative data may be used within the scope of the present disclosure.

In some embodiments, one or more sensors 204a-N may be configured to measure one or more anatomical conditions of the wearer. For example, the thermal sensor may measure the temperature of adjacent soft tissue of the patient. Similarly, a digital sensor such as an ECG or PPG may be used to measure the heartbeat of the wearer. Additional and/or alternative data may be used within the scope of the present disclosure.

One or more sensors 204a-N may be configured to measure electrical activity of local muscle tissue of the patient. For example, one or more of the sensors 204a-N may include ECG or EMG. In some embodiments, one or more sensors 204a-N may be configured to measure acoustic information, such as acoustic signals from nearby joints. For example, one or more of the sensors 204a-N may include one or more microphones.

One or more sensors 204a-N, such as pulse oximeters, may be configured to measure or detect blood volume changes in microvascular tissue.

For purposes of this disclosure, "measured patient information" refers to information measured or otherwise obtained by the wearable electronic device, e.g., motion data, anatomical conditions, electrical activity, sound information, blood volume changes, and the like.

In various embodiments, wearable electronic devices 102a-N may include one or more integrated circuits, microchips, or other memory devices. For example, the wearable electronic devices 102a-N may include a memory chip that may be removed from the wearable electronic device and inserted into another electronic device in order to transfer data stored on the memory chip. The wearable electronic device may also include firmware and/or a battery, including, for example, a thin film battery that may be packaged or may include a piezoelectric power source.

In other embodiments, the wearable electronic devices 102a-N may communicate with one or more other electronic devices, such as the client electronic devices 104a-N, via short-range communication. For example, the wearable electronic devices 102a-N may communicate with the electronic devices using Near Field Communication (NFC), Radio Frequency Identification (RFID), bluetooth, and the like. The wearable electronic devices and/or client electronic devices 104a-N may include short-range communication receivers and/or transmitters, such as RFID tags, bluetooth antennas, NFC chips, ultrasound, and the like. The electronic device may further provide power or additional power to the wearable electronic device through physical connection, induction, or through other such means.

The client electronic devices 104a-N may be smart phones, tablets, laptops, computing devices, or other electronic devices. For example, the client electronic devices 104a-N may be smartphones or tablets associated with patients. As another example, the client electronic devices 104a-N may be smartphones or tablets associated with clinicians, healthcare providers, healthcare entities, or the like.

Fig. 3 illustrates an example method of evaluating measured patient information, according to an embodiment. As shown in fig. 3, the wearable electronic device may collect 300 measured patient information over a particular period of time. For example, the IMU may measure angular velocity and/or acceleration associated with movement of the wearer over a period of time. Similarly, a barometer may measure atmospheric pressure over a period of time. In various embodiments, the sensor may continuously capture patient data. For example, the sensors may capture patient data in substantially real time. Alternatively, the sensor may capture patient data at certain times, for example at regular intervals.

Given an IMU and its placement, the IMU may provide information related to the motion of the person wearing the wearable electronic device. The raw x/y/z measurements may, for example, provide only information about the motion of the sensor itself, which may be different from the motion of the wearer. For example, known methods utilize motion sensors integrated into devices such as telephones and watches that move in a manner that is significantly different from and independent of their wearer or carrier.

One or more data points of the data may have one or more associated parameters, such as an associated timestamp, an associated velocity value, an associated barometric pressure value and an associated acceleration value, a rotation value, an orientation value, and the like.

In various embodiments, the patient may wear the wearable electronic device in the patient's daily routine. For example, a patient may wear a wearable electronic device when the patient is at home or outside of a clinical setting. A patient may wear a wearable electronic device for an extended period of time to acquire a large number of data samples. The time period may be hours, days, weeks, months, etc.

In other embodiments, the patient may wear the wearable electronic device for a limited period of time, such as in a clinical setting, during an assessment with a clinician, and so forth. In such a case, the patient may be required to perform one or more exercises, activities or protocols to gather information about the patient's movements. For example, a clinician may require a patient to sit, stand, walk, bend, lie down, or perform other activities while wearing the wearable electronic device.

In various embodiments, the wearable electronic device may notify the wearer or another person, such as a healthcare provider, if one or more measurements of patient data are outside of an acceptable range. For example, the wearable electronic device may include or communicate with a data storage device that may store acceptable ranges of measurements. The acceptable range of measurements may be a wearer-specific customized range, or may be a general range of acceptable measurements for all patients. For example, the sensor may measure rotation about an axis. If the measured rotation is outside of the acceptable range of values (e.g., the wearer is rotated too much), the wearable electronic device may display a notification on the client electronic device informing the user of the client electronic device that the measured value is outside of the acceptable range. Additional and/or alternative ranges and/or measurements may be used within the scope of the present disclosure.

Referring back to fig. 3, in some embodiments, the wearable electronic device may perform one or more pre-processing operations on at least a portion of the collected patient data. For example, the wearable electronic device may filter the data or format data into a consistent form or format.

The wearable electronic device may store 302 the collected patient data in one or more data storage devices. In various embodiments, the data storage devices may be associated with the sensors such that the motion data collected by the sensors is stored in the respective data storage devices. Alternatively, patient data collected by one sensor may be stored in one or more data storage devices along with motion data collected by one or more other sensors.

As shown in fig. 3, at least a portion of the stored patient data can be provided 304 to the electronic device. In an embodiment, patient data may be provided to the electronic device by removing a memory chip or other data storage device from the wearable device and connecting it to the electronic device. Optionally, the wearable electronic device may transmit at least a portion of the collected patient data to the electronic device via one or more communication networks. In some embodiments, the wearable electronic device may transmit patient data to the electronic device at certain times or intervals. In other embodiments, the wearable electronic device may transmit the patient data to the electronic device in response to receiving a request from the electronic device.

One or more electronic devices, such as an electronic device associated with an assessment engine or activity recognition system, may process 306 at least a portion of the patient data. In various embodiments, the electronic device may process 306 the motion data included in the patient data to classify at least a portion of the motion data into one or more activity categories. An activity category refers to an activity that a wearer may be performing when collecting at least a portion of patient data. Exemplary activity categories include, but are not limited to, sleeping, walking, driving, traveling, sitting, standing, and/or the like.

In various embodiments, the electronic device may classify the motion data into an initial grouping. The initial grouping may be associated with a posture of the wearer. As such, the initial grouping may be associated with two or more activity categories. For example, the activity categories may be associated with similar types of gestures. As such, the motion data may first be classified into initial groupings based on characteristics of the motion data (e.g., rotational position about one or more anatomical axes).

The electronic device may classify the motion data into initial groupings using machine learning techniques. For example, the electronic device may use logistic regression trained on certain gestures. Logistic regression operates on a purely binary basis, but can be extended to multi-class classification tasks using multinomial logistic regression or a pair of remaining voting approaches. Multiple logistic regression outlines a method by which multiple output classifications can be generated. For example, instead of being true or false, the possible outputs of logistic regression, multiple logistic regression, may directly label three pose states.

The remaining pair (or all of the pair) is the process in which the individual classifiers are trained in a binary fashion to identify the data as "X" or "all data except X". In this case, each possible gesture may be associated with its own classifier (e.g., a standing classifier, a sitting classifier, and a lying classifier). The data may be passed through a classifier associated with each possible gesture, and the result with the highest probability value may be assumed to be the correct gesture.

The electronic device may further classify the motion data for each initial grouping into a particular activity category of the initial grouping. For example, the electronic device may classify the athletic data that has been classified as the initial grouping "activity 1/activity 2" as activity category activity or activity category activity 2.

The electronic device may classify the motion data into an initial grouping and/or an activity category based on one or more parameter values of the motion data. For example, motion data indicating that the wearable electronic device is placed on the wearer's back in an upright manner may be and be subjected to a range of air pressures, which may be classified in the initial grouping "activity 1/activity 2". However, if the motion data is associated with a velocity within a certain range or exceeding a certain value, such motion data may be classified as an "activity 2" activity category.

As another example, motion data indicating that the wearable electronic device is experiencing a range of forces may be classified as an initial grouping "activity 3/activity 4". However, if the motion data is associated with a speed within a certain range or exceeding a certain value, such motion data may be categorized as an "activity 3" activity category because the wearer would not traditionally experience that speed during sleep.

In various embodiments, the electronic device may use pattern matching to classify the motion data. For example, the electronic device may store or otherwise access one or more data patterns that indicate motion corresponding to the initial grouping and/or activity category. For example, motion data associated with walking may have a value for a speed parameter within a range of values. The pattern may be stored in a pattern data storage device. When classifying the motion data, the electronic device may compare at least a portion of the motion data to one or more patterns to determine one or more similarities. For example, if a speed parameter value associated with a portion of motion data is similar to the example "walk" pattern described above, the electronic device may classify the portion of motion data as "walk".

In some embodiments, one or more patterns may be trained based on a particular behavior or motion of the individual wearer. The electronic device may utilize a machine learning method that may compare at least a portion of the motion data to a trained data set to determine a probability that the motion data corresponds to a pattern associated with the activity category. For example, a particular wearer may always walk at a range of speeds. As another example, the wearer may always walk in a gait that is advantageous to the right side of the wearer. As more motion data is collected for the wearer, one or more patterns may be trained to recognize that certain behaviors are wearer-specific motions, rather than indications of pain or other back condition consequences experienced by the wearer.

Returning to fig. 3, the electronic device may convert 308 at least a portion of the categorized motion data and/or other patient data into one or more scores. In various embodiments, the one or more scores may correspond to one or more questions from the ODI. For example, the ODI may require the patient to assess how the patient's pain affects his or her walking ability. The electronic device may analyze one or more parameters of the motion data that have been classified as "walking" to generate a score associated with the question. For example, the electronic device may analyze the forward speed associated with the motion data to determine the speed of the wearer's motion. As another example, the electronics can analyze pitch (forward backward motion) and/or roll (right-to-left motion) to determine the stability of the wearer's walking.

Referring back to fig. 3, in some embodiments, the electronic device may determine 310 a suggested diagnosis for the wearer. For example, the activity recognition system may send one or more of the scores to a diagnostic system. The diagnostic system may receive the score and may compare the score to diagnostic information relating to various conditions, such as cervical spondylosis and symptomatic lumbar stenosis. For example, the diagnostic system may store information associated with different conditions in one or more data storage devices. The information may include scores or ranges of scores for various sports-related aspects of the condition. If the received score is similar to a score associated with a condition, the diagnostic system may determine that the condition is a suggested diagnosis for the wearer.

For example, neurogenic claudication associated with spinal stenosis can be characterized by progressive lumbar flexion and decreased walking speed with increased out-of-bed activity. In contrast, psoas dysfunction (spasticity) may be characterized by increased posture and walking speed, with increased out-of-bed activity.

In various embodiments, the evaluation system may cause the suggested diagnosis to be displayed 312 on one or more client electronic devices. For example, the evaluation system may cause the suggested diagnosis to be displayed on a tablet associated with the wearer's clinician. In another embodiment, the assessment system may cause the suggested diagnosis to be displayed on the wearer's smartphone device. The clinician may use the suggested diagnosis to confirm the wearer's diagnosis or to suggest other treatment suggestions to the wearer.

FIG. 4 illustrates example hardware that can be used to contain or implement program instructions. Bus 400 serves as the primary information highway interconnecting the other illustrated components of the hardware. The CPU 405 is a central processing unit of the system, and executes calculations and logical operations necessary for executing programs. CPU 405, alone or in combination with one or more of the other elements disclosed in fig. 4, is an example of a processor, as that term is used within this disclosure. Read Only Memory (ROM) and Random Access Memory (RAM) constitute examples of non-transitory computer-readable storage media 420, memory devices, or data storage devices, as such terms are used within this disclosure.

Program instructions, software, or interactive modules for providing an interface and performing any queries or analyses associated with one or more data sets may be stored in the memory device 420. Optionally, the program instructions may be stored on a tangible, non-transitory computer-readable medium such as a compact disc, digital diskette, flash memory, memory card, USB drive, compact disc storage medium, and/or other recording medium.

An optional display interface 430 may allow information from bus 400 to be displayed in audio, video, graphical or alphanumeric format on display 435. Various communication ports 640 may be used to communicate with external devices. The communication port 440 may be attached to a communication network, such as the internet or an intranet.

The hardware may also include an interface 445 that allows data to be received from an input device such as keypad 450 or other input device 455 such as a touch screen, remote control, pointing device, video input device, and/or audio input device.

It will be appreciated that various of the above-disclosed and other features and functions, or alternatives thereof, may be desirably combined into many other different systems or applications, or combinations of systems and applications. Also that various presently unforeseen or unanticipated alternatives, modifications, variations or improvements therein may be subsequently made by those skilled in the art which are also intended to be encompassed by the following claims.