阅读说明：本技术 一种临床诊疗数据录入系统和方法 (Clinical diagnosis and treatment data entry system and method ) 是由 王华丽 孙国锋 岳伟华 黄雨 陈冬雪 常素华 于 2020-06-03 设计创作，主要内容包括：本发明公开一种临床诊疗数据录入系统和方法。所述临床诊疗数据录入系统包括：数据获取单元,接收原始临床诊疗数据,利用标准数据模版对原始临床诊疗数据进行筛选,得到匹配标准数据模版的多个诊疗数据项；处理单元,针对多个诊疗数据项中的任一个,接收由至少两个录入客户端基于同一诊疗数据项的两个录入结果,判断两个录入结果是否存在差异；执行单元,响应于处理单元判断出两个录入结果存在差异,则向专家系统推送录入结果的差异性信息,以请求由专家系统对存在差异的录入结果所对应的诊疗数据项进行重新录入。利用本发明的方案,可提高诊疗数据项录入的准确性。(The invention discloses a clinical diagnosis and treatment data entry system and a method. Clinical diagnosis and treatment data entry system includes: the data acquisition unit is used for receiving the original clinical diagnosis and treatment data, screening the original clinical diagnosis and treatment data by using the standard data template and obtaining a plurality of diagnosis and treatment data items matched with the standard data template; the processing unit is used for receiving two input results of at least two input clients based on the same diagnosis and treatment data item aiming at any one of a plurality of diagnosis and treatment data items and judging whether the two input results are different or not; and the execution unit responds to the processing unit and judges that the two input results are different, and then pushes difference information of the input results to the expert system so as to request the expert system to re-input the diagnosis and treatment data items corresponding to the input results with the difference. By using the scheme of the invention, the accuracy of the entry of the diagnosis and treatment data items can be improved.)

1. A clinical medical data entry system, the system comprising:

a data acquisition unit configured to: receiving original clinical diagnosis and treatment data, and screening the original clinical diagnosis and treatment data by using a standard data template to obtain a plurality of diagnosis and treatment data items matched with the standard data template, wherein the standard data template comprises baseline information, diagnosis and treatment pass information and treatment result information which accord with a CDISC standard;

a processing unit configured to: aiming at any one of the diagnosis and treatment data items, receiving two input results of at least two input clients based on the same diagnosis and treatment data item, and judging whether the two input results are different or not;

an execution unit configured to: and responding to the processing unit to judge that the two input results are different, and pushing difference information of the input results to an expert system to request the expert system to re-input the diagnosis and treatment data items corresponding to the input results with the difference.

2. The system of claim 1, wherein the raw clinical data is from at least one of the following data sources:

batch imported form data, data obtained from a hospital information system HIS, electronic medical record EMR data, image archiving and communication system PACS data, hospital laboratory information management system LIS data.

3. The system of claim 1 or 2, wherein the processing unit is further configured to:

respectively extracting a characteristic value A1 and a characteristic value A2 of the two recorded results, judging whether the difference value between the characteristic value A1 and the characteristic value A2 is within a preset threshold range, if so, determining that the two recorded results are the same, and if not, determining that the two recorded results are different.

4. The system of claim 1 or 2, wherein the execution unit is further configured to:

and responding to the processing unit to judge that the two entry results are the same, and storing the entry results to a database.

5. A server, characterized in that it comprises a clinical medical data entry system according to any of claims 1-4.

6. A clinical medical data entry method, the method comprising:

receiving original clinical diagnosis and treatment data, and screening the original clinical diagnosis and treatment data by using a standard data template to obtain a plurality of diagnosis and treatment data items matched with the standard data template, wherein the standard data template comprises baseline information, diagnosis and treatment pass information and treatment result information which accord with a CDISC standard;

aiming at any one of the diagnosis and treatment data items, receiving two input results of at least two input clients based on the same diagnosis and treatment data item, and judging whether the two input results are different or not;

and responding to the judgment that the two input results are different, pushing the difference information of the input results to an expert system to request the expert system to re-input the diagnosis and treatment data items corresponding to the input results with the difference.

7. The method of claim 6, wherein the raw clinical data is from at least one of the following data sources:

batch imported form data, data obtained from a hospital information system HIS, electronic medical record EMR data, image archiving and communication system PACS data, hospital laboratory information management system LIS data.

8. The method according to claim 6 or 7, wherein the judging whether there is a difference between the two logged results comprises:

respectively extracting a characteristic value A1 and a characteristic value A2 of the two recorded results, judging whether the difference value between the characteristic value A1 and the characteristic value A2 is within a preset threshold range, if so, determining that the two recorded results are the same, and if not, determining that the two recorded results are different.

9. The method according to claim 6 or 7, characterized in that the method further comprises:

and responding to the judgment that the two entry results are the same, and storing the entry results to a database.

10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the clinical medical data entry method of any one of claims 6-9.

Technical Field

The invention relates to the field of clinical research, in particular to a clinical diagnosis and treatment data entry system and a method.

Background

In recent years, with the increase of scientific research tasks and requirements of hospitals, the requirement on the accuracy of scientific research data acquisition is higher and higher, and because the data in different information systems has noise or pseudo data in the current clinical diagnosis and treatment data acquisition of hospitals, the error rate of directly stored data is high, the accuracy and the effectiveness of the data are reduced, and the data-based medical research is not facilitated.

Therefore, a technical solution is needed to solve the above technical problems.

Disclosure of Invention

In order to solve the technical problems, the invention provides a clinical diagnosis and treatment data entry system and a method.

As a first aspect of the present invention, there is provided a clinical medical data entry system, wherein the system comprises:

a data acquisition unit configured to: receiving original clinical diagnosis and treatment data, and screening the original clinical diagnosis and treatment data by using a standard data template to obtain a plurality of diagnosis and treatment data items matched with the standard data template, wherein the standard data template comprises baseline information, diagnosis and treatment pass information and treatment result information which accord with a CDISC standard;

a processing unit configured to: aiming at any one of the diagnosis and treatment data items, receiving two input results of at least two input clients based on the same diagnosis and treatment data item, and judging whether the two input results are different or not;

an execution unit configured to: and responding to the processing unit to judge that the two input results are different, and pushing difference information of the input results to an expert system to request the expert system to re-input the diagnosis and treatment data items corresponding to the input results with the difference.

In one embodiment, the raw clinical data is from at least one of the following data sources: batch imported form data, data obtained from a hospital information system HIS, electronic medical record EMR data, image archiving and communication system PACS data, hospital laboratory information management system LIS data.

In one embodiment, the processing unit is further configured to: respectively extracting a characteristic value A1 and a characteristic value A2 of the two recorded results, judging whether the difference value between the characteristic value A1 and the characteristic value A2 is within a preset threshold range, if so, determining that the two recorded results are the same, and if not, determining that the two recorded results are different.

In one embodiment, the execution unit is further configured to: and responding to the processing unit to judge that the two entry results are the same, and storing the entry results to a database.

As a second aspect of the present invention, there is provided a server, wherein the server comprises the clinical medical data entry system of the present invention.

As a third aspect of the present invention, there is provided a clinical diagnosis and treatment data entry method, wherein the method includes:

receiving original clinical diagnosis and treatment data, and screening the original clinical diagnosis and treatment data by using a standard data template to obtain a plurality of diagnosis and treatment data items matched with the standard data template, wherein the standard data template comprises baseline information, diagnosis and treatment pass information and treatment result information which accord with a CDISC standard;

aiming at any one of the diagnosis and treatment data items, receiving two input results of at least two input clients based on the same diagnosis and treatment data item, and judging whether the two input results are different or not;

and responding to the judgment that the two input results are different, pushing the difference information of the input results to an expert system to request the expert system to re-input the diagnosis and treatment data items corresponding to the input results with the difference.

In one embodiment, the raw clinical data is from at least one of the following data sources: batch imported form data, data obtained from a hospital information system HIS, electronic medical record EMR data, image archiving and communication system PACS data, hospital laboratory information management system LIS data.

In one embodiment, the determining whether there is a difference between the two entered results includes: respectively extracting a characteristic value A1 and a characteristic value A2 of the two recorded results, judging whether the difference value between the characteristic value A1 and the characteristic value A2 is within a preset threshold range, if so, determining that the two recorded results are the same, and if not, determining that the two recorded results are different.

In one embodiment, the method further comprises: and responding to the judgment that the two entry results are the same, and storing the entry results to a database.

To a fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing the clinical medical data entry method of the present invention.

According to the technical scheme, noise reduction and filtering can be performed on data in different information systems by using the standard data template, noise and pseudo data in original clinical diagnosis and treatment data are removed, and the effectiveness of the data is improved to a certain extent; and in the data entry process, diagnosis and treatment data items are dually entered, the entered results are verified, and then problem data can be corrected through an expert system, so that the accuracy of the entered diagnosis and treatment data items is further improved, and the medical research based on data is facilitated.

Drawings

The invention will now be described by way of non-limiting example only with reference to the accompanying drawings, in which:

FIG. 1 is a schematic diagram illustrating a clinical medical data entry system according to one embodiment of the present invention;

fig. 2 is a flow chart illustrating a clinical medical data entry method according to one embodiment of the present invention.

Detailed Description

In order to make the above and other features and advantages of the present invention more apparent, the present invention is further described below with reference to the accompanying drawings. It is understood that the specific embodiments described herein are for purposes of illustration only and are not intended to be limiting.

As a first aspect of the present invention, a clinical medical data entry system is provided. Figure 1 schematically illustrates a clinical data entry system 100 according to one embodiment of the present invention. The clinical data entry system 100 includes a data acquisition unit 110, a processing unit 120, and an execution unit 130, and each unit is communicatively coupled thereto. The clinical data entry system 100 may be partially or wholly located on a server side, such as a server.

The data acquisition unit 110 may be configured to: the method comprises the steps of receiving original clinical diagnosis and treatment data, screening the original clinical diagnosis and treatment data by utilizing a standard data template to obtain a plurality of diagnosis and treatment data items matched with the standard data template, wherein the standard data template comprises baseline information, diagnosis and treatment passing information and treatment result information which accord with the clinical data exchange standard association (CDISC) standard.

As can be understood, because the original clinical diagnosis and treatment data are mostly from different systems, noise or pseudo data and other interferences are inevitable in the data, and the original clinical diagnosis and treatment data are screened by using the standard data template, the noise and/or the pseudo data in the original clinical diagnosis and treatment data can be removed, the accuracy of the data is improved to a certain extent, so that the intelligent or automatic entry of the clinical diagnosis and treatment data can be conveniently realized, and the entry efficiency of the clinical diagnosis and treatment data can be improved.

The source or data source of the raw clinical data may include a variety of sources, depending on the circumstances. For example, the data may be originally recorded data during the diagnosis and treatment process, such as description of illness state of a patient at the time of doctor's visit, prescription made by a doctor, record of inpatient condition by a nurse, and follow-up data entered by a patient WeChat terminal, and the like, wherein the noise or the false data may be caused by inaccurate description of illness state of a patient, different recording styles of medical staff, and the like. Alternatively, the raw clinical data may be raw clinical data obtained from various data systems of a hospital, and in one embodiment, the raw clinical data is from at least one of the following data sources: batch imported form data, data obtained from a hospital information system HIS, electronic medical record EMR data, image archiving and communication system PACS data, hospital laboratory information management system LIS data. In this embodiment, when the data sources include the HIS system, the LIS system, and the PACS system described above, the raw clinical data may include baseline data of a patient in the HIS system, blood biochemical test data in the LIS system, and image data in the PACS system.

The data acquisition unit 110 may acquire the raw clinical data in a variety of possible ways. For example, data collection may be performed by a scanner, a computer used by doctors and nurses, an intelligent terminal device (e.g., a smart phone) used by patients, and the like, and the collected data may be transmitted to the data acquisition unit 110. Alternatively, in one embodiment, a front-end terminal may be independently configured for the clinical data entry system 100 to obtain the raw clinical data from various data systems of the hospital and then send the raw clinical data to the data acquisition unit 110.

As can be appreciated, the standard data template may be in many possible forms, for example, in the form of tables, statements, etc. for describing, defining, etc. the desired data. For example, the description statement of the standard data template is "hemoglobin index of patient is [ ]", and at this time, the data obtaining unit 110 may filter the original clinical diagnosis data by using the standard data template, extract the keyword "hemoglobin" from the description statement, and then match the original clinical diagnosis data to obtain "hemoglobin (HGB or Hb): 14.5g/dl ", thereby extracting" 14.5g/dl "to be supplemented to the above description sentence as a matched diagnosis and treatment data item.

Depending on the situation, the baseline information may include, but is not limited to, demographics, disease history, diagnosis, patient ID, and time to admission 5 CDISC standard sub-domains. Demographics may include, for example, but are not limited to: information such as sex, date of birth, blood type, etc.; the history of a disease can include, but is not limited to, previous disease, treatment regimen, etc. of the patient and/or its immediate relatives; the diagnosis can be standardized by using an international diagnosis dictionary ICD 10. The treatment session may include treatment modality (e.g., drugs used, equipment used, etc.), treatment period (e.g., 3 weeks, 2 months, etc.), examination results 3 CDISC standard sub-domains. The treatment outcome may include, length of stay, total cost associated with the procedure, complications, and treatment outcome 4 CDISC standard sub-domains.

The processing unit 120 may be configured to: and aiming at any one of the diagnosis and treatment data items, receiving two input results of at least two input clients based on the same diagnosis and treatment data item, and judging whether the two input results are different.

As can be understood, although the screening of the diagnosis data items by using the standard data template improves the validity of the data to some extent, considering that the entry accuracy of the diagnosis data is further improved, the processing unit 120 is required to perform further verification on the entry result.

Depending on the situation, the processing unit 120 may determine whether there is a difference between the two entered results in any available manner. For example, in one embodiment, the processing unit 120 may extract a characteristic value a1 and a characteristic value a2 of two recorded results, determine whether a difference between the characteristic value a1 and the characteristic value a2 is within a preset threshold range, determine that the two recorded results are the same if the difference is yes, and determine that the two recorded results are different if the difference is not.

Here, the characteristic value is a parameter that can be used as a basis for identification in the input result, and the type of the parameter may include at least an attribute value type or a numerical value type.

For the attribute value type, the parameter may be a medical index in the diagnosis and treatment data item or basic information of the patient, where the medical index may specifically include a name of the medical index, a special identifier of the medical index, and/or other available data; for example, the name of the medical index may be "platelet count", the corresponding result may be "normal" or "abnormal", the personal information of the patient is, for example, gender, and the corresponding result is "male" or "female".

For the numerical type, the parameter may be detection result data of medical index in the diagnosis and treatment data item of the patient or basic information of the patient. For example, the detection result data may be detection result data of hemoglobin (HGB or Hb); the basic information of the patient can be the age, the identification number, the medical insurance account number or the mobile phone number of the patient.

The extraction of the feature values may be achieved in a variety of available ways, depending on the situation. For example, the processing unit 120 may extract feature values of the two input results based on a preset algorithm, where the preset algorithm may be a natural language processing algorithm and a pre-trained neural network model (the neural network model may be obtained by pre-training a large amount of diagnosis and treatment data items), perform semantic analysis and keyword extraction on the input results by using the natural language processing algorithm, sort the keywords by using the pre-trained neural network model, and determine a feature value a1 and a feature value a2 according to the classification result, thereby implementing feature value extraction.

Further, the processing unit 120 may calculate the difference between the eigenvalue a1 and the eigenvalue a2 in a suitable manner. For example, for a feature value of an attribute value type, a chinese character may convert feature a1 and feature value a2 into binary data using GB2312-80 national standard codes, respectively (e.g., gender "male" converts hexadecimal to "C4D 0" first, and then "C4D 0" converts binary to "1100010011010000"), and similarly, for an english character may convert ASCII to binary data; then, a difference between the two binary data is calculated, and if the difference is 0 (in this case, the preset threshold range may be understood to include only 0), the characteristic value a1 is determined to be the same as the characteristic value a2, otherwise, the characteristic value a1 is determined to be different from the characteristic value a 2.

For the numerical value type eigenvalue, the processing unit 120 may calculate a difference value by dividing the large value minus the small value of the eigenvalue a1 and the eigenvalue a2 by the large value, and determine that the eigenvalue a1 is not different from the eigenvalue a2 if the difference value is within a preset threshold range, and otherwise determine that the eigenvalue a1 is different from the eigenvalue a 2.

The preset threshold value can be set according to the situation, for example, the range of the preset threshold value can be-0.0001; if a group of clinical data items to be entered is haemoglobin (HGB or Hb): 14.5g/dl, the logging results logged by two different logging clients are respectively haemoglobin (HGB or Hb): 14g/dl and hemoglobin (HGB or Hb): 14.5g/dl, the feature values that the processing unit 120 can extract are the feature value a1 and the feature value a2, respectively, wherein the feature value a1 is the value 14, and the feature value a2 is the value 14.5; then, by the above calculation method for the numerical type eigenvalue, the difference between the eigenvalue a1 and the eigenvalue a2 can be determined to be 0.03, (calculation formula (14.5-14)/14.5 ≈ 0.03), exceeding the preset threshold range-0.0001, and therefore, it can be determined that there is a difference between the two entered results. The processing unit 120 can determine, through the above determination, an entry result with a difference problem from the plurality of entry results, and then push the relevant determination information to the execution unit 130.

It should be noted that there are various reasons for the difference between the two recorded results. For example, a worker who operates the entry client to perform data entry makes a mistake, or data entered by the entry client is lost due to network delay, blockage, and the like, so that data in the entry result is incomplete. The entry client may be an intelligent terminal, such as a smart phone, a tablet computer, or other suitable intelligent devices.

The database may be any type of database suitable for use, and the stored result may match the data item stored in the database, for example, if the database is a relational database, the stored result may be stored in the form of a key-value pair.

The execution unit 130 may be configured to: and responding to the processing unit to judge that the two input results are different, and pushing difference information of the input results to an expert system to request the expert system to re-input the diagnosis and treatment data items corresponding to the input results with the difference.

As can be appreciated, the expert system is a system that makes professional judgments based on prior art, and may be an intelligent system, e.g., built through artificial intelligence, or may be an artificial client, with judgments made by clinicians or researchers. The difference information of the input result may include the input result itself and identification information of the diagnosis and treatment data item corresponding to the input result, so that the expert system determines the diagnosis and treatment data item that needs to be re-input. For example, the expert system may match the input result and the diagnosis and treatment data item, respectively, the matching may be semantic matching of keywords, and the expert system may perform keyword extraction based on a preset algorithm (e.g., a natural language processing algorithm) and then match based on the keywords. In particular, if the logging result is hemoglobin (HGB or Hb): 14.5 g/dl; the hemoglobin can be extracted as a keyword, then the hemoglobin is matched in all the diagnosis and treatment data items, after several groups of candidate diagnosis and treatment data items are matched, the identification information of the input result can be further compared with the identification information of the several groups of candidate diagnosis and treatment data items, and if the identification information is consistent, the candidate diagnosis and treatment data items are determined to be corresponding to the input result. The identification information may be, for example, data entry time, entry personnel signature information, and the like.

Further, the expert system may re-enter based on the determined clinical data items, and may feed back the entered results to the execution unit 130 for storage, such as to a database. In addition, the execution unit 130 may also directly store the entry result in the database in response to the processing unit 120 determining that the two entry results are the same.

Optionally, when the diagnosis and treatment data item is entered by the expert system, the diagnosis and treatment data item further includes supplementary data in addition to the corrected diagnosis and treatment data item, where the supplementary data includes an entry end for recording entry data, entry time, and/or a comparison confirmation trace.

In summary, according to the technical scheme of the invention, noise reduction and filtering can be performed on data in different information systems by using the standard data template, noise and pseudo data in original clinical diagnosis and treatment data are removed, the validity of the data is improved to a certain extent, double entry is performed on diagnosis and treatment data items in the data entry process, the entry result is verified, and then problem data can be corrected by using an expert system, so that the accuracy of the entered diagnosis and treatment data items is further improved, and the medical research based on the data is facilitated.

As a second aspect of the present invention, there is provided a server, wherein the server comprises the clinical medical data entry system of the present invention.

As a third aspect of the present invention, a clinical diagnosis and treatment data entry method is provided. Figure 2 schematically illustrates a clinical data entry method 200 according to one embodiment of the present invention.

As shown in fig. 2, the clinical diagnosis and treatment data entry method 200 includes: s210, original clinical diagnosis and treatment data are screened by using a standard data template to obtain a plurality of diagnosis and treatment data items matched with the standard data template, wherein the standard data template comprises baseline information, diagnosis and treatment pass information and treatment result information which accord with CDISC (compact disc computer aided design) standards; s220, receiving two input results of at least two input clients based on the same diagnosis and treatment data item aiming at any one of the diagnosis and treatment data items, and judging whether the two input results are different or not; and S230, responding to the judgment that the two input results are different, pushing the difference information of the input results to an expert system to request the expert system to re-input the diagnosis and treatment data items corresponding to the input results with the difference.

In one embodiment, the raw clinical data is from at least one of the following data sources: batch imported form data, data obtained from a hospital information system HIS, electronic medical record EMR data, image archiving and communication system PACS data, hospital laboratory information management system LIS data.

In one embodiment, the determining whether there is a difference between the two entered results includes: respectively extracting a characteristic value A1 and a characteristic value A2 of the two recorded results, judging whether the difference value between the characteristic value A1 and the characteristic value A2 is within a preset threshold range, if so, determining that the two recorded results are the same, and if not, determining that the two recorded results are different.

In one embodiment, the method further comprises: and responding to the judgment that the two entry results are the same, and storing the entry results to a database.

It will be appreciated that the specific features described herein in relation to the clinical data entry system of the first aspect may similarly be applied to similar extensions in the clinical data entry method of the third aspect. For the sake of simplicity, it is not described in detail.

It should be understood that the various elements of the clinical data entry system 100 of the present invention may be implemented in whole or in part by software, hardware, firmware, or a combination thereof. The units may be embedded in a processor of the computer device in a hardware or firmware form or independent of the processor, or may be stored in a memory of the computer device in a software form for being called by the processor to execute operations of the units. Each of the units may be implemented as a separate component or module, or two or more units may be implemented as a single component or module.

It will be appreciated by those of ordinary skill in the art that the schematic diagram of the clinical data entry system 100 shown in fig. 1 is merely an exemplary illustrative block diagram of a portion of the structure associated with aspects of the present invention and is not intended to limit the computer device, processor, or computer program embodying aspects of the present invention. A particular computer device, processor or computer program may include more or fewer components or modules than shown in the figures, or may combine or split certain components or modules, or may have a different arrangement of components or modules.

As a fourth aspect of the invention, a computer-readable storage medium is provided, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of the third aspect of the invention. In one embodiment, the computer program is distributed across a plurality of computer devices or processors coupled by a network such that the computer program is stored, accessed, and executed by one or more computer devices or processors in a distributed fashion. A single method step/operation, or two or more method steps/operations, may be performed by a single computer device or processor or by two or more computer devices or processors. One or more method steps/operations may be performed by one or more computer devices or processors, and one or more other method steps/operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step/operation, or perform two or more method steps/operations.

It will be understood by those skilled in the art that all or part of the steps of the clinical diagnostic data entry method of the present invention may be directed to relevant hardware, such as a computer device or a processor, by a computer program, which may be stored in a non-transitory computer-readable storage medium, and which when executed performs the steps of the ancillary method of the present invention. Any reference herein to memory, storage, databases, or other media may include non-volatile and/or volatile memory, as appropriate. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (prom), electrically programmable ROM (eprom), electrically erasable programmable ROM (eeprom), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, hard disk, solid state disk, and the like. Examples of volatile memory include Random Access Memory (RAM), external cache memory, and the like.

The respective technical features described above may be arbitrarily combined. Although not all possible combinations of features are described, any combination of features should be considered to be covered by the present specification as long as there is no contradiction between such combinations.

While the present invention has been described in connection with the embodiments, it is to be understood by those skilled in the art that the foregoing description and drawings are merely illustrative and not restrictive of the broad invention, and that this invention not be limited to the disclosed embodiments. Various modifications and variations are possible without departing from the spirit of the invention.