Method and device for evaluating medical record content

Abstract

The invention provides a medical record content evaluation method. The method comprises the following steps: acquiring an unstructured electronic medical record; and based on a natural language processing technology, carrying out structured processing on the unstructured electronic medical record to obtain a structured electronic medical record, the structured electronic medical record comprising structured symptom data, sign data, examination data and test data. And generating an evaluation knowledge graph based on the historical electronic medical record, wherein the evaluation knowledge graph comprises the corresponding relationship among the historical symptom data, the historical sign data, the historical examination data and the historical test data. And evaluating the structured electronic medical record based on the evaluation knowledge graph to obtain an evaluation result. According to the method provided by the invention, the electronic medical record can be accurately evaluated.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for evaluating medical record content. Background Art

[0002] With the continuous development of science and technology, the medical field is also moving towards dataization and intelligence. Electronic medical record data is the core element of hospital informatization construction, the basic data source for the reform of medical insurance payment methods, and the key indicator of medical institution performance evaluation. Most hospitals still need to rely on the quality control department or medical record room quality control personnel to manually complete the quality control work of a large number of hospital operating medical records or archived medical records. The workload is large, the professionalism is strong, and the quality control efficiency and quality are difficult to guarantee. Due to different habits of doctors, there are considerable differences in the medical records of different patients, so it is very difficult to make a unified evaluation of the archived electronic medical records.

[0003] Therefore, how to accurately evaluate electronic medical records has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0004] Based on the above problems, the present application provides a method and device for evaluating medical record content to accurately evaluate electronic medical records.

[0005] A method for evaluating medical record content is provided, the method comprising the following steps:

[0006] Access to unstructured electronic medical records;

[0007] Structuring the unstructured electronic medical record based on natural language processing technology to obtain a structured electronic medical record, wherein the structured electronic medical record includes structured symptom data, physical sign data, examination data and laboratory test data;

[0008] Generate an evaluation knowledge graph based on historical electronic medical records, wherein the evaluation knowledge graph includes the correspondence between historical symptom data, historical physical sign data, historical examination data, and historical laboratory test data;

[0009] The structured electronic medical record is evaluated based on the evaluation knowledge graph to obtain an evaluation result.

[0010] In a possible implementation, the structuring of the unstructured electronic medical record based on natural language processing technology to obtain the structured electronic medical record includes:

[0011] Processing unstructured electronic medical records based on natural language processing models of various medical record types to obtain processing results, wherein the natural language processing models include an admission history module, a past history module, a medical history module, a physical examination module, a diagnosis module, a symptom module, an echocardiogram module, an electrocardiogram module, a chest x-ray report module, a cardiac CT report module, and an electroencephalogram module;

[0012] The processing results are visualized to obtain a structured electronic medical record.

[0013] In a possible implementation, the method further comprises:

[0014] Performing mutual exclusivity detection on the contents in the unstructured electronic medical record;

[0015] The unstructured electronic medical record that passes the mutual exclusivity test is used as the unstructured electronic medical record and a step of structuring the unstructured electronic medical record based on natural language processing technology is performed.

[0016] The present application also provides a device for evaluating medical record content, the device comprising the following modules:

[0017] The acquisition module is used to obtain unstructured electronic medical records;

[0018] A structured processing module, used for performing structured processing on the unstructured electronic medical record based on natural language processing technology to obtain a structured electronic medical record, wherein the structured electronic medical record includes structured symptom data, physical sign data, examination data and laboratory test data;

[0019] A knowledge graph module, used to generate an evaluation knowledge graph based on historical electronic medical records, wherein the evaluation knowledge graph includes the correspondence between historical symptom data, historical physical sign data, historical examination data, and historical laboratory test data;

[0020] An evaluation module is used to evaluate the structured electronic medical record based on the evaluation knowledge graph to obtain an evaluation result.

[0021] In a possible implementation, the structured processing module is specifically used to:

[0022] Processing unstructured electronic medical records based on natural language processing models of various medical record types to obtain processing results, wherein the natural language processing models include an admission history module, a past history module, a medical history module, a physical examination module, a diagnosis module, a symptom module, an echocardiogram module, an electrocardiogram module, a chest x-ray report module, a cardiac CT report module, and an electroencephalogram module;

[0023] The processing results are visualized to obtain a structured electronic medical record.

[0024] In a possible implementation, the device further includes a detection module, and the detection module is specifically configured to:

[0025] Performing mutual exclusivity detection on the contents in the unstructured electronic medical record;

[0026] The unstructured electronic medical record that passes the mutual exclusivity test is used as the unstructured electronic medical record and a step of structuring the unstructured electronic medical record based on natural language processing technology is performed.

[0027] The present application also provides an electronic device, the electronic device comprising a processor and a memory:

[0028] The memory is used to store a computer program and transmit the computer program to the processor;

[0029] The processor is used to execute the steps of the above-mentioned medical record content evaluation method according to the instructions in the computer program.

[0030] The present application also provides a computer-readable storage medium, which is used to store a computer program. When the computer program is executed by an electronic device, it implements the steps of the above-mentioned medical record content evaluation method.

[0031] Compared with the prior art, this application has the following beneficial effects:

[0032] The method provided in this application uses natural language processing technology to structure unstructured electronic medical records, extract and structure the symptoms, signs, examination and test data in the medical records. This not only improves the readability and analyzability of medical record data, but also lays the foundation for subsequent data mining and intelligent analysis. In the prior art, the quality control of medical records in most hospitals still relies on manual review, which is not only time-consuming and labor-intensive, but also prone to subjective bias. This application constructs an evaluation knowledge graph and uses the data relationships in historical electronic medical records to intelligently evaluate structured electronic medical records. This evaluation mechanism based on knowledge graphs can automatically identify anomalies and deficiencies in medical records and improve the accuracy and objectivity of evaluation. Traditional quality control work focuses on form and neglects connotation, and it is difficult to fully reflect the true quality of medical records. This application significantly improves the efficiency and accuracy of quality control work through systematic structured processing and evaluation mechanisms. The system can quickly process a large amount of medical record data and promptly feedback quality control results to help hospitals discover and correct problems in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0034] Figure 1 A flowchart of a method for evaluating medical record content provided in an embodiment of the present application;

[0035] Figure 2 A schematic diagram of the conversion of a structured electronic medical record provided in an embodiment of the present application;

[0036] Figure 3 A schematic diagram of the structure of a medical record content evaluation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] As described above, most hospitals still need to rely on the quality control department or medical record room quality control personnel to manually complete the quality control work of a large number of running medical records or archived medical records in the hospital. The workload is large, the professionalism is strong, and the quality control efficiency and quality are difficult to guarantee. Due to different habits of doctors, there are considerable differences in the medical records of different patients, so it is very difficult to make a unified evaluation of the archived electronic medical records.

[0038] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] It is understandable that the method provided in the present application can be applied to a processing device, which is a processing device that can obtain unstructured electronic medical records, such as a terminal device or a server that can obtain unstructured electronic medical records. The method provided in the present application can be executed independently by a terminal device or a server, or it can be applied to a network scenario in which a terminal device and a server communicate, and is executed by the cooperation of a terminal device and a server. Among them, the terminal device can be a computer, a mobile phone and other devices. The server can be understood as an application server or a Web server. In actual deployment, the server can be a stand-alone server or a cluster server.

[0040] Figure 1 A flowchart of a method for evaluating medical record content provided in this application, the method comprising the following steps:

[0041] S101: Access unstructured electronic medical records.

[0042] Processing equipment can access unstructured electronic medical records.

[0043] Electronic medical records (EMRs) are a key component of hospital informatization, recording patients' diagnoses, treatment processes, and health conditions. However, many electronic medical records exist in unstructured form, that is, they are mainly text descriptions, including doctors' handwritten or voice transcriptions. Although these unstructured data are detailed, they are not easy to be processed and analyzed by computers. Obtaining unstructured electronic medical records is the starting point of the entire process, and they usually need to be extracted from the hospital's information system. This process involves compatible processing of multiple data formats, including PDF, Word documents, scanned images, etc. The system needs to have strong data collection capabilities to ensure accurate extraction of medical record content from different sources and formats. In addition, data privacy and security issues must be considered to ensure that medical record data is not leaked or tampered with during extraction and transmission. By obtaining unstructured electronic medical records, the system provides basic data input for subsequent structured processing, allowing the entire process to proceed smoothly.

[0044] In a possible implementation, before performing subsequent steps, the processing device may perform a mutual exclusivity test on the content in the unstructured electronic medical record, and use the unstructured electronic medical record that passes the mutual exclusivity test as the unstructured electronic medical record to perform a step of structuring the unstructured electronic medical record based on natural language processing technology. Mutual exclusivity is a test to determine whether there are mutually exclusive contents in the electronic medical record. For example, the body temperature corresponding to fever is 33 degrees, and the two are obviously mutually exclusive, so the mutual exclusivity test cannot pass.

[0045] S102: Structuring the unstructured electronic medical record based on natural language processing technology to obtain a structured electronic medical record.

[0046] The processing device can perform structured processing on unstructured electronic medical records based on natural language processing technology to obtain structured electronic medical records, which include structured symptom data, physical sign data, examination data and laboratory test data;

[0047] Natural language processing (NLP) technology plays an important role in converting unstructured electronic medical records into structured data. NLP technology can automatically extract key medical information from medical records, such as symptom descriptions, physical sign observations, test results, and laboratory data, by analyzing and understanding the semantics of text data. First, the system will perform word segmentation and part-of-speech tagging on the electronic medical record text, which is the basis for understanding the semantics of the text. Then, through named entity recognition (NER) technology, the system can identify medical terms and entities in the text, such as drug names, disease names, etc. Subsequently, syntactic analysis and relationship extraction technology are used to structure the relationship between these entities. For example, "the patient has a high fever accompanied by cough" is parsed into "symptoms: high fever, symptoms: cough". This structuring process not only improves the readability and analyzability of the data, but also lays the foundation for subsequent data mining and analysis. Through the application of NLP technology, hospitals can manage and utilize electronic medical record data more efficiently and improve the quality and efficiency of medical services.

[0048] In a possible implementation, the processing device may process the unstructured electronic medical record based on a natural language processing model of multiple medical record types to obtain a processing result, wherein the natural language processing model includes an admission history module, a past history module, a medical history module, a physical examination module, a diagnosis module, a symptom module, an echocardiogram module, an electrocardiogram module, a chest x-ray report module, a cardiac CT report module, and an electroencephalogram module. The processing result is then visualized to obtain a structured electronic medical record.

[0049] Figure 2 A schematic diagram of the conversion of a structured electronic medical record provided in an embodiment of the present application.

[0050] S103: Generate an evaluation knowledge graph based on historical electronic medical records.

[0051] The processing device generates an evaluation knowledge graph based on historical electronic medical records, and the evaluation knowledge graph includes the correspondence between historical symptom data, historical physical sign data, historical examination data and historical test data.

[0052] Knowledge graph is a technology that presents information in the form of graphics, which can effectively represent entities and their relationships. In this application, generating an evaluation knowledge graph based on historical electronic medical records is one of the key steps. By analyzing a large amount of historical medical record data, the system can identify the relationship between common symptoms, signs, test results and diagnoses, and store these relationships in the form of a knowledge graph. The knowledge graph not only includes simple entity relationships, but also can represent more complex multi-level interactive relationships, such as different test results that may result from a symptom at different stages of the disease. This process requires the use of machine learning and graph database technology to automatically mine and store these relationships. By constructing an evaluation knowledge graph, the system can establish connections between the structured data of the new medical record and the historical data, and identify abnormal patterns or deficiencies. This knowledge graph-based evaluation method not only improves the accuracy and objectivity of medical record evaluation, but also provides doctors with new diagnostic and treatment recommendations to support more accurate medical decision-making.

[0053] S104: Evaluate the structured electronic medical record based on the evaluation knowledge graph to obtain an evaluation result.

[0054] The processing device can evaluate the structured electronic medical record based on the evaluation knowledge graph to obtain an evaluation result.

[0055] After completing the structured processing and knowledge graph construction, the system will intelligently evaluate the structured electronic medical records based on the evaluation knowledge graph. The evaluation process first matches the symptoms, signs, examination and test data of the structured electronic medical records with the knowledge graph to identify common association patterns and differences. The system will automatically determine whether the data in the medical record is complete, the logic is consistent, and the diagnosis is sufficient based on the predefined evaluation criteria. For example, whether the strength of the association between certain symptoms and specific diseases is consistent with the empirical value of historical data. If not, the system will mark it as abnormal. In addition, the evaluation results also include potential risk warnings and optimization suggestions that may exist in the medical records. This evaluation process can not only quickly identify problems in medical records, but also provide data-based decision support for doctors and quality control personnel. Through the intelligent evaluation mechanism, hospitals can significantly improve the efficiency and accuracy of medical record quality control and ensure the high quality and reliability of medical record data. This method provides hospitals with a powerful tool for improving the quality and efficiency of medical services.

[0056] The method provided in this application uses natural language processing technology to structure unstructured electronic medical records, extract and structure the symptoms, signs, examination and test data in the medical records. This not only improves the readability and analyzability of medical record data, but also lays the foundation for subsequent data mining and intelligent analysis. In the prior art, the quality control of medical records in most hospitals still relies on manual review, which is not only time-consuming and labor-intensive, but also prone to subjective bias. This application constructs an evaluation knowledge graph and uses the data relationships in historical electronic medical records to intelligently evaluate structured electronic medical records. This evaluation mechanism based on knowledge graphs can automatically identify anomalies and deficiencies in medical records and improve the accuracy and objectivity of evaluation. Traditional quality control work focuses on form and neglects connotation, and it is difficult to fully reflect the true quality of medical records. This application significantly improves the efficiency and accuracy of quality control work through systematic structured processing and evaluation mechanisms. The system can quickly process a large amount of medical record data and promptly feedback quality control results to help hospitals discover and correct problems in a timely manner.

[0057] The present application also provides a Figure 3 The schematic diagram of the structure of the medical record content evaluation device shown in FIG. 300 includes the following modules:

[0058] An acquisition module 301 is used to acquire unstructured electronic medical records;

[0059] A structured processing module 302 is used to perform structured processing on the unstructured electronic medical record based on natural language processing technology to obtain a structured electronic medical record, wherein the structured electronic medical record includes structured symptom data, physical sign data, examination data and laboratory test data;

[0060] The knowledge graph module 303 is used to generate an evaluation knowledge graph based on historical electronic medical records, wherein the evaluation knowledge graph includes the correspondence between historical symptom data, historical physical sign data, historical examination data, and historical laboratory test data;

[0061] The evaluation module 304 is used to evaluate the structured electronic medical record based on the evaluation knowledge graph to obtain an evaluation result.

[0062] In a possible implementation, the structured processing module is specifically used to:

[0063] Processing unstructured electronic medical records based on natural language processing models of various medical record types to obtain processing results, wherein the natural language processing models include an admission history module, a past history module, a medical history module, a physical examination module, a diagnosis module, a symptom module, an echocardiogram module, an electrocardiogram module, a chest x-ray report module, a cardiac CT report module, and an electroencephalogram module;

[0064] The processing results are visualized to obtain a structured electronic medical record.

[0065] In a possible implementation, the device further includes a detection module, and the detection module is specifically configured to:

[0066] Performing mutual exclusivity detection on the contents in the unstructured electronic medical record;

[0067] The unstructured electronic medical record that passes the mutual exclusivity test is used as the unstructured electronic medical record and a step of structuring the unstructured electronic medical record based on natural language processing technology is performed.

[0068] The device provided in this application uses natural language processing technology to structure unstructured electronic medical records, extracting and structuring the symptoms, signs, examination and test data in the medical records. This not only improves the readability and analyzability of medical record data, but also lays the foundation for subsequent data mining and intelligent analysis. In the prior art, the quality control of medical records in most hospitals still relies on manual review, which is not only time-consuming and labor-intensive, but also prone to subjective bias. This application constructs an evaluation knowledge graph and uses the data relationships in historical electronic medical records to intelligently evaluate structured electronic medical records. This evaluation mechanism based on knowledge graphs can automatically identify anomalies and deficiencies in medical records and improve the accuracy and objectivity of evaluation. Traditional quality control work focuses on form and neglects connotation, and it is difficult to fully reflect the true quality of medical records. This application significantly improves the efficiency and accuracy of quality control work through systematic structured processing and evaluation mechanisms. The system can quickly process a large amount of medical record data and promptly feedback quality control results to help hospitals discover and correct problems in a timely manner.

[0069] An embodiment of the present application also provides a device for evaluating medical record content, wherein the device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device performs the steps of the medical record content evaluation method described in any embodiment of the present application.

[0070] In practical applications, the computer-readable storage medium may be any combination of one or more computer-readable media, which may be a computer-readable signal medium or a computer-readable storage medium.

[0071] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0072] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0073] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0074] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0075] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely schematic, in which the unit described as a separate component may or may not be physically separated, and the component prompted as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0076] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for evaluating medical record content, characterized in that: include: Access to unstructured electronic medical records; Structuring the unstructured electronic medical record based on natural language processing technology to obtain a structured electronic medical record, wherein the structured electronic medical record includes structured symptom data, physical sign data, examination data and laboratory test data; Generate an evaluation knowledge graph based on historical electronic medical records, wherein the evaluation knowledge graph includes the correspondence between historical symptom data, historical physical sign data, historical examination data, and historical laboratory test data; The structured electronic medical record is evaluated based on the evaluation knowledge graph to obtain an evaluation result.

2. The method according to claim 1, characterized in that: The structured processing of the unstructured electronic medical record based on the natural language processing technology to obtain the structured electronic medical record includes: Processing unstructured electronic medical records based on natural language processing models of multiple medical record types to obtain processing results, wherein the natural language processing models include an admission history module, a past history module, a medical history module, a physical examination module, a diagnosis module, a symptom module, an echocardiogram module, an electrocardiogram module, a chest x-ray report module, a cardiac CT report module, and an electroencephalogram module; The processing results are visualized to obtain a structured electronic medical record.

3. The method according to claim 1, characterized in that The method further comprises: Performing mutual exclusivity detection on the contents in the unstructured electronic medical record; The unstructured electronic medical record that passes the mutual exclusivity test is used as the unstructured electronic medical record and a step of structuring the unstructured electronic medical record based on natural language processing technology is performed.

4. A device for evaluating medical record content, characterized in that: include: The acquisition module is used to obtain unstructured electronic medical records; A structured processing module, used for performing structured processing on the unstructured electronic medical record based on natural language processing technology to obtain a structured electronic medical record, wherein the structured electronic medical record includes structured symptom data, physical sign data, examination data and laboratory test data; A knowledge graph module, used to generate an evaluation knowledge graph based on historical electronic medical records, wherein the evaluation knowledge graph includes the correspondence between historical symptom data, historical physical sign data, historical examination data, and historical laboratory test data; An evaluation module is used to evaluate the structured electronic medical record based on the evaluation knowledge graph to obtain an evaluation result.

5. The device according to claim 4, characterized in that The structured processing module is specifically used for: Processing unstructured electronic medical records based on natural language processing models of multiple medical record types to obtain processing results, wherein the natural language processing models include an admission history module, a past history module, a medical history module, a physical examination module, a diagnosis module, a symptom module, an echocardiogram module, an electrocardiogram module, a chest x-ray report module, a cardiac CT report module, and an electroencephalogram module; The processing results are visualized to obtain a structured electronic medical record.

6. The device according to claim 4, characterized in that The device further includes a detection module, which is specifically used to: Performing mutual exclusivity detection on the contents in the unstructured electronic medical record; The unstructured electronic medical record that passes the mutual exclusivity test is used as the unstructured electronic medical record and a step of structuring the unstructured electronic medical record based on natural language processing technology is performed.

7. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store the computer program; The processor is used to execute the computer program to implement the story allocation method based on big data as described in any one of claims 1 to 3.

8. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, the story allocation method based on big data as described in any one of claims 1 to 3 is implemented.

Images