Special disease library filling method and device, electronic equipment, storage medium and product

Through automated data extraction technology based on medical instruction database and large language models, the problem of low efficiency and accuracy of specialized disease database filling is solved, efficient and accurate data filling is achieved, and the quality of disease monitoring and epidemiological research is improved.

CN119007903AActive Publication Date: 2024-11-22ANHUI IFLYHEALTH CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411024416.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-22
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

The existing special disease database filling method relies on manual input, resulting in low efficiency and low accuracy, especially when the data volume is large, which is prone to errors, affecting the quality of disease monitoring and epidemiological research.

Method used

Based on the pre-constructed medical instruction library and patient medical data, data extraction instructions are determined and executed, and data is automatically extracted and filled from the items to be filled in the special disease database, and data extraction and verification are used to improve the automation and accuracy of filling out. sex.

Benefits of technology

Automatic acquisition and filling of data in specialized disease databases has been realized, which significantly improves the efficiency and accuracy of filling, reduces manual errors, and improves data quality and research reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007903A_ABST
    Figure CN119007903A_ABST
Patent Text Reader

Abstract

The invention provides a special disease library filling method and device, electronic equipment, a storage medium and a product, and the method comprises the steps: determining a data extraction instruction corresponding to a to-be-filled item of a special disease library based on a pre-constructed medical instruction knowledge base and pre-collected medical data of a special patient; the medical instruction library comprises a data extraction instruction template corresponding to the to-be-filled item; extracting data corresponding to the to-be-filled items in the special disease library from the medical data of the special patient by executing the data extraction instruction; and filling the to-be-filled items of the special disease database with the data. By adopting the technical scheme of the invention, automatic acquisition of the data corresponding to the to-be-filled item of the special disease library and automatic filling of the data corresponding to the to-be-filled item of the special disease library can be realized, and the efficiency and accuracy of filling and reporting of the special disease library are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data extraction technology, and in particular to a method, device, electronic device, storage medium and product for filling in a special disease database. Background Art

[0002] In the medical industry, the establishment and maintenance of disease-specific databases is crucial for disease monitoring, epidemiological research, and public health management. The existing method of filling in disease-specific databases relies on manual input, that is, medical personnel manually enter the patient's clinical information, diagnosis results, treatment process, and follow-up data. Although manual data entry can ensure the specificity and meticulousness of data entry, manual filling of disease-specific databases is inefficient and prone to errors. Especially when the amount of data is large, the tediousness and error rate of manual processing become the main factors limiting efficiency, resulting in low efficiency and accuracy in filling in disease-specific databases. Summary of the invention

[0003] Based on the above needs, the present application proposes a method, device, electronic device, storage medium and product for filling in a special disease database, which can improve the efficiency and accuracy of filling in a special disease database.

[0004] To achieve the above objectives, this application proposes the following technical solutions:

[0005] According to a first aspect of an embodiment of the present application, a method for filling in a special disease database is provided, comprising:

[0006] Based on a pre-built medical instruction library and pre-collected medical data of patients with specific diseases, determining data extraction instructions corresponding to the items to be filled in the specific disease library; the medical instruction library includes data extraction instruction templates corresponding to the items to be filled;

[0007] By executing the data extraction instruction, the data corresponding to the item to be filled in the special disease database is extracted from the medical data of the special disease patient;

[0008] The data is filled into the items to be filled in the special disease database.

[0009] Optionally, based on a pre-built medical instruction library and pre-collected medical data of patients with specific diseases, determining a data extraction instruction corresponding to an item to be filled in the specific disease library includes:

[0010] According to the preset instruction mapping rules, a data extraction instruction template corresponding to the item to be filled in the special disease library is determined from the pre-built medical instruction library; the instruction mapping rules include the corresponding relationship between the item to be filled and the data extraction instruction template;

[0011] According to the preset medical record fragment mapping rule, the medical record fragment extraction source corresponding to the item to be filled in the special disease database is determined from the pre-collected medical data of the special disease patient; the medical record fragment mapping rule includes the corresponding relationship between the item to be filled and the medical record fragment extraction source;

[0012] Based on the medical record fragment extraction source corresponding to the item to be filled in the special disease library and the data extraction instruction template corresponding to the item to be filled in the special disease library, the data extraction instruction corresponding to the item to be filled in the special disease library is constructed.

[0013] Optionally, based on the medical record fragment extraction source corresponding to the item to be filled in the special disease database and the data extraction instruction template corresponding to the item to be filled in the special disease database, constructing the data extraction instruction corresponding to the item to be filled in the special disease database includes:

[0014] Fill the medical record fragment extraction source corresponding to the item to be filled in the special disease database into the data extraction instruction template corresponding to the item to be filled in the special disease database, and obtain the data extraction instruction corresponding to the item to be filled in the special disease database.

[0015] Optionally, by executing the data extraction instruction, data corresponding to the item to be filled in the special disease database is extracted from the medical data of the special disease patient, including:

[0016] According to the preset medical record fragment mapping rule, extract the medical record fragment corresponding to the item to be filled in the special disease database from the medical data of the special disease patient;

[0017] By executing the data extraction instruction, the data corresponding to the item to be filled in the special disease database is extracted from the medical record fragment corresponding to the item to be filled in the special disease database.

[0018] Optionally, if the item to be filled in the special disease database has a dependency relationship with other items to be filled in the special disease database, then the item to be filled in the special disease database and other items to be filled in the special disease database that have a dependency relationship with the item to be filled in the special disease database correspond to the same data extraction instruction;

[0019] By executing the data extraction instruction, data corresponding to the item to be filled in the special disease database is extracted from the medical data of the special disease patient, including:

[0020] By executing the data extraction instruction, data corresponding to the item to be filled in the special disease library and data corresponding to other special disease library items to be filled that have a dependency relationship with the item to be filled in the special disease library are extracted from the medical data of the special disease patient.

[0021] Optionally, by executing the data extraction instruction, data corresponding to the item to be filled in the special disease database is extracted from the medical data of the special disease patient, including:

[0022] Inputting the data extraction instructions of the items to be filled in the special disease database and the medical data of the special disease patients into the pre-built data extraction model to obtain the reporting data of the items to be filled in;

[0023] The data extraction model is used to extract data corresponding to the items to be filled in the special disease database from the medical data of the special disease patients by executing the data extraction instruction; wherein, the data extraction model is a large language model.

[0024] Optionally, before filling the data into the items to be filled in the disease-specific database, the method further includes:

[0025] According to the preset quality inspection rules, the data corresponding to the items to be filled in the special disease database are quality inspected to determine the quality inspection information corresponding to the data;

[0026] If the quality inspection information indicates that the quality inspection is qualified, the data is filled into the item to be filled in the special disease database;

[0027] If the quality inspection information indicates that the quality inspection is unqualified, a prompt message indicating that the data output is wrong is output.

[0028] Optionally, the method for filling in the special disease database also includes:

[0029] If the quality inspection information indicates that the data is unqualified, the training samples corresponding to the items to be filled in the special disease database and the real data corresponding to the training samples are collected; wherein the training samples corresponding to the items to be filled in the special disease database include: data extraction instructions corresponding to the items to be filled in the special disease database and sample medical data corresponding to the items to be filled in the special disease database;

[0030] Inputting the training sample into the data extraction model to obtain prediction data corresponding to the training sample;

[0031] Based on the difference between the real data corresponding to the training samples and the predicted data corresponding to the training samples, parameters of the data extraction model are adjusted.

[0032] Optionally, based on the pre-built medical instruction library and the pre-collected medical data of patients with specific diseases, before determining the data extraction instruction corresponding to the item to be filled in the specific disease library, it also includes:

[0033] The to-be-filled form of the special disease database is identified, and at least one to-be-filled item of the special disease database is extracted from the to-be-filled form.

[0034] According to a second aspect of an embodiment of the present application, a device for filling in a special disease database is provided, comprising:

[0035] An instruction determination module is used to determine the data extraction instruction corresponding to the item to be filled in the special disease library based on the pre-built medical instruction library and the pre-collected medical data of the special disease patient; the medical instruction library includes the data extraction instruction template corresponding to the item to be filled;

[0036] A data determination module, used to extract data corresponding to the items to be filled in the special disease database from the medical data of the special disease patient by executing the data extraction instruction;

[0037] The data filling module is used to fill the data into the items to be filled in the special disease database.

[0038] According to a third aspect of an embodiment of the present application, there is provided an electronic device, including: a memory and a processor;

[0039] The memory is connected to the processor and is used to store programs;

[0040] The processor is used to implement the above-mentioned method for filling in the special disease database by running the program in the memory.

[0041] According to a fourth aspect of an embodiment of the present application, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method for filling in the special disease database is implemented.

[0042] According to a fifth aspect of an embodiment of the present application, a computer program product is provided, including computer program instructions, which, when executed by a processor, enable the processor to implement the above-mentioned method for filling in a special disease database.

[0043] The method for filling the special disease database proposed in this application determines the data extraction instructions corresponding to the items to be filled in the special disease database based on the pre-built medical instruction knowledge base and the pre-collected medical data of special disease patients; the medical instruction library includes data extraction instruction templates corresponding to the items to be filled; by executing the data extraction instructions, the data corresponding to the items to be filled in the special disease database are extracted from the medical data of the special disease patients; and the data is filled into the items to be filled in the special disease database. The technical solution of this application can realize the automatic acquisition of data corresponding to the items to be filled in the special disease database, and the automatic filling of data corresponding to the items to be filled in the special disease database, thereby improving the efficiency and accuracy of filling in the special disease database. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] 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 embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0045] Figure 1 A flowchart of a method for filling in a special disease database provided in an embodiment of the present application;

[0046] Figure 2 A schematic diagram of a processing flow for extracting data corresponding to items to be filled in a disease-specific database provided in an embodiment of the present application;

[0047] Figure 3 A schematic diagram of a processing flow for data quality inspection corresponding to items to be filled in a disease-specific database provided in an embodiment of the present application;

[0048] Figure 4 A schematic diagram of a processing flow for training a data extraction model provided in an embodiment of the present application;

[0049] Figure 5 A schematic diagram of the structure of a device for filling in a special disease database provided in an embodiment of the present application;

[0050] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The technical solution of the embodiment of the present application is applicable to the application scenario of data extraction, and is specifically used in the application scenario of data extraction for filling in the special disease database. The technical solution of the embodiment of the present application can realize the automatic acquisition and automatic filling of the filling data of the items to be filled in the special disease database, thereby improving the efficiency and accuracy of filling in the special disease database.

[0052] A disease-specific database, also known as a disease-specific database or a single disease database, is a standardized database specifically established for a certain disease or disease type that contains the clinical data of patients with that disease. The establishment of this database aims to collect and integrate comprehensive information on a specific disease or disease type, including multi-dimensional data such as the patient's biological information, genotype, lifestyle, drug use, and laboratory test results, in order to conduct in-depth disease research and clinical scientific research.

[0053] In the medical industry, the establishment and maintenance of disease-specific databases are crucial for disease monitoring, epidemiological research, and public health management. The traditional method of filling in disease-specific databases relies on manual input, that is, medical personnel manually enter the patient's clinical information, diagnosis results, treatment process, and follow-up data. Although manual data entry can ensure the specificity and meticulousness of data entry, manual filling of disease-specific databases is inefficient, especially when faced with a large amount of data. It is time-consuming and labor-intensive. In addition, manual filling of disease-specific databases is prone to errors, such as input errors, omission of important information, or data inconsistency. These problems may lead to a decline in data quality, resulting in low accuracy in filling in disease-specific databases, affecting subsequent data analysis and the accuracy of research results.

[0054] Based on this, the present application proposes a method for filling a special disease database. This technical solution can realize the automatic acquisition and automatic filling of reporting data for items to be filled in the special disease database, thereby solving the problem of low efficiency and accuracy in filling out special disease databases in the prior art.

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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.

[0056] Exemplary Methods

[0057] See also Figure 1 As shown, the embodiment of the present application proposes a method for filling in a special disease database. The method comprises:

[0058] S101. Based on a pre-built medical instruction library and pre-collected medical data of patients with specific diseases, determine data extraction instructions corresponding to the items to be filled in the specific disease library.

[0059] Specifically, for the special disease databases corresponding to different symptoms, there are corresponding special disease forms that need to be filled in, and the special disease forms are used as the to-be-filled forms of the special disease database. The to-be-filled forms of the special disease database corresponding to the symptoms list the items that need to be filled in the to-be-filled forms when the special disease database corresponding to the symptoms is filled in, that is, the to-be-filled items of the special disease database. For example, the to-be-filled forms of the special disease database include the clinical information, diagnosis results, treatment process, and follow-up data of the patients with special diseases waiting to be filled. For the clinical information in the to-be-filled forms of the special disease database corresponding to coronary heart disease, the to-be-filled forms include: age, gender, and occupation waiting to be filled in, the diagnosis results include: family history, past medical history, and comorbidities waiting to be filled in, the treatment process includes: blood pressure, heart rate, weight, height, blood lipids, blood sugar, anesthesia methods, and drug treatment information waiting to be filled in, and the follow-up data include: re-hospitalization, eating habits, and exercise habits waiting to be filled in. Therefore, this embodiment first needs to extract the to-be-filled items of the special disease database from the to-be-filled forms of the special disease database.

[0060] After extracting the items to be filled in the special disease library corresponding to the symptoms, this embodiment needs to determine the data extraction instructions corresponding to the items to be filled in the special disease library based on the pre-constructed medical instruction library and the pre-collected medical data of the special disease patient. Among them, the medical instruction library includes data extraction instruction templates corresponding to the items to be filled. The data extraction instruction templates corresponding to the items to be filled in the medical instruction library in this embodiment are all designed by medical personnel with professional medical knowledge. Therefore, the data extraction instructions determined by the data extraction instruction templates in the medical instruction library are highly professional and scientific. The data extraction instruction templates corresponding to the items to be filled in this embodiment are designed based on the data extraction intention and data output standard of the items to be filled, that is, the data extraction instruction templates corresponding to the items to be filled include the data extraction intention and data output standard of the items to be filled. In addition, the medical instruction library constructed in this embodiment can include data extraction instruction templates corresponding to the items to be filled in the special disease library corresponding to several symptoms, or a medical instruction library can be constructed corresponding to each special disease library corresponding to each symptom, and the medical instruction library corresponding to the special disease library corresponding to a symptom only includes the data extraction instruction templates corresponding to the items to be filled in the special disease library corresponding to the symptom.

[0061] The medical data of the special disease patient collected in advance in this embodiment is the medical record data collected from the electronic medical record system of the hospital or the physical examination data collected from the system of the physical examination hospital. That is, the medical data includes medical record data and physical examination data. For example, the medical record data included in the electronic medical record system of the hospital covers the patient's basic information, admission and discharge records, detailed medical history, diagnosis information, treatment information, test results, imaging examination results, drug prescriptions, and clinician's notes. Among them, the basic information usually includes the patient's name, ID number, date of birth, occupation, etc., which are usually recorded in the admission record and / or discharge record. The admission record also includes the admission time, admission reason and preliminary diagnosis, etc.; the discharge record also includes the discharge date, treatment results and medical advice at the time of discharge, etc. The medical history records the patient's past medical history, family medical history and chronic disease conditions in detail. The test results cover laboratory results such as various blood tests and urine tests, while the imaging examination results include X-rays, CT scans, MRI, etc. The drug prescription records the patient's medication type, dosage and medication time in detail. Clinicians' notes include treatment plans, surgical records, and follow-up information, providing patients with a comprehensive medical record and ongoing health management.

[0062] This embodiment is for filling in a special disease database for a certain disease, so the special disease patients in the pre-collected medical data are patients diagnosed with the disease or patients having certain symptoms of the disease. For example, when filling in the special disease database for coronary heart disease, the pre-collected medical data of special disease patients include medical data of patients diagnosed with coronary heart disease or medical data of patients having symptoms of coronary heart disease (for example, medical data of patients with chest pain symptoms, etc.).

[0063] The medical data of patients with special diseases collected in this embodiment not only includes the medical data of patients with special diseases, but also records the position of each medical data in the medical data of all patients with special diseases as the extraction source when extracting medical data, that is, the medical record fragment extraction source. For example, if the item to be filled in the special disease database is age, the position of age in the medical data of all patients with special diseases may be the age recorded in the admission record, then the medical record fragment extraction source of age is admission record-age.

[0064] In this embodiment, the data extraction instruction template corresponding to the item to be filled in the special disease library can be obtained from the pre-built medical instruction library, and the medical record fragment extraction source corresponding to the item to be filled in the special disease library can be obtained from the pre-collected medical data of the special disease patient. Based on the acquired data extraction instruction template corresponding to the item to be filled and the medical record fragment extraction source, the data extraction instruction corresponding to the item to be filled can be constructed, and the data extraction instruction contains the intention when extracting the data corresponding to the item to be filled and the data output standard when outputting the data. The specific steps are as follows:

[0065] First, according to the preset instruction mapping rules, a data extraction instruction template corresponding to the item to be filled in the special disease library is determined from the pre-built medical instruction library.

[0066] This embodiment pre-sets instruction mapping rules, which include the correspondence between the items to be filled in the special disease library and the data extraction instruction templates. According to the instruction mapping rules, the data extraction instruction templates corresponding to the items to be filled in the special disease library can be queried from all the data extraction instruction templates stored in the pre-built medical instruction library. Among them, since the items to be filled in the special disease libraries of different diseases are different, the correspondence contained in the instruction mapping rules corresponding to the special disease libraries of different diseases is also different. Therefore, when setting the instruction mapping rules, different instruction mapping rules need to be set for the special disease libraries of different diseases.

[0067] Second, according to the preset medical record fragment mapping rules, the source of medical record fragment extraction corresponding to the item to be filled in the special disease database is determined from the pre-collected medical data of special disease patients.

[0068] The present embodiment pre-sets a medical record fragment mapping rule, which includes the correspondence between the items to be filled in the special disease library and the source of medical record fragment extraction. According to the medical record fragment mapping rule, the source of medical record fragment extraction corresponding to the items to be filled in the special disease library can be determined from the pre-collected medical data of special disease patients. Among them, since the items to be filled in the special disease library of different diseases are different, the correspondence contained in the medical record fragment mapping rules corresponding to the special disease library of different diseases is also different. Therefore, when setting the medical record fragment mapping rules, different medical record fragment mapping rules need to be set for the special disease library of different diseases. For example, as shown in the following Table 1, part of the contents of the medical record fragment mapping rules corresponding to the special disease library of coronary heart disease are recorded:

[0069] Table 1

[0070]

[0071]

[0072] Thirdly, based on the medical record fragment extraction source corresponding to the items to be filled in the special disease database and the data extraction instruction template corresponding to the items to be filled in the special disease database, construct the data extraction instructions for the items to be filled in the special disease database.

[0073] After the present embodiment determines the medical record fragment extraction source and the data extraction instruction template corresponding to the item to be filled in the special disease library, the data extraction instruction corresponding to the item to be filled in the special disease library is constructed by combining the medical record fragment extraction source and the data extraction instruction template corresponding to the item to be filled in the special disease library. Among them, the combination of the medical record fragment extraction source and the data extraction instruction template corresponding to the item to be filled in the special disease library can be based on all the contents in the data extraction instruction template corresponding to the item to be filled in the special disease library and all the contents in the medical record fragment extraction source corresponding to the item to be filled in the special disease library. The data extraction instruction corresponding to the item to be filled in the special disease library is obtained by recombining all the contents in the data extraction instruction template corresponding to the item to be filled in the special disease library and all the contents in the medical record fragment extraction source corresponding to the item to be filled in the special disease library, so that the data extraction instruction corresponding to the item to be filled in the special disease library includes both the contents in the data extraction instruction template corresponding to the item to be filled in the special disease library and the contents in the medical record fragment extraction source corresponding to the item to be filled in the special disease library.

[0074] In addition, the combination of the medical record fragment extraction source corresponding to the item to be filled in the special disease library and the data extraction instruction template can also be: fill the medical record fragment extraction source corresponding to the item to be filled in the special disease library into the data extraction instruction template corresponding to the item to be filled in the special disease library, and obtain the data extraction instruction corresponding to the item to be filled in the special disease library. That is, the filling position of the medical record fragment extraction source is pre-set in the data extraction instruction template corresponding to the item to be filled in the special disease library, and the medical record fragment extraction source corresponding to the item to be filled in the special disease library is directly filled into the filling position set in the data extraction instruction template corresponding to the item to be filled in the special disease library, so as to obtain a complete data extraction instruction. The data extraction instruction corresponding to the item to be filled can play a guiding role in extracting the data corresponding to the item to be filled, extract the data that meets the data extraction intention in the data extraction instruction, and output the data corresponding to the item to be filled according to the data output standard in the data extraction instruction, so that the data output format of the data corresponding to the item to be filled finally obtained meets the data output standard in the data extraction instruction. For example, when the item to be filled is age, the data extraction instruction corresponding to the item to be filled is:

[0075] "Now you are a hospital data analyst and need to Admission Record-Age Extract the patient's age for statistics and analysis. The specific requirements are as follows:

[0076] 1. Focus on accurately extracting age information from the text, which usually follows the "age:" tag;

[0077] 2. Age should be extracted as a complete string with units (such as "42, years old") to ensure the consistency of units and facilitate subsequent processing;

[0078] 3. Handle possible exceptions, such as missing age fields or incorrect formats (for example, non-numeric characters), and the extracted numerical content should be between 0-150. "

[0079] In the example of the data extraction instruction corresponding to the above-mentioned item to be filled, the position of "admission record-age" is the filling position set in the data extraction instruction template. "Admission record-age" is the extraction source of the medical record fragment corresponding to the item to be filled. All other contents except "admission record-age" are data extraction instruction templates corresponding to the item to be filled.

[0080] S102. Extract data corresponding to the items to be filled in the special disease database from the medical data of patients with special diseases by executing data extraction instructions.

[0081] After the data extraction instructions corresponding to the items to be filled in the special disease library are determined through the above steps, the data extraction instructions are executed, and according to the data extraction intention contained in the data extraction instructions and the medical record fragment extraction source corresponding to the items to be filled in the special disease library, the data corresponding to the items to be filled in the special disease library are extracted from the position corresponding to the medical record fragment extraction source corresponding to the items to be filled in the special disease library in the medical data of the special disease patient, and the data is output according to the data output standard in the data extraction instruction, so that the data output format of the data corresponding to the items to be filled conforms to the data output standard in the data extraction instruction. The data extraction instructions corresponding to the items to be filled in the special disease library in this embodiment are constructed based on the data extraction instruction template corresponding to the items to be filled in the special disease library and the medical record fragment extraction source corresponding to the items to be filled in the special disease library. Since the data extraction instruction template corresponding to the items to be filled in the special disease library is designed by medical personnel with professional medical knowledge and is highly professional and scientific, the data quality of the data corresponding to the items to be filled in the special disease library extracted using the data extraction instructions corresponding to the items to be filled in the special disease library is higher, that is, the data accuracy is higher. For example, when the item to be filled in the special disease library is age, the output data corresponding to the item to be filled in the special disease library can be as follows:

[0082] {

[0083] "patient_age": "42",

[0084] “patient_age_unit”: “years old”

[0085] }

[0086] Specifically, in this embodiment, a data extraction model is pre-constructed, and the data extraction instructions corresponding to the items to be filled in the special disease library and the pre-collected medical data of special disease patients are input into the pre-constructed data extraction model, so that the data extraction model executes the data extraction instructions and extracts the data corresponding to the items to be filled in the special disease library from the medical data of special disease patients. Among them, the data extraction model is preferably a large language model (LLM). The deep learning ability of the large language model can accurately parse information from complex medical data, and the high-level language understanding ability of the large language model can process data of various formats and sources, and has high adaptability, so that the method for filling the special disease library of this embodiment can be effectively deployed in different medical environments, without the need to redesign or adjust the system for each specific situation, which greatly improves the application flexibility of the method for filling the special disease library.

[0087] S103, filling the data into the items to be filled in the special disease database.

[0088] After extracting the data corresponding to the items to be filled in the special disease database through the above steps, this embodiment needs to fill the data corresponding to the items to be filled in the special disease database into the filling positions corresponding to the corresponding items to be filled in the special disease database. That is, fill the data corresponding to the items to be filled in the special disease database into the items to be filled in the to-be-filled form of the special disease database.

[0089] In this embodiment, the data of patients with special diseases need to be filled into the special disease database separately, that is, one patient at a time is filled into the special disease database. Specifically, pre-collecting the medical data of patients with special diseases means pre-collecting the medical data of patients with special diseases for a patient with special diseases. At this time, by executing the data extraction instruction, the data corresponding to the items to be filled in the special disease database are extracted from the medical data of patients with special diseases for a patient with special diseases, and the data are filled into the items to be filled in the special disease database, thereby completing the filling of the special disease database for one patient, and then collecting the medical data of patients with special diseases for another patient with special diseases to complete the filling of the special disease database for another patient, until finally, in the special disease database, the data corresponding to the items to be filled in the special disease database of all patients with special diseases are filled into the items to be filled in the special disease database.

[0090] In this embodiment, a special disease library contains at least one special disease library item to be filled. When the special disease library contains multiple special disease library items to be filled, the data extraction instructions corresponding to the multiple special disease library items to be filled can be determined at the same time, so as to extract the data corresponding to the multiple special disease library items to be filled at the same time, and fill the data corresponding to the multiple special disease library items to be filled into the special disease library items to be filled at the same time.

[0091] From the above introduction, it can be seen that the method for filling the special disease database proposed in the embodiment of the present application determines the data extraction instructions corresponding to the items to be filled in the special disease database based on the pre-constructed medical instruction knowledge base and the pre-collected medical data of special disease patients; the medical instruction library includes data extraction instruction templates corresponding to the items to be filled; by executing the data extraction instructions, the data corresponding to the items to be filled in the special disease database are extracted from the medical data of the special disease patients; and the data is filled into the items to be filled in the special disease database. The technical solution of this embodiment can realize the automatic acquisition of data corresponding to the items to be filled in the special disease database, and the automatic filling of data corresponding to the items to be filled in the special disease database, thereby improving the efficiency and accuracy of filling in the special disease database.

[0092] As an optional implementation, see Figure 2 As shown, in another embodiment of the present application, step S102 is disclosed, in which data corresponding to the items to be filled in the special disease database are extracted from the medical data of the special disease patient by executing the data extraction instruction, which specifically includes the following steps:

[0093] S201. According to the preset medical record fragment mapping rules, the medical record fragments corresponding to the items to be filled in the special disease database are extracted from the medical data of the special disease patients.

[0094] Before extracting the data corresponding to the items to be filled in the special disease database, this embodiment can first extract the medical record fragments corresponding to the items to be filled in the special disease database from the pre-collected medical data of special disease patients according to the preset medical record fragment mapping rules. Specifically, first determine the medical record fragment extraction source corresponding to the item to be filled in the special disease database according to the preset medical record fragment mapping rules, and then, according to the medical record fragment extraction source corresponding to the item to be filled, extract the medical record fragment from the position corresponding to the medical record fragment extraction source in the pre-collected medical data of special disease patients as the medical record fragment corresponding to the item to be filled in the special disease database.

[0095] For example, when the item to be filled in the special disease database is age, the medical record fragment corresponding to the item to be filled in the special disease database is extracted from the admission record. Therefore, the medical record fragment corresponding to the item to be filled in the special disease database extracted from the medical data of the special disease patient is the medical record fragment of the admission record, where the medical record fragment of the admission record is as follows:

[0096] "Patient's name: Zhang San

[0097] Age: 42

[0098] Gender: Male

[0099] Date of admission: April 12, 2024

[0100] Chief complaint: Chest pain lasting 3 hours

[0101] Diagnosis: Angina pectoris

[0102] S202. Extract data corresponding to the items to be filled in the special disease database from the medical record fragments corresponding to the items to be filled in the special disease database by executing the data extraction instruction.

[0103] This embodiment directly extracts data corresponding to the items to be filled in the special disease database from the medical record fragments corresponding to the items to be filled in the special disease database extracted from the medical data of the special disease patient by executing the data extraction instruction. Compared with directly extracting data corresponding to the items to be filled in the special disease database from the medical data of the special disease patient by executing the data extraction instruction, the medical record fragments corresponding to the items to be filled in the special disease database are first extracted from the medical data of the special disease patient, and then the data corresponding to the items to be filled in the special disease database are extracted from the medical record fragments. The accuracy of the extracted data corresponding to the items to be filled in the special disease database is higher.

[0104] Specifically, when using the data extraction model to extract data corresponding to the items to be filled in the special disease database, the data extraction instructions corresponding to the items to be filled in the special disease database and the medical record fragments corresponding to the items to be filled in the special disease database extracted from the medical data of special disease patients are directly input into the data extraction model. The data extraction model extracts the data corresponding to the items to be filled in the special disease database from the medical record fragments corresponding to the items to be filled in the special disease database by executing the data extraction instructions. Compared with using the data extraction model to execute the data extraction instructions to extract the data corresponding to the items to be filled in the special disease database from the medical data of special disease patients, the data extraction model of this embodiment has higher processing efficiency, and the extracted data corresponding to the items to be filled in the special disease database are more accurate.

[0105] As an optional implementation, another embodiment of the present application discloses that among the items to be filled in the special disease library extracted from the to-be-filled form of the special disease library, some of the items to be filled in the special disease library may have dependencies. If a special disease library item to be filled does not have other special disease library items to be filled with dependencies, then the special disease library item to be filled corresponds to a corresponding data extraction instruction alone. If a special disease library item to be filled has dependencies with other special disease library items to be filled, then the special disease library item to be filled and the other special disease library items to be filled with dependencies with the special disease library item to be filled correspond to the same data extraction instruction. At this time, step S102, extracting data corresponding to the item to be filled in the special disease library from the medical data of the special disease patient by executing the data extraction instruction, includes:

[0106] By executing the data extraction instruction, data corresponding to the items to be filled in the special disease library and data corresponding to other special disease library items to be filled that have a dependency relationship with the items to be filled in the special disease library are extracted from the medical data of the special disease patients.

[0107] Specifically, the same data extraction instruction corresponding to the item to be filled in the special disease database and other items to be filled in the special disease database that have a dependency relationship with the item to be filled in the special disease database is used to extract the data corresponding to the item to be filled in the special disease database and the data corresponding to other items to be filled in the special disease database that have a dependency relationship with the item to be filled in the special disease database from the medical data of the special disease patient. For example, the item A to be filled in the special disease database has a dependency relationship with both the item B to be filled in the special disease database and the item C to be filled in the special disease database, that is, the other items to be filled in the special disease database that have a dependency relationship with the item A to be filled in the special disease database are the item B to be filled in the special disease database and the item C to be filled in the special disease database. At this time, the item A to be filled in the special disease database, the item B to be filled in the special disease database and the item C to be filled in the special disease database correspond to the same data extraction instruction, and by executing this data extraction instruction, the data corresponding to the item A to be filled in the special disease database, the data corresponding to the item B to be filled in the special disease database and the data corresponding to the item C to be filled in the special disease database can be extracted from the medical data of the special disease patient.

[0108] If an item to be filled in the special disease library has a dependency relationship with other items to be filled in the special disease library, then the pre-constructed medical instruction library contains the same data extraction instruction template corresponding to the item to be filled in the special disease library and other items to be filled in the special disease library that have a dependency relationship with the item to be filled in the special disease library. The method for determining the same data extraction instruction corresponding to the item to be filled in the special disease library and other items to be filled in the special disease library that have a dependency relationship with the item to be filled in the special disease library is: first, according to the preset instruction mapping rules, determine from the pre-constructed medical instruction library the same data extraction instruction template corresponding to the item to be filled in the special disease library and other items to be filled in the special disease library that have a dependency relationship with the item to be filled in the special disease library; then, according to the preset medical record fragment mapping rules, determine from the pre-collected medical data of special disease patients the medical record fragment extraction source corresponding to the item to be filled in the special disease library and the medical record fragment extraction source corresponding to other items to be filled in the special disease library that have a dependency relationship with the item to be filled in the special disease library; finally, based on the same data extraction instruction template corresponding to the item to be filled in the special disease library and other items to be filled in the special disease library that have a dependency relationship with the item to be filled in the special disease library, board, as well as the medical record fragment extraction source corresponding to the item to be filled in the special disease library and the medical record fragment extraction source corresponding to other special disease library items to be filled that have a dependency relationship with the item to be filled in the special disease library, to construct the same data extraction instruction corresponding to the item to be filled in the special disease library and the other special disease library items to be filled that have a dependency relationship with the item to be filled in the special disease library, that is, the medical record fragment extraction source corresponding to the item to be filled in the special disease library and the medical record fragment extraction source corresponding to other special disease library items to be filled that have a dependency relationship with the item to be filled in the special disease library are all filled into the same data extraction instruction template corresponding to the item to be filled in the special disease library and the other special disease library items to be filled that have a dependency relationship with the item to be filled in the special disease library, to obtain the same data extraction instruction corresponding to the item to be filled in the special disease library and the other special disease library items to be filled that have a dependency relationship with the item to be filled in the special disease library.

[0109] For example, in the actual medical process, it is necessary to first determine whether there are stenotic coronary arteries. If so, determine which specific coronary arteries are stenotic (left main trunk, right coronary artery, anterior descending branch, etc.), the degree of stenosis, whether thrombosis exists, whether balloon dilatation is used, whether stents are implanted, whether stent implantation is successful, etc. From this, it can be seen that the items to be filled in the special disease library, such as patient position, puncture entrance, name of stenotic blood vessel, degree of vascular stenosis, whether balloon dilatation is performed, whether stents are implanted, and whether stent implantation is successful, are items to be filled in the special disease library with dependencies. At this point, when the items to be filled in the special disease library are patient position, puncture entrance, name of stenotic blood vessel, degree of vascular stenosis, whether balloon dilatation is performed, whether stents are implanted, and whether stent implantation is successful, the constructed data extraction instructions are as follows:

[0110] “You are a medical records clerk working in a large hospital. Your main responsibility is to organize and record surgical procedures and ensure that all documents are accurate for subsequent reference by medical staff.

[0111] Specific task requirements:

[0112] 1. Pay attention to input Surgical record-operative process If there is other content entered together with the information in the text, you do not need to pay attention to it.

[0113] 2. Output the contents of the fields of interest (patient position, puncture entrance, name of stenotic vessel, degree of stenosis, whether balloon dilatation was performed, whether stent was implanted, and whether stent implantation was successful) in JSON format;

[0114] 3. There is a fixed dependency relationship between the contents of these fields: the "degree of vascular stenosis" can be described only when the "name of stenotic blood vessel" exists, and the "whether the stent is successfully implanted" can be described only when the "whether the stent is implanted" is "yes". If there is no precondition, the content of the field also needs to be recorded, such as "there is no stenotic blood vessel, so the degree of stenosis cannot be described", so that the output JSON is completely fixed, which is convenient for subsequent parsing and processing;

[0115] 4. If Surgical record-operative process If the content of the concerned field is not described, directly record "not described";

[0116] 5. Directly output the content in json format, and do not make any other descriptions. ”

[0117] The above-mentioned "Operation Record - Operation Process" is the source of medical record fragment extraction corresponding to the patient's body position, puncture entrance, name of stenotic blood vessel, degree of vascular stenosis, whether balloon dilatation is performed, whether stent is implanted, and whether the stent implantation is successful. The other contents in the above-mentioned data extraction instructions except "Operation Record - Operation Process" are data extraction instruction templates corresponding to the patient's body position, puncture entrance, name of stenotic blood vessel, degree of vascular stenosis, whether balloon dilatation is performed, whether stent is implanted, and whether the stent implantation is successful.

[0118] Correspondingly, by executing the above data extraction instruction, the data corresponding to the items to be filled in the special disease database extracted from the medical data of special disease patients are as follows:

[0119] {

[0120] "Patient position": "Supine position",

[0121] "Puncture Port": "Right Radial Artery",

[0122] "Disease vessels": [{

[0123] "Name of stenotic vessel": "LAD",

[0124] "Stenosis": "75%"

[0125] }]

[0126] "Whether to perform balloon dilatation": "Yes",

[0127] "Is the stent inserted": "Yes",

[0128] "Is stent placement successful?": "Yes"

[0129] }

[0130] Correspondingly, when the data corresponding to the items to be filled in the special disease database are extracted from the medical data of the special disease patient by executing the above data extraction instruction, it is necessary to extract the medical record fragments corresponding to the items to be filled in the special disease database from the medical data of the special disease patient according to the preset medical record fragment mapping rules. The extracted medical record fragments corresponding to the items to be filled in the special disease database, that is, the medical record fragments corresponding to the medical record fragments extracted from the "operation record-operation process" are as follows:

[0131] "After local anesthesia, the patient took a supine position and remained stable. The right radial artery was punctured and a catheter was inserted into the opening of the coronary artery. Contrast agent was injected, and the 75% stenosis of the left anterior descending branch (LAD) was confirmed through dynamic X-ray observation. The balloon catheter was introduced to the stenotic site for dilation. The initial dilation result was not ideal, the stenotic site was not completely opened, and the degree of stenosis dropped to 60%. In view of the poor effect of balloon dilation, it was decided to insert a metal stent. The stent of appropriate size was selected, introduced and accurately placed in the stenotic site, and the stent was deployed to ensure good fit to the blood vessel wall. After the stent was inserted, contrast agent was injected again to confirm that the stent was in the correct position, the left anterior descending branch was well opened, the stenosis was relieved, and the blood flow returned to normal. All catheter materials were withdrawn, the puncture site was compressed to stop bleeding, and bandaged and fixed. The patient's vital signs were stable during the operation, and no obvious complications occurred. He was sent back to the ward for further observation and treatment."

[0132] This embodiment can use one data extraction instruction to extract the data corresponding to all items to be filled with dependencies at one time, avoiding multiple calls to the data extraction instruction, which can significantly improve work efficiency, reduce error rate, and ensure the consistency and accuracy of data processing.

[0133] As an optional implementation, see Figure 3 As shown, in another embodiment of the present application, before executing step S103 and filling the data into the to-be-filled items in the disease-specific database, the following steps are also included:

[0134] S301. According to the pre-set quality inspection rules, the data corresponding to the items to be filled in the special disease database are quality inspected to determine the quality inspection information corresponding to the data.

[0135] In this embodiment, quality inspection rules for data corresponding to items to be filled in the special disease database are pre-set, and different quality inspection rules correspond to different items to be filled in the special disease database. For example, when the item to be filled in the special disease database is age, the quality inspection rules for data corresponding to the item to be filled in the special disease database include that the data must include numeric characters, etc.

[0136] This embodiment performs quality inspection on the data corresponding to the items to be filled in the special disease database extracted according to the pre-set quality inspection rules, judges whether the data corresponding to the items to be filled in the special disease database conforms to the quality inspection rules corresponding to the items to be filled in the special disease database, and determines the quality inspection information corresponding to the data according to the judgment result. If the data corresponding to the items to be filled in the special disease database conforms to the quality inspection rules corresponding to the items to be filled in the special disease database, the quality inspection information is determined to indicate that the quality inspection is qualified; if the data corresponding to the items to be filled in the special disease database does not conform to the quality inspection rules corresponding to the items to be filled in the special disease database, the quality inspection information is determined to indicate that the quality inspection is unqualified.

[0137] S302. If the quality inspection information indicates that the quality inspection is qualified, the data is filled into the items to be filled in the special disease database.

[0138] If it is determined that the quality inspection information corresponding to the data indicates that the quality inspection is qualified, the data is filled into the item to be filled in the special disease database, thereby improving the accuracy of the filling of the special disease database. The specific implementation method of filling the data into the item to be filled in the special disease database has been specifically described in step S103 of the above embodiment, and will not be repeated in this embodiment.

[0139] S303: If the quality inspection information indicates that the quality inspection is unqualified, output a prompt message indicating that the data output is wrong.

[0140] If it is determined that the quality inspection information corresponding to the data indicates that the quality inspection is unqualified, a prompt message indicating that the data output is wrong is output to prompt the user that the data corresponding to the item to be filled in the special disease library extracted is wrong, and the data corresponding to the item to be filled in the special disease library is extracted again. If the extraction of the data corresponding to the item to be filled in the special disease library is achieved by using a data extraction model, the prompt message indicating that the data output is wrong is output, which can prompt the user that the data extraction accuracy of the data extraction model for the item to be filled in the special disease library is low, and the data extraction model can be evaluated. The user can optimize the data extraction model for the item to be filled in the special disease library. Training.

[0141] As an optional implementation, see Figure 4As shown, in another embodiment of the present application, if the quality inspection information of the data corresponding to the item to be filled in the special disease library indicates that the quality inspection is unqualified, or the data corresponding to the item to be filled in the special disease library is manually reviewed, and the review result indicates that the data is unqualified, then it is necessary to optimize the data extraction model for the item to be filled in the special disease library. The specific training steps include:

[0142] S401, collecting training samples corresponding to the items to be filled in the disease database and real data corresponding to the training samples.

[0143] When optimizing and training the data extraction model for the items to be filled in the special disease library in this embodiment, it is first necessary to collect the training samples corresponding to the items to be filled in the special disease library, as well as the real data corresponding to each training sample. The training samples corresponding to the items to be filled in the special disease library include: the data extraction instructions corresponding to the items to be filled in the special disease library and the sample medical data corresponding to the items to be filled in the special disease library. Among them, the data extraction instructions corresponding to the items to be filled in the special disease library are determined based on the pre-constructed medical instruction library and the pre-collected medical data of special disease patients. The specific steps have been specifically described in step S101 of the above embodiment, and this embodiment will not repeat them. The sample medical data corresponding to the items to be filled in the special disease library can be the pre-collected medical data of special disease patients, or it can be the medical record fragments corresponding to the items to be filled in the special disease library extracted from the pre-collected medical data of special disease patients according to the preset medical record fragment mapping rules. The specific extraction steps have been specifically described in the above embodiment, and this embodiment will not repeat them. The real data corresponding to the training samples are the real data corresponding to the items to be filled in the special disease library in the pre-collected medical data of special disease patients.

[0144] S402: Input the training sample into the data extraction model to obtain the prediction data corresponding to the training sample.

[0145] In this embodiment, the collected training samples are input into the data extraction model, and the data extraction model extracts the data corresponding to the items to be filled in the special disease library from the sample medical data corresponding to the items to be filled in the special disease library in the training samples as the prediction data corresponding to the training samples by executing the data extraction instructions corresponding to the items to be filled in the special disease library in the training samples. The specific execution method of the data extraction model extracting the data corresponding to the items to be filled in the special disease library from the sample medical data corresponding to the items to be filled in the special disease library in the training samples by executing the data extraction instructions corresponding to the items to be filled in the special disease library in the training samples is the same as the execution method of step S102 in the above embodiment, and will not be repeated in this embodiment.

[0146] S403: Adjust parameters of the data extraction model based on the difference between the real data corresponding to the training samples and the predicted data corresponding to the training samples.

[0147] This embodiment is based on the difference between the real data corresponding to the training samples and the predicted data corresponding to the training samples, with the goal of minimizing the difference between the real data corresponding to the training samples and the predicted data corresponding to the training samples, and adjusts the parameters of the data extraction model. That is, the loss function between the real data corresponding to the training samples and the predicted data corresponding to the training samples can be calculated, and the parameters of the data extraction model can be adjusted with the goal of minimizing the loss function until the loss function between the real data corresponding to the training samples and the predicted data corresponding to the training samples reaches a preset standard range, and then the optimization training of the data extraction model for the items to be filled in the special disease library is stopped.

[0148] As an optional implementation, another embodiment of the present application discloses that before step S101, based on the pre-built medical instruction library and the pre-collected medical data of patients with special diseases, determining the data extraction instruction corresponding to the item to be filled in the special disease library, the following steps are also included:

[0149] The to-be-filled forms of the special disease database are identified, and at least one to-be-filled item of the special disease database is extracted from the to-be-filled forms.

[0150] In this embodiment, the special disease databases corresponding to different diseases all correspond to special disease forms that need to be filled in, and the special disease forms are used as the to-be-filled forms of the special disease database. By identifying the to-be-filled forms of the special disease database, the fields of the to-be-filled items in the to-be-filled forms of the special disease database can be identified, so as to extract at least one to-be-filled item of the special disease database from the to-be-filled forms. Among them, the identification of the to-be-filled forms of the special disease database can adopt existing text recognition methods, such as OCR recognition technology, etc.

[0151] Exemplary Devices

[0152] Correspondingly, the present application embodiment also provides a disease database filling device, see Figure 5 As shown, the device comprises:

[0153] The instruction determination module 100 is used to determine the data extraction instruction corresponding to the item to be filled in the special disease library based on the pre-built medical instruction library and the pre-collected medical data of the special disease patient; the medical instruction library includes the data extraction instruction template corresponding to the item to be filled;

[0154] The data determination module 110 is used to extract data corresponding to the items to be filled in the special disease database from the medical data of the special disease patients by executing the data extraction instruction;

[0155] The data filling module 120 is used to fill the data into the items to be filled in the special disease database.

[0156] From the above introduction, it can be seen that the special disease database filling device proposed in the embodiment of the present application can realize the automatic acquisition of data corresponding to the items to be filled in the special disease database, and the automatic filling of data corresponding to the items to be filled in the special disease database, thereby improving the efficiency and accuracy of special disease database filling.

[0157] As an optional implementation, in another embodiment of the present application, it is disclosed that the instruction determination module 100 includes: a first determination unit, a second determination unit and a construction unit;

[0158] The first determining unit is used to determine the data extraction instruction template corresponding to the item to be filled in the special disease library from the pre-built medical instruction library according to the preset instruction mapping rule; the instruction mapping rule includes the corresponding relationship between the item to be filled and the data extraction instruction template;

[0159] The second determination unit is used to determine the medical record fragment extraction source corresponding to the item to be filled in the special disease database from the pre-collected medical data of the special disease patient according to the preset medical record fragment mapping rule; the medical record fragment mapping rule includes the corresponding relationship between the item to be filled and the medical record fragment extraction source;

[0160] A construction unit is used to construct data extraction instructions corresponding to the items to be filled in the special disease database based on the medical record fragment extraction source corresponding to the items to be filled in the special disease database and the data extraction instruction template corresponding to the items to be filled in the special disease database.

[0161] As an optional implementation, another embodiment of the present application discloses a construction unit, specifically used for:

[0162] Fill the medical record fragment extraction source corresponding to the item to be filled in the special disease database into the data extraction instruction template corresponding to the item to be filled in the special disease database, and obtain the data extraction instruction corresponding to the item to be filled in the special disease database.

[0163] As an optional implementation, another embodiment of the present application discloses that the data determination module 110 is specifically used to:

[0164] According to the preset medical record fragment mapping rules, extract the medical record fragments corresponding to the items to be filled in the special disease database from the medical data of special disease patients;

[0165] By executing the data extraction instruction, the data corresponding to the items to be filled in the special disease database are extracted from the medical record fragments corresponding to the items to be filled in the special disease database.

[0166] As an optional implementation, another embodiment of the present application discloses that if the item to be filled in the special disease library has a dependency relationship with other items to be filled in the special disease library, then the item to be filled in the special disease library and other items to be filled in the special disease library that have a dependency relationship with the item to be filled in the special disease library correspond to the same data extraction instruction;

[0167] The data determination module 110 is also specifically used to extract data corresponding to the items to be filled in the special disease library and data corresponding to other special disease library items to be filled that have a dependency relationship with the items to be filled in the special disease library from the medical data of special disease patients by executing data extraction instructions.

[0168] As an optional implementation, another embodiment of the present application discloses that the data determination module 110 is further configured to:

[0169] Input the data extraction instructions of the items to be filled in the special disease database and the medical data of the special disease patients into the pre-built data extraction model to obtain the reporting data of the items to be filled;

[0170] The data extraction model is used to extract data corresponding to the items to be filled in the special disease database from the medical data of patients with special diseases by executing data extraction instructions; among them, the data extraction model is a large language model.

[0171] As an optional implementation, another embodiment of the present application discloses that the device for filling in the special disease database further includes: a quality inspection module and an output module;

[0172] The quality inspection module is used to perform quality inspection on the data corresponding to the items to be filled in the disease database according to the pre-set quality inspection rules, and determine the quality inspection information corresponding to the data;

[0173] The data filling module is also used to fill the data into the to-be-filled items in the special disease database if the quality inspection information indicates that the quality inspection is qualified;

[0174] The output module is used to output a prompt message indicating data output error if the quality inspection information indicates that the quality inspection is unqualified.

[0175] As an optional implementation, another embodiment of the present application discloses that the device for filling in a specialized disease database further includes: a training sample collection module, an input module, and a parameter adjustment module.

[0176] The training sample collection module is used to collect the training samples corresponding to the items to be filled in the special disease database and the real data corresponding to the training samples if the quality inspection information indicates that the items are unqualified; wherein the training samples corresponding to the items to be filled in the special disease database include: data extraction instructions corresponding to the items to be filled in the special disease database and sample medical data corresponding to the items to be filled in the special disease database;

[0177] An input module is used to input the training samples into the data extraction model to obtain the prediction data corresponding to the training samples;

[0178] The parameter adjustment module is used to adjust the parameters of the data extraction model based on the difference between the real data corresponding to the training samples and the predicted data corresponding to the training samples.

[0179] As an optional implementation, disclosed in another embodiment of the present application, the device for filling in the special disease database also includes: an identification module.

[0180] The recognition module is used to recognize the to-be-filled form of the special disease database and extract at least one to-be-filled item of the special disease database from the to-be-filled form.

[0181] The device for filling in the special disease database provided in this embodiment belongs to the same application concept as the method for filling in the special disease database provided in the above embodiments of this application, and can execute the method for filling in the special disease database provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects for executing the method for filling in the special disease database. For the technical details not fully described in this embodiment, please refer to the specific processing content of the method for filling in the special disease database provided in the above embodiments of this application, which will not be repeated here.

[0182] Exemplary Electronic Devices

[0183] Another embodiment of the present application also provides an electronic device, see Figure 6 As shown, the device includes:

[0184] Memory 200 and processor 210;

[0185] The memory 200 is connected to the processor 210 and is used to store programs;

[0186] The processor 210 is used to implement the method for filling in the special disease database disclosed in any of the above embodiments by running the program stored in the memory 200.

[0187] Specifically, the electronic device may further include: a bus, a communication interface 220 , an input device 230 and an output device 240 .

[0188] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus.

[0189] A bus may include a pathway that transfers information between components of a computer system.

[0190] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0191] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0192] The memory 200 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0193] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0194] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0195] The communication interface 220 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0196] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement each step of any one of the special disease database reporting methods provided in the above embodiments of the present application.

[0197] Exemplary computer program products and storage media

[0198] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method for filling the special disease database according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0199] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0200] In addition, an embodiment of the present application may also be a storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the method for filling the special disease database according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0201] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0202] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. 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.

[0203] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0204] The modules and sub-modules in the devices and terminals of the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0205] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0206] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0207] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0208] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0209] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0210] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0211] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for filling in a special disease database. It is characterized in that include: Based on a pre-built medical instruction library and pre-collected medical data of patients with specific diseases, determining data extraction instructions corresponding to the items to be filled in the specific disease library; the medical instruction library includes data extraction instruction templates corresponding to the items to be filled; By executing the data extraction instruction, the data corresponding to the item to be filled in the special disease database is extracted from the medical data of the special disease patient; Fill the data into the items to be filled in the special disease database.

2. The method according to claim 1, It is characterized in that Based on the pre-built medical instruction library and the pre-collected medical data of patients with specific diseases, determine the data extraction instructions corresponding to the items to be filled in the specific disease library, including: According to the preset instruction mapping rules, a data extraction instruction template corresponding to the item to be filled in the special disease library is determined from the pre-built medical instruction library; the instruction mapping rules include the corresponding relationship between the item to be filled and the data extraction instruction template; According to the preset medical record fragment mapping rule, the medical record fragment extraction source corresponding to the item to be filled in the special disease database is determined from the pre-collected medical data of the special disease patient; the medical record fragment mapping rule includes the corresponding relationship between the item to be filled and the medical record fragment extraction source; Based on the medical record fragment extraction source corresponding to the item to be filled in the special disease library and the data extraction instruction template corresponding to the item to be filled in the special disease library, the data extraction instruction corresponding to the item to be filled in the special disease library is constructed.

3. The method according to claim 2, It is characterized in that Based on the medical record fragment extraction source corresponding to the item to be filled in the special disease database and the data extraction instruction template corresponding to the item to be filled in the special disease database, construct the data extraction instruction corresponding to the item to be filled in the special disease database, including: Fill the medical record fragment extraction source corresponding to the item to be filled in the special disease database into the data extraction instruction template corresponding to the item to be filled in the special disease database, and obtain the data extraction instruction corresponding to the item to be filled in the special disease database.

4. The method according to claim 1, It is characterized in that By executing the data extraction instruction, data corresponding to the item to be filled in the special disease database is extracted from the medical data of the special disease patient, including: According to the preset medical record fragment mapping rule, extract the medical record fragment corresponding to the item to be filled in the special disease database from the medical data of the special disease patient; By executing the data extraction instruction, the data corresponding to the item to be filled in the special disease database is extracted from the medical record fragment corresponding to the item to be filled in the special disease database.

5. The method according to claim 1, It is characterized in that If the item to be filled in the special disease database has a dependency relationship with other items to be filled in the special disease database, then the item to be filled in the special disease database and other items to be filled in the special disease database that have a dependency relationship with the item to be filled in the special disease database correspond to the same data extraction instruction; By executing the data extraction instruction, data corresponding to the item to be filled in the special disease database is extracted from the medical data of the special disease patient, including: By executing the data extraction instruction, data corresponding to the item to be filled in the special disease library and data corresponding to other special disease library items to be filled that have a dependency relationship with the item to be filled in the special disease library are extracted from the medical data of the special disease patient.

6. The method according to claim 1, It is characterized in that By executing the data extraction instruction, data corresponding to the item to be filled in the special disease database is extracted from the medical data of the special disease patient, including: Inputting the data extraction instructions of the items to be filled in the special disease database and the medical data of the special disease patients into the pre-built data extraction model to obtain the reporting data of the items to be filled in; The data extraction model is used to extract data corresponding to the items to be filled in the special disease database from the medical data of the special disease patients by executing the data extraction instruction; wherein, the data extraction model is a large language model.

7. The method according to claim 6, It is characterized in that Before filling the data into the items to be filled in the disease-specific database, the method further includes: According to the preset quality inspection rules, the data corresponding to the items to be filled in the special disease database are quality inspected to determine the quality inspection information corresponding to the data; If the quality inspection information indicates that the quality inspection is qualified, the data is filled into the item to be filled in the special disease database; If the quality inspection information indicates that the quality inspection is unqualified, a prompt message indicating that the data output is wrong is output.

8. The method according to claim 7, It is characterized in that Also includes: If the quality inspection information indicates that the data is unqualified, the training samples corresponding to the items to be filled in the special disease database and the real data corresponding to the training samples are collected; wherein the training samples corresponding to the items to be filled in the special disease database include: data extraction instructions corresponding to the items to be filled in the special disease database and sample medical data corresponding to the items to be filled in the special disease database; Inputting the training sample into the data extraction model to obtain prediction data corresponding to the training sample; Based on the difference between the real data corresponding to the training samples and the predicted data corresponding to the training samples, parameters of the data extraction model are adjusted.

9. The method according to claim 1, It is characterized in that Based on the pre-built medical instruction library and the pre-collected medical data of patients with specific diseases, before determining the data extraction instructions corresponding to the items to be filled in the specific disease library, it also includes: The to-be-filled form of the special disease database is identified, and at least one to-be-filled item of the special disease database is extracted from the to-be-filled form.

10. A device for filling in a special disease database, It is characterized in that include: An instruction determination module is used to determine the data extraction instruction corresponding to the item to be filled in the special disease library based on the pre-built medical instruction library and the pre-collected medical data of the special disease patient; the medical instruction library includes the data extraction instruction template corresponding to the item to be filled; A data determination module, used to extract data corresponding to the items to be filled in the special disease database from the medical data of the special disease patient by executing the data extraction instruction; The data filling module is used to fill the data into the items to be filled in the special disease database.

11. An electronic device, It is characterized in that include: Memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the method for filling the special disease database as described in any one of claims 1 to 9 by running the program in the memory.

12. A storage medium, It is characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the method for filling in the special disease database as described in any one of claims 1 to 9 is implemented.

13. A computer program product, It is characterized in that It includes computer program instructions, which, when executed by a processor, enable the processor to implement the method for filling in a special disease database as described in any one of claims 1 to 9.

Citation Information

Patent Citations

  • Data retrieval method and device based on intention understanding, equipment and storage medium

    CN110019713A

  • Quality inspection method for electronic medical records and reminding method and device for similar medical records

    CN110413981A

  • Task instruction generation method and device, equipment and storage medium

    CN113504728A

  • Clinical scientific research big data analysis system

    CN115497631A

  • Voice control method and device, electronic equipment and readable storage medium

    CN116705018A