CN116344011B - Medical record file establishment management method and system - Google Patents
Medical record file establishment management method and system Download PDFInfo
- Publication number
- CN116344011B CN116344011B CN202310609703.3A CN202310609703A CN116344011B CN 116344011 B CN116344011 B CN 116344011B CN 202310609703 A CN202310609703 A CN 202310609703A CN 116344011 B CN116344011 B CN 116344011B
- Authority
- CN
- China
- Prior art keywords
- disease
- data
- information
- medical record
- different
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application provides a medical record filing management method and system, and relates to the technical field of filing management. The method comprises the steps of obtaining medical record data, and classifying diseases into a first classification category according to the medical record data to form a disease information database aiming at different diseases; obtaining diagnosis and treatment data of disease information databases of different diseases, and classifying by taking window indexes as second classification categories to form disease stage data aiming at different diseases; acquiring disease stage data of different diseases, and classifying by taking related indexes as a third classification class to form disease difference data aiming at different disease stages; acquiring treatment data of disease information databases of different diseases, and matching the treatment data with disease difference data to form disease treatment associated information; and correlating the disease treatment correlation information with the patient data to form a disease-based patient medical record archive. The medical record profiling management is designed efficiently and reasonably to realize functional assistance for outpatient service.
Description
Technical Field
The application relates to the technical field of filing management, in particular to a medical record filing management method.
Background
The current medical record management system is not perfect enough, and the management of medical records is mostly only simple to store all diagnosis and treatment data of patients according to the information of the patients. Most of the time, medical record management is used for only calling medical record data of a target patient if needed and performing simple understanding and disease tracing. The functions and the contents are very simple. Moreover, there is limited effect on the portion of the medical record that is in natural language, which can be structured if the physician enters it in a structured manner. If the physician enters natural language text, the portion cannot be structured.
Along with the increasing demands and the continuous development of medical systems, the demands for medical record profiling management are more and more complex, and particularly in the aspect of improving the more convenient outpatient service work of hospitals based on the historical diagnosis and treatment data, the urgent demands of medical record profiling management meet the functions of the aspect, and the medical record profiling management is exerted. Obviously, the current medical record filing management is mainly based on individual patient filing management, and in order to provide reliable data reference for outpatient service, a medical record data filing mode which is more fit for the outpatient service needs to be considered.
Therefore, designing a medical record filing management method and system, which can realize the functional assistance to the outpatient service by efficiently and reasonably designing the medical record filing management, is a problem to be solved at present.
Disclosure of Invention
The application aims to provide a medical record filing management method, which is characterized in that medical record data are classified and divided in a grading manner with diseases as targets to form reasonable disease classification case filing management data, so that reliable and accurate auxiliary reference is provided for diagnosis and treatment judgment based on historical medical record data for outpatient service. The high-level application of the medical record data is fully realized, and the history information of the patient is also associated, so that the medical record data can be conveniently known and traced based on the individual patient.
The application also aims to provide a medical record filing management system, which can completely collect the case data of the patient through an outpatient service terminal and provide a reliable data base for case filing management. The processing center centrally completes the filing management of medical records to form reasonable and ordered case files, and provides a material basis for understanding and tracing the illness state of patients and assisting the outpatient service by using history medical record data.
In a first aspect, the present application provides a medical record profiling management method, including obtaining medical record data, classifying a disease into a first classification category according to the medical record data, and forming a disease information database for different diseases; obtaining diagnosis and treatment data of disease information databases of different diseases, and classifying by taking window indexes as second classification categories to form disease stage data aiming at different diseases; acquiring disease stage data of different diseases, and classifying by taking related indexes as a third classification class to form disease difference data aiming at different disease stages; acquiring treatment data of disease information databases of different diseases, and matching the treatment data with disease difference data to form disease treatment associated information; and correlating the disease treatment correlation information with the patient data to form a disease-based patient medical record archive.
According to the method, medical record data are classified and divided in a grading manner with diseases as targets, so that reasonable disease classification case filing management data are formed, and reliable and accurate auxiliary reference is provided for diagnosis and treatment judgment based on historical medical record data in outpatient service. The high-level application of the medical record data is fully realized, and the history information of the patient is also associated, so that the medical record data can be conveniently known and traced based on the individual patient.
As one possible implementation manner, obtaining medical record data, classifying diseases into a first classification category according to the medical record data, and forming a disease information database for different diseases, including: obtaining diagnosis information, dividing the diagnosis information based on rules of feature words to determine feature diseases, and sorting medical record data of different feature diseases to form a feature disease information database; obtaining medical record data excluding characteristic diseases, determining the main diseases based on division of the inclusion relation according to main patient information, and sorting medical record data of different main diseases to form a main disease information database.
In the application, the disease classification and classification is determined by analyzing and judging according to the diagnosis information in the simplest mode, so that the disease type can be accurately positioned, and a large number of medical records are accurately classified according to the disease type. In practical situations, however, the diagnostic information may not always be able to fully give accurate decisions, such as certain rare diseases, diseases with similar symptoms, etc. According to the application, the disease which is not given by the diagnosis information is classified by analyzing the main information, so that on one hand, the symptom of a patient can be accurately known, accurate disease judgment is given, a data basis is provided for subsequent disease-based analysis, and on the other hand, the main content and the therapeutic data form a corresponding relation, so that the rationality and the accuracy of the logical connection of case data are ensured.
As a possible implementation manner, obtaining diagnosis information, performing rule division based on feature words according to the diagnosis information to determine feature diseases, and sorting medical record data of different feature diseases to form a feature disease information database, including: extracting disease nouns and pathological adjectives from the diagnosis information; classifying and dividing for the first time based on the disease nouns to form different main diseases; obtaining pathological adjectives under different main diseases, and carrying out secondary classification and division based on the pathological adjectives to form characteristic diseases; medical record data of different characteristic diseases are arranged according to the checking and judging data and the treatment data, and the checking and judging data and the treatment data are logically related in diagnosis and treatment to form a characteristic disease information database.
In the application, aiming at classifying diseases based on diagnosis information, mainly determining information for judging the diseases in the diagnosis information, generally, the diagnosis information is relatively simple, and different diseases can be accurately classified by extracting words with parts of speech such as adjectives containing degrees, nouns containing names of the diseases and the like based on the diagnosis conditions of the diseases and then combining and sorting the extracted words. The classification based on nouns can accurately locate the categories of diseases, and the classification based on adjectives can further refine the specific disease conditions of the main diseases, so that the disease data can be further processed in detail, and a reliable reference basis is provided for subsequent data use.
As a possible implementation manner, obtaining medical record data excluding characteristic diseases, determining the main diseases based on division of inclusion relations according to main patient information, and sorting medical record data of different main diseases to form a main disease information database, including: establishing a non-information element word stock based on the main description; acquiring main information, screening out non-information element words from the main information according to a non-information element word library, and forming main element information; performing word frequency statistics on different main element information, and determining the main diseases based on word frequency; and sorting medical record data of different main diseases according to the checking and judging data and the treatment data, and logically associating the checking and judging data with the treatment data in diagnosis and treatment to form a main disease information database.
In the present application, it is considered that the main information is generally about 20 words, and information such as symptoms, time, pain and the like is often included therein, so that relatively unnecessary information is removed when extracting the information. Because the main information is doctor description based on patient, there is often individuality description habit difference, so the main information can be screened by establishing a non-information element word stock based on big data. Then, the information element words are divided based on word frequency analysis, so that medical records can be reasonably classified according to disease types.
As a possible implementation manner, performing word frequency statistics on different principal element information, and determining principal diseases based on word frequencies, including: acquiring information element class words of different main element information to form a main element information set A= [ A ] 1 ，A 2 ，…，A n ]Wherein A is n =[a n1 ，a n2 ，…，a nk ]N represents the total number of different main element information in the main element information set, and k represents the total number of information element words in the main element information with the reference number n; extracting information element words in all main element information in the main element information set A to form an information element statistical set B, A n ⊆ B, performing word frequency statistics to form information element frequency statistics results, and determining the main diseases according to the statistics results by the following steps: the information element words are combined in the same kind and then are sequenced according to the sequence from the big to the small of the frequency of the statistical result, and an information element statistical class collection C= [ C ] is formed 1 ，c 2 ，…，c m ]Wherein m is the total number of information element words which are formed after all the information element words in the information element statistical set B are subjected to similar combination and have no repetition, and C ⊆ B; obtaining information element class words with the largest frequency from the information element statistical class set C to form a frequency information element set D: when only one element c in D 1 At c 1 For screening the object, c is selected from A 1 Form a frequency screening set E= [ A ] x ，A x+1 ，…，A x+y ]X, y are all non-zero self-membersHowever, x is less than n, and x+y is less than or equal to n; for the main element information in the frequency screening set E, there will be a division of c 1 The main element information of the similar information element words with the exception of not less than 2 is divided into the same main disease, and the other words except c are present 1 Determining the main element information of the similar information element words with the number less than 2 as the independent main disease until all the main element information is divided; when there are multiple elements in D, c is first in order of frequency from higher to lower 1 For screening the object, c is selected from A 1 Form a frequency screening set E= [ A ] x ，A x+1 ，…，A x+y ]X and y are all non-zero natural numbers, and x is less than n, and x+y is less than or equal to n; for the main element information in the frequency screening set E, there will be a division of c 1 The main element information of the similar information element words with the exception of not less than 2 is divided into the same main disease, and the other words except c are present 1 Determining the main element information of the similar information element words with the number less than 2 as the independent main disease until all the main element information is divided; after all the main element information in E is removed in A, the element sequence in D is used as the screening object to be processed and c 1 The same screening mode is adopted until all elements in the D are used up; and eliminating the divided main element information, forming a new information element statistical set to perform word frequency statistics, and repeating the determining step of the main diseases until all main element information in the main element information set A is determined.
In the application, a way of reasonable disease type division based on the main element information is provided. After word frequency statistics is carried out, the information element words with highest frequency are selected as screening objects, so that the subsequent screening quantity can be reduced rapidly, and the workload of division is reduced greatly. Meanwhile, due to the characteristics of the main information, the diseases of the same type basically keep consistent information in three aspects of time, symptoms and pain, so that when the type is divided and judged, the basis of whether three information element words are the same or not is more reasonable and efficient. The screening and dividing mode is repeated, so that disease division based on the main information can be completed quickly.
As a possible implementation manner, obtaining diagnosis and treatment data of a disease information database of different diseases, classifying by using window indexes as a second classification category, and forming disease stage data for different diseases, including: obtaining diagnosis and treatment data of a disease information database of a single disease, comparing the examination indexes based on health index values, and determining the changed associated examination indexes to form single disease associated examination index data; repeatedly analyzing the associated check indexes in the single disease associated check index data to determine window indexes, so as to form single disease window index data; and carrying out range statistics on window indexes in the single disease window index data according to different medical record sources, determining different stage range values, and carrying out stage division on the single disease based on the stage range values to form disease stage data.
In the application, after the disease type division is completed, the data of different disease stages of different types of diseases are determined, which provides an important data basis for the analysis of the disease development condition and the finer disease diagnosis by using the medical record archive later. For each disease, there are different stages of disease progression, and the different stages must have window indicators for judgment. The window index can be accurately and rapidly judged by adopting a comparison and repeatability analysis mode.
As one possible implementation manner, performing repeatability analysis on the associated check index in the single disease associated check index data, determining a window index, and forming single disease window index data, including: setting a repeatability threshold value, carrying out repeatability statistics on the associated check indexes, and forming repeatability statistics result data; and sorting according to the repeated statistics result data and according to the repeated frequency, and determining window indexes by combining the repeated threshold value to form single disease window index data.
In the application, the index repeatability is considered to be more or less, and it can be understood that the more the index with more repeatability is more obvious for representing the disease, the threshold value is set to select, on one hand, to optimize the window index, and on the other hand, to improve the effectiveness and rationality of diagnosis, and to optimize the flow of diagnosis and reasonable classification of data. Of course, the setting of the threshold may be determined as needed or as a result of statistical analysis of the data.
As a possible implementation manner, performing range statistics of index values on window indexes in single disease window index data according to different medical record sources, determining different stage range values, and performing stage division on single disease based on the stage range values to form disease stage data, including: combining different window indexes by taking different medical record sources as the basis of group division to form different medical record window index groups F v =[f v1 ，f v2 ，…，f vt ]Wherein v is the total number of the medical record window index groups, and t is the total number of window indexes; extracting the same medical record window index in different medical record window index groups, and performing range union analysis on index values of the medical record window index: establishing the number of overlapping index value ranges, and providing the range with the least overlapping number to form a discontinuous range set [ f t，q ，f t，q+1 ]Wherein q represents the index of the intermittent range which appears in sequence in the whole variation range of the medical record window index; at a normal value f t，0 The average value of the intermittent range is used as a demarcation point as a starting point, different index value ranges of the window indexes are determined, and an index range set G of the window indexes corresponding to the single disease in different disease states is formed, wherein:
G=[[f t，0 ，]，[/>，/>]，…，[/>，/>]]the method comprises the steps of carrying out a first treatment on the surface of the And acquiring an index range set G of different window indexes of a single disease to form disease stage data.
In the present application, since there are individual differences between different cases, in order to accurately determine the index range values of the window index at different stages, the window index is determined by determining the number of times of overlapping the index ranges. It should be noted that, based on the analysis of the results of statistics of medical record data, the overlapping times are regularly distributed, i.e. a range with a significantly lower overlapping degree appears after a certain range with a high overlapping degree, so that, according to the overlapping condition, extracting the ranges with the lower overlapping degree can obtain intermittent values of a plurality of index ranges with higher overlapping degree, which are data representation of most patients in the disease stage. The end value of the index range is obtained as an average value. Of course, it can be obtained according to other statistical processing methods, such as confidence interval, weight analysis method, etc.
As a possible implementation manner, acquiring disease stage data of different diseases, classifying by using a related index as a third classification category, and forming disease difference data for different disease stages, including: removing the window index determined in the single disease associated check index data to form single disease associated non-window index data; dividing the single disease associated non-window index data according to different disease stages to form non-window index data of different disease stages; classifying and dividing non-window index data in non-window index data of different disease stages to form disease difference data of different disease stages.
In the application, after the disease stage range value division determination of the window index is completed, the rest non-window index often has stronger individual variability, which is an important part of medical record data, and can provide personalized data reference basis for later different patient diagnosis. The examination on the medical record is considered to have the frequency and batchability, so that after the window index is determined, the non-window index can be smoothly classified and divided according to the medical record treatment data.
In a second aspect, the present application provides a medical record profiling management system, adopting the medical record profiling management method of the first aspect, including an outpatient terminal for inputting the main information, the examination index result data, the diagnosis data and the patient basic information of the patient; the data processing center is used for acquiring information data sent by the clinic terminal to form medical record data and carrying out filing management according to the medical record data.
In the application, the system completely collects the case data of the patient through an outpatient service terminal and provides a reliable data base for case profiling management. The processing center centrally completes the filing management of medical records to form reasonable and ordered case files, and provides a material basis for understanding and tracing the illness state of patients and assisting the outpatient service by using history medical record data.
The medical record file creation management method and system provided by the embodiment have the beneficial effects that:
according to the method, medical record data are classified and divided in a grading manner with diseases as targets, so that reasonable disease classification case filing management data are formed, and reliable and accurate auxiliary reference is provided for diagnosis and treatment judgment based on historical medical record data in outpatient service. The high-level application of the medical record data is fully realized, and the history information of the patient is also associated, so that the medical record data can be conveniently known and traced based on the individual patient.
The system completely collects the case data of the patient through an outpatient department and provides a reliable data base for case profiling management. The processing center centrally completes the filing management of medical records to form reasonable and ordered case files, and provides a material basis for understanding and tracing the illness state of patients and assisting the outpatient service by using history medical record data.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a step diagram of a medical record file creation management method according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.
The current medical record management system is not perfect enough, and the management of medical records is mostly only simple to store all diagnosis and treatment data of patients according to the information of the patients. Most of the time, medical record management is used for only calling medical record data of a target patient if needed and performing simple understanding and disease tracing. The functions and the contents are very simple. Moreover, there is limited effect on the portion of the medical record that is in natural language, which can be structured if the physician enters it in a structured manner. If the physician enters natural language text, the portion cannot be structured.
Along with the increasing demands and the continuous development of medical systems, the demands for medical record profiling management are more and more complex, and particularly in the aspect of improving the more convenient outpatient service work of hospitals based on the historical diagnosis and treatment data, the urgent demands of medical record profiling management meet the functions of the aspect, and the medical record profiling management is exerted. Obviously, the current medical record filing management is mainly based on individual patient filing management, and in order to provide reliable data reference for outpatient service, a medical record data filing mode which is more fit for the outpatient service needs to be considered.
Referring to fig. 1, an embodiment of the present application provides a medical record file management method. According to the method, medical record data are classified and divided in a grading manner with diseases as targets, so that reasonable disease classification case filing management data are formed, and reliable and accurate auxiliary reference is provided for diagnosis and treatment judgment based on historical medical record data in outpatient service. The high-level application of the medical record data is fully realized, and the history information of the patient is also associated, so that the medical record data can be conveniently known and traced based on the individual patient.
The medical record file establishment management method comprises the following main steps:
s1: and obtaining medical record data, classifying the diseases into a first classification category according to the medical record data, and forming a disease information database aiming at different diseases.
The method comprises the following steps: obtaining diagnosis information, dividing the diagnosis information based on rules of feature words to determine feature diseases, and sorting medical record data of different feature diseases to form a feature disease information database; obtaining medical record data excluding characteristic diseases, determining the main diseases based on division of the inclusion relation according to main patient information, and sorting medical record data of different main diseases to form a main disease information database.
For classifying and classifying diseases, the simplest mode is to analyze and judge according to diagnosis information to determine, so that the type of the diseases can be accurately positioned, and a large number of medical records can be accurately classified according to the type of the diseases. In practical situations, however, the diagnostic information may not always be able to fully give accurate decisions, such as certain rare diseases, diseases with similar symptoms, etc. According to the application, the disease which is not given by the diagnosis information is classified by analyzing the main information, so that on one hand, the symptom of a patient can be accurately known, accurate disease judgment is given, a data basis is provided for subsequent disease-based analysis, and on the other hand, the main content and the therapeutic data form a corresponding relation, so that the rationality and the accuracy of the logical connection of case data are ensured.
The method for obtaining the diagnosis information, dividing and determining the characteristic diseases based on the rule of the characteristic words according to the diagnosis information, and sorting medical record data of different characteristic diseases to form a characteristic disease information database comprises the following steps: extracting disease nouns and pathological adjectives from the diagnosis information; classifying and dividing for the first time based on the disease nouns to form different main diseases; obtaining pathological adjectives under different main diseases, and carrying out secondary classification and division based on the pathological adjectives to form characteristic diseases; medical record data of different characteristic diseases are arranged according to the checking and judging data and the treatment data, and the checking and judging data and the treatment data are logically related in diagnosis and treatment to form a characteristic disease information database.
The method mainly comprises the steps of determining information for judging diseases in diagnostic information, extracting words with part of speech such as adjectives containing degrees and nouns containing disease names based on the diagnostic conditions of the diseases, and then merging and sorting the extracted words to accurately divide different diseases. The classification based on nouns can accurately locate the categories of diseases, and the classification based on adjectives can further refine the specific disease conditions of the main diseases, so that the disease data can be further processed in detail, and a reliable reference basis is provided for subsequent data use.
Obtaining medical record data excluding characteristic diseases, determining the main diseases based on division of inclusion relations according to main patient information, and sorting medical record data of different main diseases to form a main disease information database, wherein the method comprises the following steps: establishing a non-information element word stock based on the main description; acquiring main information, screening out non-information element words from the main information according to a non-information element word library, and forming main element information; performing word frequency statistics on different main element information, and determining the main diseases based on word frequency; and sorting medical record data of different main diseases according to the checking and judging data and the treatment data, and logically associating the checking and judging data with the treatment data in diagnosis and treatment to form a main disease information database.
Since the main information is generally about 20 words, and information such as symptoms, time, pain is often included therein, the information is removed relatively when the information is extracted. Because the main information is doctor description based on patient, there is often individuality description habit difference, so the main information can be screened by establishing a non-information element word stock based on big data. Then, the information element words are divided based on word frequency analysis, so that medical records can be reasonably classified according to disease types.
Will be different from the mainThe element information performs word frequency statistics, and determines the main diseases based on word frequency, including: acquiring information element class words of different main element information to form a main element information set A= [ A ] 1 ，A 2 ，…，A n ]Wherein A is n =[a n1 ，a n2 ，…，a nk ]N represents the total number of different main element information in the main element information set, and k represents the total number of information element words in the main element information with the reference number n; extracting information element words in all main element information in the main element information set A to form an information element statistical set B, A n ⊆ B, performing word frequency statistics to form information element frequency statistics results, and determining the main diseases according to the statistics results by the following steps: the information element words are combined in the same kind and then are sequenced according to the sequence from the big to the small of the frequency of the statistical result, and an information element statistical class collection C= [ C ] is formed 1 ，c 2 ，…，c m ]Wherein m is the total number of information element words which are formed after all the information element words in the information element statistical set B are subjected to similar combination and have no repetition, and C ⊆ B; obtaining information element class words with the largest frequency from the information element statistical class set C to form a frequency information element set D: when only one element c in D 1 At c 1 For screening the object, c is selected from A 1 Form a frequency screening set E= [ A ] x ，A x+1 ，…，A x+y ]X and y are all non-zero natural numbers, and x is less than n, and x+y is less than or equal to n; for the main element information in the frequency screening set E, there will be a division of c 1 The main element information of the similar information element words with the exception of not less than 2 is divided into the same main disease, and the other words except c are present 1 Determining the main element information of the similar information element words with the number less than 2 as the independent main disease until all the main element information is divided; when there are multiple elements in D, c is first in order of frequency from higher to lower 1 For screening the object, c is selected from A 1 Form a frequency screening set E= [ A ] x ，A x+1 ，…，A x+y ]X, y are non-zero natural numbers, andx is less than n, and x+y is less than or equal to n; for the main element information in the frequency screening set E, there will be a division of c 1 The main element information of the similar information element words with the exception of not less than 2 is divided into the same main disease, and the other words except c are present 1 Determining the main element information of the similar information element words with the number less than 2 as the independent main disease until all the main element information is divided; after all the main element information in E is removed in A, the element sequence in D is used as the screening object to be processed and c 1 The same screening mode is adopted until all elements in the D are used up; and eliminating the divided main element information, forming a new information element statistical set to perform word frequency statistics, and repeating the determining step of the main diseases until all main element information in the main element information set A is determined.
After word frequency statistics is carried out, the information element words with highest frequency are selected as screening objects, so that the subsequent screening quantity can be reduced rapidly, and the workload of division is reduced greatly. Meanwhile, due to the characteristics of the main information, the diseases of the same type basically keep consistent information in three aspects of time, symptoms and pain, so that when the type is divided and judged, the basis of whether three information element words are the same or not is more reasonable and efficient. The screening and dividing mode is repeated, so that disease division based on the main information can be completed quickly.
S2: and acquiring diagnosis and treatment data of the disease information databases of different diseases, and classifying by taking the window indexes as second classification categories to form disease stage data aiming at different diseases.
Obtaining diagnosis and treatment data of disease information databases of different diseases, classifying by taking window indexes as second classification categories, and forming disease stage data aiming at different diseases, wherein the method comprises the following steps: obtaining diagnosis and treatment data of a disease information database of a single disease, comparing the examination indexes based on health index values, and determining the changed associated examination indexes to form single disease associated examination index data; repeatedly analyzing the associated check indexes in the single disease associated check index data to determine window indexes, so as to form single disease window index data; and carrying out range statistics on window indexes in the single disease window index data according to different medical record sources, determining different stage range values, and carrying out stage division on the single disease based on the stage range values to form disease stage data.
After the disease type is divided, the data of different disease stages of different types of diseases are determined, and an important data basis is provided for the analysis of the disease development condition and the finer disease diagnosis by using a medical record archive later. For each disease, there are different stages of disease progression, and the different stages must have window indicators for judgment. The window index can be accurately and rapidly judged by adopting a comparison and repeatability analysis mode.
Performing repetitive analysis on the associated check index in the single disease associated check index data to determine a window index, forming single disease window index data, including: setting a repeatability threshold value, carrying out repeatability statistics on the associated check indexes, and forming repeatability statistics result data; and sorting according to the repeated statistics result data and according to the repeated frequency, and determining window indexes by combining the repeated threshold value to form single disease window index data.
Considering how many indexes are repeatable, it can be understood that the more repeatable indexes are more obvious for the condition of representing the disease, the threshold is set to select, on one hand, to optimize the window indexes, on the other hand, to improve the effectiveness and rationality of diagnosis, and to optimize the flow of the diagnosis and the reasonable classification of the data. Of course, the setting of the threshold may be determined as needed or as a result of statistical analysis of the data.
Window indexes in single disease window index data are subjected to index value range statistics according to different medical record sources, different stage range values are determined, and single disease is subjected to stage division based on the stage range values to form disease stage data, wherein the method comprises the following steps: combining different window indexes by taking different medical record sources as the basis of group division to form different medical record window index groups F v =[f v1 ，f v2 ，…，f vt ]Wherein v is the total number of the medical record window index groups, and t is the total number of window indexes; extracting the same medical record window index in different medical record window index groups, and performing range union analysis on index values of the medical record window index: establishing the number of overlapping index value ranges, and providing the range with the least overlapping number to form a discontinuous range set [ f t，q ，f t，q+1 ]Wherein q represents the index of the intermittent range which appears in sequence in the whole variation range of the medical record window index; at a normal value f t，0 The average value of the intermittent range is used as a demarcation point as a starting point, different index value ranges of the window indexes are determined, and an index range set G of the window indexes corresponding to the single disease in different disease states is formed, wherein:
G=[[f t，0 ，]，[/>，/>]，…，[/>，/>]]the method comprises the steps of carrying out a first treatment on the surface of the And acquiring an index range set G of different window indexes of a single disease to form disease stage data.
Since there are individual differences between different cases, the window index is determined by determining the number of overlapping index ranges in order to accurately determine the index range values of the window index at different stages. It should be noted that, based on the analysis of the results of statistics of medical record data, the overlapping times are regularly distributed, i.e. a range with a significantly lower overlapping degree appears after a certain range with a high overlapping degree, so that, according to the overlapping condition, extracting the ranges with the lower overlapping degree can obtain intermittent values of a plurality of index ranges with higher overlapping degree, which are data representation of most patients in the disease stage. The end value of the index range is obtained as an average value. Of course, it can be obtained according to other statistical processing methods, such as confidence interval, weight analysis method, etc.
S3: and acquiring disease stage data of different diseases, and classifying by taking the related indexes as a third classification class to form disease difference data aiming at different disease stages.
Acquiring disease stage data of different diseases, classifying by taking related indexes as a third classification category, and forming disease difference data aiming at different disease stages, wherein the method comprises the following steps: removing the window index determined in the single disease associated check index data to form single disease associated non-window index data; dividing the single disease associated non-window index data according to different disease stages to form non-window index data of different disease stages; classifying and dividing non-window index data in non-window index data of different disease stages to form disease difference data of different disease stages.
After the disease stage range value of the window index is divided and determined, the rest non-window index often has stronger individual variability, which is an important part of medical record data, and can provide personalized data reference basis for later different patient diagnosis. The examination on the medical record is considered to have the frequency and batchability, so that after the window index is determined, the non-window index can be smoothly classified and divided according to the medical record treatment data.
S4: and acquiring treatment data of disease information databases of different diseases, and matching the treatment data with disease difference data to form disease treatment related information.
The disease treatment associated information can ensure the matching of the examination diagnosis data and the treatment data, provides effective help for assisting the outpatient service, and unifies the medical record data of the patient.
S5: and correlating the disease treatment correlation information with the patient data to form a disease-based patient medical record archive.
The invention also provides a medical record filing management system, which adopts the medical record filing management method provided by the invention, and comprises an outpatient terminal, a medical record filing management system and a medical record filing management system, wherein the outpatient terminal is used for inputting main information, check index result data, diagnosis data and basic information of a patient; the data processing center is used for acquiring information data sent by the clinic terminal to form medical record data and carrying out filing management according to the medical record data.
The system completely collects the case data of the patient through an outpatient department and provides a reliable data base for case profiling management. The processing center centrally completes the filing management of medical records to form reasonable and ordered case files, and provides a material basis for understanding and tracing the illness state of patients and assisting the outpatient service by using history medical record data.
In summary, the medical record file creation management method provided by the embodiment of the application has the beneficial effects that:
according to the method, medical record data are classified and divided in a grading manner with diseases as targets, so that reasonable disease classification case filing management data are formed, and reliable and accurate auxiliary reference is provided for diagnosis and treatment judgment based on historical medical record data in outpatient service. The high-level application of the medical record data is fully realized, and the history information of the patient is also associated, so that the medical record data can be conveniently known and traced based on the individual patient.
The system completely collects the case data of the patient through an outpatient department and provides a reliable data base for case profiling management. The processing center centrally completes the filing management of medical records to form reasonable and ordered case files, and provides a material basis for understanding and tracing the illness state of patients and assisting the outpatient service by using history medical record data.
In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the elements and method steps of the examples described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or as a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system, system and unit described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, system or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random acceLL memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (8)
1. A medical record profiling management method, comprising:
acquiring medical record data, and classifying diseases into a first classification category according to the medical record data to form a disease information database aiming at different diseases;
obtaining diagnosis and treatment data of the disease information databases of different diseases, and classifying by taking window indexes as second classification categories to form disease stage data aiming at different diseases;
Acquiring the disease stage data of different diseases, and classifying by taking related indexes as a third classification class to form disease difference data aiming at different disease stages;
acquiring treatment data of the disease information database of different diseases, and matching the treatment data with the disease difference data to form disease treatment associated information;
correlating the disease treatment correlation information with patient data to form a disease-based patient medical record archive;
the method for obtaining diagnosis and treatment data of the disease information database of different diseases comprises the steps of:
acquiring diagnosis and treatment data of the disease information database of the single disease, comparing the examination indexes based on the health index values, and determining the changed associated examination indexes to form single disease associated examination index data; repeatedly analyzing the associated check indexes in the single disease associated check index data to determine window indexes, so as to form single disease window index data; performing index value range statistics on the window indexes in the single disease window index data according to different medical record sources, determining different stage range values, and performing stage division on the single disease based on the stage range values to form disease stage data;
Acquiring the disease stage data of different diseases, classifying the disease stage data by taking the related indexes as a third classification category, and forming disease difference data aiming at different disease stages, wherein the method comprises the following steps:
removing the window index determined in the single disease associated check index data to form single disease associated non-window index data; dividing the single disease associated non-window index data according to different disease stages to form non-window index data of different disease stages; classifying and dividing the non-window index data in the non-window index data of different disease stages to form disease difference data of different disease stages.
2. The medical record filing management method according to claim 1, wherein the obtaining medical record data, classifying the diseases into a first classification category according to the medical record data, and forming a disease information database for different diseases, comprises:
obtaining diagnosis information, dividing and determining characteristic diseases based on rules of characteristic words according to the diagnosis information, and sorting medical record data of different characteristic diseases to form a characteristic disease information database;
And acquiring medical record data excluding the characteristic diseases, determining the main diseases based on the division of the inclusion relation according to the main information of the patient, and sorting the medical record data of different main diseases to form a main disease information database.
3. The medical record filing management method according to claim 2, wherein the obtaining the diagnosis information, performing rule division based on feature words according to the diagnosis information to determine feature diseases, and sorting medical record data of different feature diseases to form a feature disease information database, comprises:
extracting disease nouns and pathological adjectives from the diagnosis information;
classifying and dividing for the first time based on the disease nouns to form different main diseases;
obtaining the pathological adjectives under different main diseases, and carrying out secondary classification and division based on the pathological adjectives to form the characteristic diseases;
and sorting medical record data of different characteristic diseases according to the checking and judging data and the treatment data, and logically associating the checking and judging data with the treatment data in diagnosis and treatment to form the characteristic disease information database.
4. The medical record filing management method as set forth in claim 3, wherein the obtaining medical record data excluding the characteristic diseases, determining the disease based on division of inclusion relation according to the patient main information, and sorting medical record data of different main diseases to form a main disease information database, includes:
establishing a non-information element word stock based on the main description;
acquiring main information, screening out non-information element words from the main information according to the non-information element word stock, and forming main element information;
performing word frequency statistics on different main element information, and determining the main diseases based on word frequency;
and sorting the medical record data of different main diseases according to the checking and judging data and the treatment data, and logically associating the checking and judging data with the treatment data in diagnosis and treatment to form the main disease information database.
5. The medical record filing management method according to claim 4, wherein the step of counting word frequencies of different main element information and determining the main diseases based on the word frequencies comprises the steps of:
Obtaining information element class words of different main element information to form a main element information set A= [ A ] 1 ，A 2 ，…，A n ]Wherein an= [ a ] n1 ，a n2 ，…，a nk ]N represents the total number of different main element information in the main element information set, and k represents the total number of the information element class words in the main element information with the reference number n;
extracting the information element words in all the main element information in the main element information set A to form informationElement statistics set B, A n ⊆ B, performing word frequency statistics to form information element frequency statistics results, and determining the main diseases according to the statistics results by the following steps:
the information element words are subjected to similar combination and then are sequenced according to the sequence from the big to the small of the frequency of the statistical result to form an information element statistical score class set C= [ C ] 1 ，c 2 ，…，c m ]Wherein m is the total number of the information element words which are formed after all the information element words in the information element statistical set B are subjected to similar combination and have no repetition, and C ⊆ B;
obtaining the information element class word with the largest frequency from the information element statistical class set C to form a frequency information element set D:
when there is only one element c in D 1 At c 1 For screening the object, c is selected from A 1 Form a frequency screening set E= [ A ] x ，A x+1 ，…，A x+y ]X and y are all non-zero natural numbers, and x is less than n, and x+y is less than or equal to n; dividing the main element information with the same class of information element words which are not less than 2 and are except c1 into the same main disease for the main element information in the frequency screening set E, and determining the main element information with the same class of information element words which are not less than 2 and are except c1 into the independent main disease until all the main element information is divided;
when there are multiple elements in D, c is first in order of frequency from higher to lower 1 For screening the object, c is selected from A 1 Form a frequency screening set E= [ A ] x ，A x+1 ，…，A x+y ]X and y are all non-zero natural numbers, and x is less than n, and x+y is less than or equal to n; for the main element information in the frequency screen set E, dividing the main element information with the same category of information element words with the exception of c1 into the same main disease, and determining the main element information with the same category of information element words with the exception of c1 into the single main disease Until all the main element information is divided; after all the main element information in E is removed, the subsequent element sequence in D is used as a screening object to carry out the same screening mode as c1 until all the elements in D are used up;
and eliminating the divided main element information, forming a new information element statistical set to perform word frequency statistics, and repeating the step of determining the main diseases until all main element information in the main element information set A is determined.
6. The medical record profiling management method according to claim 1, wherein repeatedly analyzing the associated check index in the single disease associated check index data, determining a window index, and forming single disease window index data, comprises:
setting a repeatability threshold value, carrying out repeatability statistics on the associated check indexes, and forming repeatability statistics result data;
and sorting according to the repeatability statistical result data and according to the repetition frequency, and determining the window index by combining the repeatability threshold value to form the single disease window index data.
7. The medical record profiling management method according to claim 6, wherein the step of performing index value range statistics on the window index in the single disease window index data according to different medical record sources, determining different stage range values, and performing stage division on the single disease based on the stage range values to form the disease stage data includes:
Combining different window indexes by taking different medical record sources as the basis of group division to form different medical record window index groups F v =[f v1 ，f v2 ，…，f vt ]Wherein v is the total number of the medical record window index groups, and t is the total number of the window indexes;
extracting the same medical record window indexes in different medical record window index groups, and performing range union analysis on index values of the medical record window indexes:
establishing the number of overlapping index value ranges, and providing the range with the least overlapping number to form a discontinuous range set [ f t，q ，f t，q+1 ]Wherein q represents the index of the intermittent range which appears in sequence in the whole variation range of the medical record window index;
at a normal value f t，0 Taking the average value of the intermittent range as a demarcation point, determining different index value ranges of the window indexes to form an index range set G of the window indexes corresponding to the single disease in different disease states, wherein:
G=[[f t，0 ，]，[/>，/>]，…，[/>，/>]]；
and obtaining the index range set G of different window indexes of the single disease to form disease stage data.
8. A medical record profiling management system employing the medical record profiling management method according to any one of claims 1 to 7, comprising:
The outpatient terminal is used for inputting the main information of the patient, the examination index result data, the diagnosis data and the basic information of the patient;
the data processing center is used for acquiring the information data sent by the outpatient terminal to form medical record data and carrying out filing management according to the medical record data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310609703.3A CN116344011B (en) | 2023-05-29 | 2023-05-29 | Medical record file establishment management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310609703.3A CN116344011B (en) | 2023-05-29 | 2023-05-29 | Medical record file establishment management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116344011A CN116344011A (en) | 2023-06-27 |
| CN116344011B true CN116344011B (en) | 2023-08-15 |
Family
ID=86884438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310609703.3A Active CN116344011B (en) | 2023-05-29 | 2023-05-29 | Medical record file establishment management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116344011B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117235582B (en) * | 2023-10-31 | 2024-10-01 | 中国人民解放军总医院 | Multi-granularity information processing method and device based on electronic medical record |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111489821A (en) * | 2020-03-31 | 2020-08-04 | 宜昌市中心人民医院(三峡大学第一临床医学院、三峡大学附属中心人民医院) | Diagnostic group management system |
| WO2021139116A1 (en) * | 2020-05-14 | 2021-07-15 | 平安科技（深圳）有限公司 | Method, apparatus and device for intelligently grouping similar patients, and storage medium |
| WO2022229964A1 (en) * | 2021-04-29 | 2022-11-03 | Impilo Ltd. | Method of generating a diseases database, usage of the diseases database, and system therefor |
| CN115374053A (en) * | 2022-08-09 | 2022-11-22 | 科凌力智能医学软件(深圳)有限公司 | Intelligent information archiving method and device, electronic equipment and storage medium |
| CN115620915A (en) * | 2022-09-14 | 2023-01-17 | 杭州逸曜信息技术有限公司 | Diagnosis and treatment data-based user portrait label mining method and device and computer equipment |
-
2023
- 2023-05-29 CN CN202310609703.3A patent/CN116344011B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111489821A (en) * | 2020-03-31 | 2020-08-04 | 宜昌市中心人民医院(三峡大学第一临床医学院、三峡大学附属中心人民医院) | Diagnostic group management system |
| WO2021139116A1 (en) * | 2020-05-14 | 2021-07-15 | 平安科技（深圳）有限公司 | Method, apparatus and device for intelligently grouping similar patients, and storage medium |
| WO2022229964A1 (en) * | 2021-04-29 | 2022-11-03 | Impilo Ltd. | Method of generating a diseases database, usage of the diseases database, and system therefor |
| CN115374053A (en) * | 2022-08-09 | 2022-11-22 | 科凌力智能医学软件(深圳)有限公司 | Intelligent information archiving method and device, electronic equipment and storage medium |
| CN115620915A (en) * | 2022-09-14 | 2023-01-17 | 杭州逸曜信息技术有限公司 | Diagnosis and treatment data-based user portrait label mining method and device and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 大数据背景下财务精细化档案管理应用研究;钟雪柏等;《档案工作》(第7期);第140-141页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116344011A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Divjak et al. | Finding structure in linguistic data | |
| AU2011247830B2 (en) | Method and system for generating text | |
| CN116344011B (en) | Medical record file establishment management method and system | |
| CN110299209B (en) | Similar medical record searching method, device and equipment and readable storage medium | |
| KR20160098084A (en) | System for filtering documents of interest and method thereof | |
| JP6316844B2 (en) | User interface for predictive model generation | |
| CN111739634A (en) | Method, device and equipment for intelligently grouping similar patients and storage medium | |
| CN111599486A (en) | Traditional Chinese medicine prescription recommendation sorting method based on data matching | |
| CN113724847A (en) | Medical resource allocation method, device, terminal equipment and medium based on artificial intelligence | |
| Nhu et al. | Deep learning for automated epileptiform discharge detection from scalp EEG: A systematic review | |
| CN115438040A (en) | Pathological archive information management method and system | |
| CN115101193A (en) | Symptom recommendation method and device and computer-readable storage medium | |
| KR102359652B1 (en) | System and Method for Classifying Disease Using Class Association Rules | |
| JP2001175724A (en) | System for analyzing medical fee bill | |
| JP2015032013A (en) | Numeric data analyzer and program | |
| JP7368679B2 (en) | Cell population identification systems, methods, and programs | |
| CN114168751B (en) | Medical text label identification method and system based on medical knowledge conceptual diagram | |
| Jouirou et al. | Multi-view content-based mammogram retrieval using dynamic similarity and locality sensitive hashing | |
| CN109102896A (en) | A kind of method of generating classification model, data classification method and device | |
| CN114780408A (en) | Software user behavior path analysis method and device | |
| CN111986815B (en) | Project combination mining method based on co-occurrence relation and related equipment | |
| Watanabe et al. | SACMiner: A new classification method based on statistical association rules to mine medical images | |
| CN114021699A (en) | Gradient-based convolutional neural network pruning method and device | |
| Ambika et al. | Anaemia Estimation for Patients Using Lasso And Ridge Regression Algorithms | |
| De Iorio et al. | Bayesian nonparametric mixture modeling for temporal dynamics of gender stereotypes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |