CN113284614A - Abnormal diagnosis recognition method and device, electronic equipment and storage medium - Google Patents

Abnormal diagnosis recognition method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113284614A
CN113284614A CN202110633650.XA CN202110633650A CN113284614A CN 113284614 A CN113284614 A CN 113284614A CN 202110633650 A CN202110633650 A CN 202110633650A CN 113284614 A CN113284614 A CN 113284614A
Authority
CN
China
Prior art keywords
data
target patient
preset
disease
visit
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.)
Pending
Application number
CN202110633650.XA
Other languages
Chinese (zh)
Inventor
徐欣星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Ping An Smart Healthcare Technology Co ltd
Original Assignee
Ping An International Smart City Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An International Smart City Technology Co Ltd filed Critical Ping An International Smart City Technology Co Ltd
Priority to CN202110633650.XA priority Critical patent/CN113284614A/en
Publication of CN113284614A publication Critical patent/CN113284614A/en
Pending legal-status Critical Current

Links

Images

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
    • 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
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Epidemiology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Primary Health Care (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • General Business, Economics & Management (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computational Linguistics (AREA)
  • Business, Economics & Management (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Medicinal Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The invention relates to the technical field of artificial intelligence, and provides an identification method, an identification device, electronic equipment and a storage medium for abnormal treatment, wherein the method comprises the following steps: determining first data and second data of a target patient according to the participation information and the visit data of the target patient; inputting the first population category and the disease data of the target patient into a pre-trained disease type prediction model, and outputting a first pre-judgment result; when the first pre-judgment result does not exist in the preset first diagnosis condition, inputting the second crowd category and the medicine data into a pre-trained medicine type prediction model, and outputting a second pre-judgment result; and when a second pre-judgment result exists in the preset second diagnosis condition, determining that the target patient is an abnormal diagnosis. According to the method and the device, the abnormal treatment identification is carried out from multiple dimensions according to the first crowd type, the disease type, the second crowd type and the medicine type of the patient, so that the accuracy of the abnormal treatment identification is improved.

Description

Abnormal diagnosis recognition method and device, electronic equipment and storage medium
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an abnormal treatment identification method and device, electronic equipment and a storage medium.
Background
In the current medical industry, disease data and drug data are analyzed, abnormal diagnosis is identified according to the analysis result, and the simple diagnosis of prescriptions is assisted by practitioners in the medical industry such as hospitals.
However, in the process of identifying abnormal treatment for disease data and medicine data, classification of people is not considered, and a problem that an analysis result is inaccurate due to the fact that one medical insurance card is used by multiple people, and therefore the accuracy of the identification result of abnormal treatment identification is low can exist.
Disclosure of Invention
In view of the above, there is a need for an abnormal medical examination recognition method, an abnormal medical examination recognition apparatus, an electronic device, and a storage medium, which perform abnormal medical examination recognition from multiple dimensions according to a first population category, a disease type, a second population category, and a drug type of a patient, and improve accuracy of the abnormal medical examination recognition.
A first aspect of the present invention provides a method for identifying an abnormal medical visit, the method comprising:
analyzing a visit request of a target patient to acquire participation information and visit data of the target patient;
determining first data and second data of the target patient according to the participation information and the visit data of the target patient, wherein the first data comprises a first crowd category and disease data, and the second data comprises a second crowd category and medicine data;
inputting the first population category and the disease data of the target patient into a pre-trained disease type prediction model, and outputting a first pre-judgment result;
identifying whether a first pre-judgment result exists in a preset first diagnosis condition or not;
when the first pre-judgment result does not exist in the preset first visit condition, inputting the second population category and the drug data into a pre-trained drug type prediction model, and outputting a second pre-judgment result;
identifying whether a second pre-judgment result exists in a preset second diagnosis condition or not;
and when the second pre-judgment result exists in the preset second diagnosis condition, determining that the target patient is an abnormal diagnosis.
Optionally, the determining the first data and the second data of the target patient according to the participation information and the visit data of the target patient comprises:
identifying the participation information of the target patient, and determining the age and the sex of the target patient;
determining a first crowd category and a second crowd category which are matched with the age and the gender of the target patient from a preset crowd category library;
extracting key information from the visit data, and converting the key information according to a preset format conversion rule to obtain converted key information;
dividing the converted key information into disease data and medicine data according to a preset dividing rule;
determining the first population category and disease data as first data for the target patient and determining the second population category and drug data as second data for the target patient.
Optionally, the training process of the disease type prediction model includes:
obtaining a plurality of patients corresponding to each first group category;
extracting a plurality of disease data and corresponding disease types of each patient to form a data set;
randomly dividing the data set into a first number of training sets and a second number of test sets;
inputting a plurality of disease data in the training set and corresponding disease types into a preset convolutional neural network for training to obtain a disease type prediction model;
inputting the test set into the disease type prediction model for testing to obtain a test passing rate;
judging whether the test passing rate is greater than a preset passing rate threshold value or not;
when the test passing rate is greater than or equal to the preset passing rate threshold value, finishing the training of the disease type prediction model; or when the test passing rate is smaller than the preset passing rate threshold, increasing the number of the training sets, and re-training the disease type prediction model.
Optionally, the preset first visit condition comprises one or more of the following combinations:
the disease type is a common female disease, and the target patient is a male;
the disease type is a common disease in males, and the target patient is a female;
the disease type is common diseases of the elderly, and the target patient is young;
the disease type is common in young people, and the target patient is the old;
the disease type is childhood disease, and the target patient is an adult;
the disease type is common in young people and the target patient is children.
Optionally, the preset second visit condition comprises one or more of the following combinations:
the type of the medicine is forbidden for children, and the target patient is children;
the medicine type is pediatric, and the target patient is an adult;
the drug type is female medication and the target patient is male;
the drug type is male medication and the target patient is female.
Optionally, the identifying whether the preset first medical condition exists or not includes:
matching the first pre-judgment result with the preset first medical condition;
when a first diagnosis condition matched with the first pre-judgment result is matched in the preset first diagnosis conditions, determining that the first pre-judgment result exists in the preset first diagnosis conditions; or
And when the first diagnosis condition matched with the first pre-judgment result is not matched in the preset first diagnosis conditions, determining that the first pre-judgment result does not exist in the preset first diagnosis conditions.
Optionally, the parsing the visit request of the target patient to obtain the participation information and the visit data of the target patient includes:
analyzing the message of the visit request of the target patient to obtain message information carried by the message;
acquiring the identification code of the target patient from the message information;
determining an interface of the participation information and an interface of the visit data according to the identification code of the target patient;
calling the interface of the participation information to acquire the participation information of the target patient, and calling the interface of the visit data to acquire the visit data of the target patient.
A second aspect of the present invention provides an apparatus for identifying an abnormal medical visit, the apparatus comprising:
the analysis module is used for analyzing the visit request of the target patient to acquire the participation insurance information and the visit data of the target patient;
the first determination module is used for determining first data and second data of the target patient according to the participation information and the visit data of the target patient, wherein the first data comprises a first crowd category and disease data, and the second data comprises a second crowd category and medicine data;
the first input module is used for inputting the first crowd category and the disease data of the target patient into a pre-trained disease type prediction model and outputting a first pre-judgment result;
the first identification module is used for identifying whether a first pre-judgment result exists in a preset first diagnosis condition or not;
the second input module is used for inputting the second crowd type and the medicine data into a pre-trained medicine type prediction model and outputting a second pre-judgment result when the first pre-judgment result does not exist in the preset first diagnosis condition;
the second identification module is used for identifying whether a second pre-judgment result exists in a preset second diagnosis condition or not;
and the second determination module is used for determining that the target patient is an abnormal diagnosis when the second pre-judgment result exists in the preset second diagnosis condition.
A third aspect of the present invention provides an electronic device, which includes a processor and a memory, wherein the processor is configured to implement the method for identifying an abnormal medical visit when executing a computer program stored in the memory.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method for identifying an abnormal medical visit.
In summary, according to the identification method, the identification device, the electronic device and the storage medium for abnormal medical visits, on one hand, the first crowd type, the disease type, the second crowd type and the medicine type of the patient are determined according to the participation information and the medical visit data of the patient, and in the subsequent identification process for abnormal medical visits, the crowd type, the disease type and the medicine type are combined to be considered from multiple dimensions, so that the accuracy of the identification result in the subsequent identification process for abnormal medical visits is improved; on the other hand, the first crowd type and the disease data of the target patient are input into a pre-trained disease type prediction model, a first pre-judgment result is output, the second crowd type and the medicine data are input into a pre-trained medicine type prediction model, a second pre-judgment result is output, and whether the target patient belongs to an abnormal doctor or not is verified from two dimensions by combining the crowd type of the target patient, so that the accuracy of the recognition result of the abnormal doctor is improved; and finally, when a second pre-judgment result exists in the preset second treatment condition, determining that the target patient is an abnormal treatment, sending alarm information to the target patient after determining that the target patient is the abnormal treatment, informing the target patient that the target patient can not use the medical insurance card for treatment, and sending abnormal information of the abnormal treatment to a doctor of the target patient to remind the doctor of determining whether the prescribed prescription is correct or not, so that errors in the treatment process are reduced, and the safety of the treatment is improved.
Drawings
Fig. 1 is a flowchart of an identification method for an abnormal medical visit according to an embodiment of the present invention.
Fig. 2 is a structural diagram of an apparatus for identifying an abnormal medical examination according to a second embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Example one
Fig. 1 is a flowchart of an identification method for an abnormal medical visit according to an embodiment of the present invention.
In this embodiment, the method for identifying an abnormal medical examination may be applied to an electronic device, and for an electronic device that needs to identify an abnormal medical examination, the function of identifying an abnormal medical examination provided by the method of the present invention may be directly integrated on the electronic device, or may be run in the electronic device in the form of a Software Development Kit (SDK).
As shown in fig. 1, the method for identifying an abnormal medical visit specifically includes the following steps, and the order of the steps in the flowchart may be changed and some may be omitted according to different requirements.
And S11, analyzing the visit request of the target patient to acquire the participation insurance information and the visit data of the target patient.
In this embodiment, the visit request is sent from the electronic device to the server, and is used to request a visit, specifically, the visit request may be sent from the target patient to the server through the electronic device during the visit process, for example, the target patient may log in to a medical institution through the electronic device, such as a visit subsystem in a hospital medical system, and send a visit request to the medical system server in the visit subsystem.
In this embodiment, the visit request carries referral information and visit data of the target patient, specifically, the referral information includes an identification number, a contact information, a social security number and other information that can confirm the identity of the target patient, and the visit data includes disease data, medicine data and other data.
In an optional embodiment, the parsing the visit request of the target patient to obtain the participation information and the visit data of the target patient includes:
analyzing the message of the visit request of the target patient to obtain message information carried by the message;
acquiring the identification code of the target patient from the message information;
determining an interface of the participation information and an interface of the visit data according to the identification code of the target patient;
calling the interface of the participation information to acquire the participation information of the target patient, and calling the interface of the visit data to acquire the visit data of the target patient.
In this embodiment, the identification code of the target patient may be a social security number of the target patient, or may also be an identification number of the target patient or a mobile phone number of the target patient.
In this embodiment, in order to ensure the correctness of the participation information and the visit data, the participation information and the visit data are simultaneously acquired from the corresponding interfaces, so that the acquisition efficiency of the participation information and the visit data is improved.
And S12, determining first data and second data of the target patient according to the participation information and the visit data of the target patient, wherein the first data comprises a first crowd category and disease data, and the second data comprises a second crowd category and medicine data.
In this embodiment, since the information of participation in insurance and the data of visiting doctor include different types of data, the information of participation in insurance and the data of visiting doctor of the target patient are classified to determine the first data and the second data of the target patient.
In an alternative embodiment, the determining the first data and the second data of the target patient according to the participation information and the visit data of the target patient comprises:
identifying the participation information of the target patient, and determining the age and the sex of the target patient;
determining a first crowd category and a second crowd category which are matched with the age and the gender of the target patient from a preset crowd category library;
extracting key information from the visit data, and converting the key information according to a preset format conversion rule to obtain converted key information;
dividing the converted key information into disease data and medicine data according to a preset dividing rule;
determining the first population category and disease data as first data for the target patient and determining the second population category and drug data as second data for the target patient.
Specifically, the first group of people is classified based on age and gender, and the group of people is classified into three types according to age: children, young adults and elderly, wherein children are < 14 years old and elderly > 60 years old; the population is divided into two categories according to gender: male and female.
The second crowd category is divided based on age and gender, and the crowd is divided into two categories according to age: children and adults, wherein children are < 14 years old; the population is divided into two categories according to gender: male and female.
In other alternative embodiments, the first population category and the second population category may also classify women into both pregnant and non-pregnant categories.
In this embodiment, a format conversion rule and a partition rule may be preset, where the preset format conversion rule may be set according to a medical general format, and the partition rule may be preset according to a disease attribute and a drug attribute, for example, when the key information is cough, the cough is partitioned into disease data; the key information is amoxicillin, and the amoxicillin is classified into medicine data.
In other alternative embodiments, the disease data may include one or more and the drug data may include one or more.
In this embodiment, the first crowd type, the disease type, the second crowd type and the medicine type of the patient are determined according to the participation information and the visit data of the patient, and in the subsequent abnormal visit identification process, the crowd type, the disease type and the medicine type are combined, and the consideration is performed from multiple dimensions, so that the accuracy of the identification result in the subsequent abnormal visit identification process is improved.
And S13, inputting the first crowd category and the disease data of the target patient into a pre-trained disease type prediction model, and outputting a first prediction result.
In this embodiment, after the first population category and the disease data of the target patient are determined, the first population category and the disease data of the target patient are input into a pre-trained disease type model to obtain a disease type of the target patient, the disease type and the first population category of the target patient are determined as a first predetermined result, and the first predetermined result output by the disease type prediction model is received.
Specifically, the training process of the disease type prediction model comprises the following steps:
obtaining a plurality of patients corresponding to each first group category;
extracting a plurality of disease data and corresponding disease types of each patient to form a data set;
randomly dividing the data set into a first number of training sets and a second number of test sets;
inputting a plurality of disease data in the training set and corresponding disease types into a preset convolutional neural network for training to obtain a disease type prediction model;
inputting the test set into the disease type prediction model for testing to obtain a test passing rate;
judging whether the test passing rate is greater than a preset passing rate threshold value or not;
when the test passing rate is greater than or equal to the preset passing rate threshold value, finishing the training of the disease type prediction model; or when the test passing rate is smaller than the preset passing rate threshold, increasing the number of the training sets, and re-training the disease type prediction model.
In this embodiment, the first pre-judging result is used to characterize the disease type of the target patient, and the first population category and the disease type of the target patient are determined as the first pre-judging result of the target patient.
In particular, the disease types may include, but are not limited to, one or more combinations of the following: common diseases of women; common diseases in men; common diseases of children; common diseases in young people; common diseases of the elderly.
In this embodiment, for a plurality of first population categories, a data set may be constructed by obtaining a plurality of patients in each first population category, and a plurality of disease data and corresponding disease types for each patient. And in the subsequent service process, taking the plurality of disease data of the target patient and the corresponding disease types as new data so as to increase the number of the data sets, and retraining the disease type prediction model based on the new data sets. Namely, the disease type prediction model is continuously updated, so that the accuracy of disease type prediction is continuously improved.
And S14, identifying whether the preset first diagnosis condition has the first pre-judgment result.
In this embodiment, first medical treatment conditions may be preset, and specifically, the preset first medical treatment conditions include one or more of the following combinations:
the disease type is a common female disease, and the target patient is a male; the disease type is a common disease in males, and the target patient is a female; the disease type is common diseases of the elderly, and the target patient is young; the disease type is common in young people, and the target patient is the old; the disease type is childhood disease, and the target patient is an adult; the disease type is common in young people and the target patient is children.
In other optional embodiments, the disease type of the preset first visit condition is a common disease of the pregnant woman, and the patient is not the pregnant woman.
In an optional embodiment, the identifying whether the preset first visit condition exists or not includes:
matching the first pre-judgment result with the preset first medical condition;
when a first diagnosis condition matched with the first pre-judgment result is matched in the preset first diagnosis conditions, determining that the first pre-judgment result exists in the preset first diagnosis conditions; or
And when the first diagnosis condition matched with the first pre-judgment result is not matched in the preset first diagnosis conditions, determining that the first pre-judgment result does not exist in the preset first diagnosis conditions.
In this embodiment, the disease type and the first population category of the target patient are matched with the preset first diagnosis condition, whether the target patient is an abnormal diagnosis is preliminarily determined according to the matching result, the disease data does not need to be specifically analyzed, the prediction result of the abnormal diagnosis is directly obtained, and the recognition efficiency of the abnormal diagnosis prediction is improved.
And S15, when the first pre-judgment result does not exist in the preset first diagnosis condition, inputting the second population category and the medicine data into a pre-trained medicine type prediction model, and outputting a second pre-judgment result.
In this embodiment, the drug type prediction module may be trained in advance, and specifically, the training process of the drug type prediction model is the same as the training process of the disease type prediction model, which is not described in detail herein.
In this embodiment, after the second population category and the drug data are obtained, the second population category and the drug data are input into the drug type prediction model, so as to obtain the drug type of the medication for the target patient.
In particular, the drug type may include, but is not limited to, one or more of the following: medication for children, medication for women and medication for men.
Further, the method further comprises:
and when the first pre-judgment result exists in the preset first diagnosis condition, determining that the target patient is an abnormal diagnosis.
In this embodiment, for a plurality of second population categories, a data set may be constructed by obtaining a plurality of patients in each second population category, and a plurality of drug data and corresponding drug types for each patient. And in the subsequent service process, taking the plurality of drug data of the target patient and the corresponding drug types as new data so as to increase the number of the data sets, and retraining the drug type prediction model based on the new data sets. Namely, the medicine type prediction model is continuously updated, so that the accuracy of medicine type prediction is continuously improved.
And S16, identifying whether the preset second diagnosis condition has the second pre-judgment result.
In this embodiment, the second predetermined result is used to characterize the drug type of the target patient, and the second population category and the drug type of the target patient are determined as the second predetermined result of the target patient.
Specifically, the preset second visit condition includes one or more of the following combinations:
the type of the medicine is forbidden for children, and the target patient is children; the medicine type is pediatric, and the target patient is an adult; the drug type is female medication and the target patient is male; the drug type is male medication and the target patient is female.
In some other optional embodiments, the type of the predetermined second visit condition is prohibited for the pregnant woman, and the target patient is the pregnant woman.
In an optional embodiment, the identifying whether the preset second visit condition exists or not includes:
matching the second pre-judgment result with the preset second visit condition;
when a second diagnosis condition matched with the second pre-judgment result is matched in the preset second diagnosis conditions, determining that the second pre-judgment result exists in the preset second diagnosis conditions; or
And when the second diagnosis condition matched with the second pre-judgment result is not matched in the preset second diagnosis conditions, determining that the second pre-judgment result does not exist in the preset second diagnosis conditions.
In this embodiment, when it is determined that there is no abnormality in the disease treatment of the target patient, whether there is an abnormality in the drug treatment of the target patient is continuously identified, and by matching the second predetermined result with the preset second treatment condition, whether there is an abnormality in the drug treatment of the target patient is determined according to the matching result, and by combining the population category of the target patient, whether the target patient belongs to the abnormal treatment is verified from two dimensions, so that the accuracy of the identification result of the abnormal treatment is improved.
And S17, when the second pre-judgment result exists in the preset second diagnosis condition, determining that the target patient is an abnormal diagnosis.
In this embodiment, the abnormal medical visit may be used to indicate whether the target patient borrows a medical insurance card of another person during the medical visit, and may also be used to indicate that a disease description error or a medication abnormality exists in a medical prescription prescribed by a doctor.
Further, the method further comprises:
and when the target patient is determined to be abnormal, ending the treatment, and sending alarm information to the target patient and sending abnormal information corresponding to the abnormal treatment to a doctor for seeing a doctor corresponding to the target patient according to a preset sending mode.
And S18, when the second pre-judgment result does not exist in the preset second diagnosis condition, determining that the target patient is a normal diagnosis, and continuing to perform the diagnosis.
In this embodiment, when it is determined that the target patient is an abnormal medical treatment, the target patient is sent with alarm information to inform that the target patient cannot use the medical insurance card for medical treatment, and the abnormal information of the abnormal medical treatment is sent to the doctor of the target patient to remind the doctor of determining whether the prescribed prescription is correct, so that errors in the medical treatment process are reduced, and the safety of the medical treatment is improved.
In some alternative embodiments, the method comprises:
analyzing a visit request of a target patient to acquire participation information and visit data of the target patient;
determining first data and second data of the target patient according to the participation information and the visit data of the target patient, wherein the first data comprises a first crowd category and disease data, and the second data comprises a second crowd category and medicine data;
inputting the second crowd category and the medicine data into a pre-trained medicine type prediction model, and outputting a second pre-judgment result;
identifying whether a second pre-judgment result exists in a preset second diagnosis condition or not;
when the second pre-judgment result does not exist in the preset second diagnosis condition, inputting the first population category and the disease data of the target patient into a pre-trained disease type prediction model, and outputting a first pre-judgment result;
identifying whether a first pre-judgment result exists in a preset first diagnosis condition or not;
and when the first pre-judgment result exists in the preset first diagnosis condition, determining that the target patient is an abnormal diagnosis.
In some alternative embodiments, the method comprises:
analyzing a visit request of a target patient to acquire participation information and visit data of the target patient;
determining first data and second data of the target patient according to the participation information and the visit data of the target patient, wherein the first data comprises a first crowd category and disease data, and the second data comprises a second crowd category and medicine data;
inputting the first population category and the disease data of the target patient into a pre-trained disease type prediction model, outputting a first pre-judgment result, inputting the second population category and the drug data into a pre-trained drug type prediction model, and outputting a second pre-judgment result;
identifying whether a first pre-judgment result exists in a preset first diagnosis condition or not, and identifying whether a second pre-judgment result exists in a preset second diagnosis condition or not;
and when the first pre-judgment result exists in the preset first diagnosis condition and/or when the second pre-judgment result exists in the preset second diagnosis condition, determining that the target patient is an abnormal diagnosis.
In this embodiment, it may be identified whether the disease type of the target patient is abnormal in the treatment process, and then identify whether the medication type of the target patient is abnormal in the treatment process; or whether the medication type of the target patient is abnormal in the treatment process can be identified firstly, and then whether the disease type of the target patient is abnormal in the treatment process can be identified; the diagnosis abnormity identification can be carried out according to the disease type and the medicine type of the target patient in the diagnosis process, and the diversity of diagnosis abnormity identification is improved.
In summary, in the identification method for abnormal medical visits described in this embodiment, on one hand, according to the participation information and the medical visit data of the target patient, first data and second data of the target patient are determined, where the first data includes a first crowd category and disease data, and the second data includes a second crowd category and medicine data, and the first crowd category, the disease type, the second crowd category and the medicine type of the patient are determined according to the participation information and the medical visit data of the patient, and in a subsequent identification process of abnormal medical visits, the crowd category, the disease type and the medicine type are combined, and the consideration is performed from multiple dimensions, so as to improve the accuracy of identification results in the subsequent identification process of abnormal medical visits; on the other hand, the first crowd type and the disease data of the target patient are input into a pre-trained disease type prediction model, a first pre-judgment result is output, the second crowd type and the medicine data are input into a pre-trained medicine type prediction model, a second pre-judgment result is output, and whether the target patient belongs to an abnormal doctor or not is verified from two dimensions by combining the crowd type of the target patient, so that the accuracy of the recognition result of the abnormal doctor is improved; and finally, when the second pre-judgment result exists in the preset second diagnosis condition, determining that the target patient is in abnormal diagnosis, sending alarm information to the target patient after determining that the target patient is in abnormal diagnosis, informing the target patient that the medical insurance card cannot be used for diagnosis, and sending abnormal information of the abnormal diagnosis to a doctor of the target patient to remind the doctor of determining whether the prescription is correct, so that errors in the diagnosis process are reduced, and the safety of the diagnosis is improved.
Example two
Fig. 2 is a structural diagram of an apparatus for identifying an abnormal medical examination according to a second embodiment of the present invention.
In some embodiments, the identification device 20 for abnormal diagnosis may include a plurality of functional modules composed of program code segments. The program code of each program segment in the abnormal diagnosis recognition apparatus 20 may be stored in a memory of the electronic device and executed by the at least one processor to perform the function of recognizing the abnormal diagnosis (described in detail in fig. 1).
In this embodiment, the recognition device 20 for the abnormal medical treatment may be divided into a plurality of functional modules according to the functions performed by the recognition device. The functional module may include: the system comprises a parsing module 201, a first determining module 202, a first input module 203, a first identifying module 204, a second input module 205, a second identifying module 206 and a second determining module 207. The module referred to herein is a series of computer program segments capable of being executed by at least one processor and capable of performing a fixed function and is stored in memory. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.
The analysis module 201 is configured to analyze the visit request of the target patient to obtain the participation insurance information and the visit data of the target patient.
In this embodiment, the visit request is sent from the electronic device to the server, and is used to request a visit, specifically, the visit request may be sent from the target patient to the server through the electronic device during the visit process, for example, the target patient may log in to a medical institution through the electronic device, such as a visit subsystem in a hospital medical system, and send a visit request to the medical system server in the visit subsystem.
In this embodiment, the visit request carries referral information and visit data of the target patient, specifically, the referral information includes an identification number, a contact information, a social security number and other information that can confirm the identity of the target patient, and the visit data includes disease data, medicine data and other data.
In an alternative embodiment, the parsing module 201 for parsing the visit request of the target patient to obtain the participation information and the visit data of the target patient includes:
analyzing the message of the visit request of the target patient to obtain message information carried by the message;
acquiring the identification code of the target patient from the message information;
determining an interface of the participation information and an interface of the visit data according to the identification code of the target patient;
calling the interface of the participation information to acquire the participation information of the target patient, and calling the interface of the visit data to acquire the visit data of the target patient.
In this embodiment, the identification code of the target patient may be a social security number of the target patient, or may also be an identification number of the target patient or a mobile phone number of the target patient.
In this embodiment, in order to ensure the correctness of the participation information and the visit data, the participation information and the visit data are simultaneously acquired from the corresponding interfaces, so that the acquisition efficiency of the participation information and the visit data is improved.
A first determining module 202, configured to determine first data and second data of the target patient according to the participation information and the visit data of the target patient, where the first data includes a first crowd category and disease data, and the second data includes a second crowd category and medicine data.
In this embodiment, since the information of participation in insurance and the data of visiting doctor include different types of data, the information of participation in insurance and the data of visiting doctor of the target patient are classified to determine the first data and the second data of the target patient.
In an alternative embodiment, the first determining module 202 determines the first data and the second data of the target patient according to the participation information and the visit data of the target patient comprises:
identifying the participation information of the target patient, and determining the age and the sex of the target patient;
determining a first crowd category and a second crowd category which are matched with the age and the gender of the target patient from a preset crowd category library;
extracting key information from the visit data, and converting the key information according to a preset format conversion rule to obtain converted key information;
dividing the converted key information into disease data and medicine data according to a preset dividing rule;
determining the first population category and disease data as first data for the target patient and determining the second population category and drug data as second data for the target patient.
Specifically, the first group of people is classified based on age and gender, and the group of people is classified into three types according to age: children, young adults and elderly, wherein children are < 14 years old and elderly > 60 years old; the population is divided into two categories according to gender: male and female.
The second crowd category is divided based on age and gender, and the crowd is divided into two categories according to age: children and adults, wherein children are < 14 years old; the population is divided into two categories according to gender: male and female.
In other alternative embodiments, the first population category and the second population category may also classify women into both pregnant and non-pregnant categories.
In this embodiment, a format conversion rule and a partition rule may be preset, where the preset format conversion rule may be set according to a medical general format, and the partition rule may be preset according to a disease attribute and a drug attribute, for example, when the key information is cough, the cough is partitioned into disease data; the key information is amoxicillin, and the amoxicillin is classified into medicine data.
In other alternative embodiments, the disease data may include one or more and the drug data may include one or more.
In this embodiment, the first crowd type, the disease type, the second crowd type and the medicine type of the patient are determined according to the participation information and the visit data of the patient, and in the subsequent abnormal visit identification process, the crowd type, the disease type and the medicine type are combined, and the consideration is performed from multiple dimensions, so that the accuracy of the identification result in the subsequent abnormal visit identification process is improved.
The first input module 203 is configured to input the first population category and the disease data of the target patient into a pre-trained disease type prediction model, and output a first pre-judgment result.
In this embodiment, after the first population category and the disease data of the target patient are determined, the first population category and the disease data of the target patient are input into a pre-trained disease type model to obtain a disease type of the target patient, the disease type and the first population category of the target patient are determined as a first predetermined result, and the first predetermined result output by the disease type prediction model is received.
Specifically, the training process of the disease type prediction model comprises the following steps:
obtaining a plurality of patients corresponding to each first group category;
extracting a plurality of disease data and corresponding disease types of each patient to form a data set;
randomly dividing the data set into a first number of training sets and a second number of test sets;
inputting a plurality of disease data in the training set and corresponding disease types into a preset convolutional neural network for training to obtain a disease type prediction model;
inputting the test set into the disease type prediction model for testing to obtain a test passing rate;
judging whether the test passing rate is greater than a preset passing rate threshold value or not;
when the test passing rate is greater than or equal to the preset passing rate threshold value, finishing the training of the disease type prediction model; or when the test passing rate is smaller than the preset passing rate threshold, increasing the number of the training sets, and re-training the disease type prediction model.
In this embodiment, the first pre-judging result is used to characterize the disease type of the target patient, and the first population category and the disease type of the target patient are determined as the first pre-judging result of the target patient.
In particular, the disease types may include, but are not limited to, one or more combinations of the following: common diseases of women; common diseases in men; common diseases of children; common diseases in young people; common diseases of the elderly.
In this embodiment, for a plurality of first population categories, a data set may be constructed by obtaining a plurality of patients in each first population category, and a plurality of disease data and corresponding disease types for each patient. And in the subsequent service process, taking the plurality of disease data of the target patient and the corresponding disease types as new data so as to increase the number of the data sets, and retraining the disease type prediction model based on the new data sets. Namely, the disease type prediction model is continuously updated, so that the accuracy of disease type prediction is continuously improved.
The first identifying module 204 is configured to identify whether a preset first medical condition has the first predetermined result.
In this embodiment, first medical treatment conditions may be preset, and specifically, the preset first medical treatment conditions include one or more of the following combinations:
the disease type is a common female disease, and the target patient is a male; the disease type is a common disease in males, and the target patient is a female; the disease type is common diseases of the elderly, and the target patient is young; the disease type is common in young people, and the target patient is the old; the disease type is childhood disease, and the target patient is an adult; the disease type is common in young people and the target patient is children.
In other optional embodiments, the disease type of the preset first visit condition is a common disease of the pregnant woman, and the patient is not the pregnant woman.
In an optional embodiment, the identifying, by the first identifying module 204, whether the first predetermined result exists in the preset first medical condition includes:
matching the first pre-judgment result with the preset first medical condition;
when a first diagnosis condition matched with the first pre-judgment result is matched in the preset first diagnosis conditions, determining that the first pre-judgment result exists in the preset first diagnosis conditions; or
And when the first diagnosis condition matched with the first pre-judgment result is not matched in the preset first diagnosis conditions, determining that the first pre-judgment result does not exist in the preset first diagnosis conditions.
In this embodiment, the disease type and the first population category of the target patient are matched with the preset first diagnosis condition, whether the target patient is an abnormal diagnosis is preliminarily determined according to the matching result, the disease data does not need to be specifically analyzed, the prediction result of the abnormal diagnosis is directly obtained, and the recognition efficiency of the abnormal diagnosis prediction is improved.
A second input module 205, configured to, when the first pre-determination result does not exist in the preset first visit condition, input the second population category and the drug data into a pre-trained drug type prediction model, and output a second pre-determination result.
In this embodiment, the drug type prediction module may be trained in advance, and specifically, the training process of the drug type prediction model is the same as the training process of the disease type prediction model, which is not described in detail herein.
In this embodiment, after the second population category and the drug data are obtained, the second population category and the drug data are input into the drug type prediction model, so as to obtain the drug type of the medication for the target patient.
In particular, the drug type may include, but is not limited to, one or more of the following: children's drugs, women's drugs, men's drugs.
Further, when the first pre-judgment result exists in the preset first diagnosis condition, the target patient is determined to be an abnormal diagnosis.
In this embodiment, for a plurality of second population categories, a data set may be constructed by obtaining a plurality of patients in each second population category, and a plurality of drug data and corresponding drug types for each patient. And in the subsequent service process, taking the plurality of drug data of the target patient and the corresponding drug types as new data so as to increase the number of the data sets, and retraining the drug type prediction model based on the new data sets. Namely, the medicine type prediction model is continuously updated, so that the accuracy of medicine type prediction is continuously improved.
And the second identification module 206 is configured to identify whether a preset second medical condition has the second predetermined result.
In this embodiment, the second predetermined result is used to characterize the drug type of the target patient, and the second population category and the drug type of the target patient are determined as the second predetermined result of the target patient.
Specifically, the preset second visit condition includes one or more of the following combinations:
the type of the medicine is forbidden for children, and the target patient is children; the medicine type is pediatric, and the target patient is an adult; the drug type is female medication and the target patient is male; the drug type is male medication and the target patient is female.
In some other optional embodiments, the type of the predetermined second visit condition is prohibited for the pregnant woman, and the target patient is the pregnant woman.
In an optional embodiment, the identifying, by the second identifying module 206, whether the second predetermined result exists in the preset second visit condition includes:
matching the second pre-judgment result with the preset second visit condition;
when a second diagnosis condition matched with the second pre-judgment result is matched in the preset second diagnosis conditions, determining that the second pre-judgment result exists in the preset second diagnosis conditions; or
And when the second diagnosis condition matched with the second pre-judgment result is not matched in the preset second diagnosis conditions, determining that the second pre-judgment result does not exist in the preset second diagnosis conditions.
In this embodiment, when it is determined that there is no abnormality in the disease treatment of the target patient, whether there is an abnormality in the drug treatment of the target patient is continuously identified, and by matching the second predetermined result with the preset second treatment condition, whether there is an abnormality in the drug treatment of the target patient is determined according to the matching result, and by combining the population category of the target patient, whether the target patient belongs to the abnormal treatment is verified from two dimensions, so that the accuracy of the identification result of the abnormal treatment is improved.
A second determining module 207, configured to determine that the target patient is an abnormal diagnosis when the second predetermined result exists in the preset second diagnosis condition.
In this embodiment, the abnormal medical visit is used to indicate whether the target patient borrows a medical insurance card of another person during the medical visit, and may also be used to indicate that a disease description error or a medication abnormality exists in a medical prescription prescribed by a doctor.
Further, when the target patient is determined to be an abnormal diagnosis, the diagnosis is ended, and the alarm information is sent to the target patient according to a preset sending mode and the abnormal information corresponding to the abnormal diagnosis is sent to the doctor who visits the target patient.
Further, when the second predetermined result does not exist in the preset second medical treatment condition, the target patient is determined to be a normal medical treatment, and the medical treatment is continuously performed.
In this embodiment, when it is determined that the target patient is an abnormal medical treatment, the target patient is sent with alarm information to inform that the target patient cannot use the medical insurance card for medical treatment, and the abnormal information of the abnormal medical treatment is sent to the doctor of the target patient to remind the doctor of determining whether the prescribed prescription is correct, so that errors in the medical treatment process are reduced, and the safety of the medical treatment is improved.
In some alternative embodiments, the method comprises:
analyzing a visit request of a target patient to acquire participation information and visit data of the target patient;
determining first data and second data of the target patient according to the participation information and the visit data of the target patient, wherein the first data comprises a first crowd category and disease data, and the second data comprises a second crowd category and medicine data;
inputting the second crowd category and the medicine data into a pre-trained medicine type prediction model, and outputting a second pre-judgment result;
identifying whether a second pre-judgment result exists in a preset second diagnosis condition or not;
when the second pre-judgment result does not exist in the preset second diagnosis condition, inputting the first population category and the disease data of the target patient into a pre-trained disease type prediction model, and outputting a first pre-judgment result;
identifying whether a first pre-judgment result exists in a preset first diagnosis condition or not;
and when the first pre-judgment result exists in the preset first diagnosis condition, determining that the target patient is an abnormal diagnosis.
In some alternative embodiments, the method comprises:
analyzing a visit request of a target patient to acquire participation information and visit data of the target patient;
determining first data and second data of the target patient according to the participation information and the visit data of the target patient, wherein the first data comprises a first crowd category and disease data, and the second data comprises a second crowd category and medicine data;
inputting the first population category and the disease data of the target patient into a pre-trained disease type prediction model, outputting a first pre-judgment result, inputting the second population category and the drug data into a pre-trained drug type prediction model, and outputting a second pre-judgment result;
identifying whether a first pre-judgment result exists in a preset first diagnosis condition or not, and identifying whether a second pre-judgment result exists in a preset second diagnosis condition or not;
and when the first pre-judgment result exists in the preset first diagnosis condition and/or when the second pre-judgment result exists in the preset second diagnosis condition, determining that the target patient is an abnormal diagnosis.
In this embodiment, it may be identified whether the disease type of the target patient is abnormal in the treatment process, and then identify whether the medication type of the target patient is abnormal in the treatment process; or whether the medication type of the target patient is abnormal in the treatment process can be identified firstly, and then whether the disease type of the target patient is abnormal in the treatment process can be identified; the diagnosis abnormity identification can be carried out according to the disease type and the medicine type of the target patient in the diagnosis process, and the diversity of diagnosis abnormity identification is improved.
In summary, in the identification apparatus for abnormal medical visits described in this embodiment, on one hand, according to the participation information and the medical visit data of the target patient, first data and second data of the target patient are determined, where the first data includes a first crowd category and disease data, and the second data includes a second crowd category and medicine data, and the first crowd category, the disease type, the second crowd category and the medicine type of the patient are determined according to the participation information and the medical visit data of the patient, and in a subsequent identification process of abnormal medical visits, the crowd category, the disease type and the medicine type are combined, and the consideration is performed from multiple dimensions, so as to improve the accuracy of an identification result in the subsequent identification process of abnormal medical visits; on the other hand, the first crowd type and the disease data of the target patient are input into a pre-trained disease type prediction model, a first pre-judgment result is output, the second crowd type and the medicine data are input into a pre-trained medicine type prediction model, a second pre-judgment result is output, and whether the target patient belongs to an abnormal doctor or not is verified from two dimensions by combining the crowd type of the target patient, so that the accuracy of the recognition result of the abnormal doctor is improved; and finally, when the second pre-judgment result exists in the preset second diagnosis condition, determining that the target patient is in abnormal diagnosis, sending alarm information to the target patient after determining that the target patient is in abnormal diagnosis, informing the target patient that the medical insurance card cannot be used for diagnosis, and sending abnormal information of the abnormal diagnosis to a doctor of the target patient to remind the doctor of determining whether the prescription is correct, so that errors in the diagnosis process are reduced, and the safety of the diagnosis is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. In the preferred embodiment of the present invention, the electronic device 3 comprises a memory 31, at least one processor 32, at least one communication bus 33 and a transceiver 34.
It will be appreciated by those skilled in the art that the configuration of the electronic device shown in fig. 3 does not constitute a limitation of the embodiment of the present invention, and may be a bus-type configuration or a star-type configuration, and the electronic device 3 may include more or less other hardware or software than those shown, or a different arrangement of components.
In some embodiments, the electronic device 3 is an electronic device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The electronic device 3 may also include a client device, which includes, but is not limited to, any electronic product that can interact with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, and the like.
It should be noted that the electronic device 3 is only an example, and other existing or future electronic products, such as those that can be adapted to the present invention, should also be included in the scope of the present invention, and are included herein by reference.
In some embodiments, the memory 31 is used for storing program codes and various data, such as the identification device 20 for abnormal medical visits installed in the electronic equipment 3, and realizes high-speed and automatic access to programs or data during the operation of the electronic equipment 3. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.
In some embodiments, the at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The at least one processor 32 is a Control Unit (Control Unit) of the electronic device 3, connects various components of the electronic device 3 by using various interfaces and lines, and executes various functions and processes data of the electronic device 3 by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31.
In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.
Although not shown, the electronic device 3 may further include a power supply (such as a battery) for supplying power to each component, and optionally, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, an electronic device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present invention.
In a further embodiment, in conjunction with fig. 2, the at least one processor 32 may execute operating means of the electronic device 3 and various installed applications (such as the identification means 20 for abnormal medical visits), program code, etc., such as the respective modules described above.
The memory 31 has program code stored therein, and the at least one processor 32 can call the program code stored in the memory 31 to perform related functions. For example, the various modules illustrated in fig. 2 are program code stored in the memory 31 and executed by the at least one processor 32 to implement the functions of the various modules for the purpose of identifying an abnormal medical visit.
Illustratively, the program code may be divided into one or more modules, which are stored in the memory 31 and executed by the processor 32 to perform the method. The one or more modules may be a series of computer-readable instruction segments capable of performing certain functions, which are used to describe the execution of the computer-readable instructions in the computer device 3. For example, the program code may be divided into a parsing module 201, a first determining module 202, a first input module 203, a first identifying module 204, a second input module 205, a second identifying module 206, and a second determining module 207 in fig. 2, and specific functions of each module are described in embodiment two.
In one embodiment of the present invention, the memory 31 stores a plurality of instructions that are executed by the at least one processor 32 to perform the function of identifying an abnormal encounter.
Specifically, the at least one processor 32 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, and details are not repeated here.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the present invention may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A method of identifying an abnormal encounter, the method comprising:
analyzing a visit request of a target patient to acquire participation information and visit data of the target patient;
determining first data and second data of the target patient according to the participation information and the visit data of the target patient, wherein the first data comprises a first crowd category and disease data, and the second data comprises a second crowd category and medicine data;
inputting the first population category and the disease data of the target patient into a pre-trained disease type prediction model, and outputting a first pre-judgment result;
identifying whether a first pre-judgment result exists in a preset first diagnosis condition or not;
when the first pre-judgment result does not exist in the preset first visit condition, inputting the second population category and the drug data into a pre-trained drug type prediction model, and outputting a second pre-judgment result;
identifying whether a second pre-judgment result exists in a preset second diagnosis condition or not;
and when the second pre-judgment result exists in the preset second diagnosis condition, determining that the target patient is an abnormal diagnosis.
2. The method for identifying an abnormal medical visit of claim 1, wherein the determining the first data and the second data of the target patient based on the participation information and the visit data of the target patient comprises:
identifying the participation information of the target patient, and determining the age and the sex of the target patient;
determining a first crowd category and a second crowd category which are matched with the age and the gender of the target patient from a preset crowd category library;
extracting key information from the visit data, and converting the key information according to a preset format conversion rule to obtain converted key information;
dividing the converted key information into disease data and medicine data according to a preset dividing rule;
determining the first population category and disease data as first data for the target patient and determining the second population category and drug data as second data for the target patient.
3. The method of identifying an abnormal medical visit as claimed in claim 1, wherein the training process of the disease type prediction model comprises:
obtaining a plurality of patients corresponding to each first group category;
extracting a plurality of disease data and corresponding disease types of each patient to form a data set;
randomly dividing the data set into a first number of training sets and a second number of test sets;
inputting a plurality of disease data in the training set and corresponding disease types into a preset convolutional neural network for training to obtain a disease type prediction model;
inputting the test set into the disease type prediction model for testing to obtain a test passing rate;
judging whether the test passing rate is greater than a preset passing rate threshold value or not;
when the test passing rate is greater than or equal to the preset passing rate threshold value, finishing the training of the disease type prediction model; or when the test passing rate is smaller than the preset passing rate threshold, increasing the number of the training sets, and re-training the disease type prediction model.
4. The method for identifying an abnormal medical visit as claimed in claim 1, wherein the preset first medical visit condition comprises one or more of the following combinations:
the disease type is a common female disease, and the target patient is a male;
the disease type is a common disease in males, and the target patient is a female;
the disease type is common diseases of the elderly, and the target patient is young;
the disease type is common in young people, and the target patient is the old;
the disease type is childhood disease, and the target patient is an adult;
the disease type is common in young people and the target patient is children.
5. The method for identifying an abnormal medical visit as claimed in claim 1, wherein the preset second medical visit condition comprises one or more of the following combinations:
the type of the medicine is forbidden for children, and the target patient is children;
the medicine type is pediatric, and the target patient is an adult;
the drug type is female medication and the target patient is male;
the drug type is male medication and the target patient is female.
6. The method for identifying an abnormal medical examination as claimed in claim 1, wherein the identifying whether the preset first medical examination condition exists or not comprises:
matching the first pre-judgment result with the preset first medical condition;
when a first diagnosis condition matched with the first pre-judgment result is matched in the preset first diagnosis conditions, determining that the first pre-judgment result exists in the preset first diagnosis conditions; or
And when the first diagnosis condition matched with the first pre-judgment result is not matched in the preset first diagnosis conditions, determining that the first pre-judgment result does not exist in the preset first diagnosis conditions.
7. The method for identifying an abnormal medical visit as claimed in claim 1, wherein the parsing the visit request of the target patient to obtain the participation information and the visit data of the target patient comprises:
analyzing the message of the visit request of the target patient to obtain message information carried by the message;
acquiring the identification code of the target patient from the message information;
determining an interface of the participation information and an interface of the visit data according to the identification code of the target patient;
calling the interface of the participation information to acquire the participation information of the target patient, and calling the interface of the visit data to acquire the visit data of the target patient.
8. An apparatus for identifying an abnormal medical visit, the apparatus comprising:
the analysis module is used for analyzing the visit request of the target patient to acquire the participation insurance information and the visit data of the target patient;
the first determination module is used for determining first data and second data of the target patient according to the participation information and the visit data of the target patient, wherein the first data comprises a first crowd category and disease data, and the second data comprises a second crowd category and medicine data;
the first input module is used for inputting the first crowd category and the disease data of the target patient into a pre-trained disease type prediction model and outputting a first pre-judgment result;
the first identification module is used for identifying whether a first pre-judgment result exists in a preset first diagnosis condition or not;
the second input module is used for inputting the second crowd type and the medicine data into a pre-trained medicine type prediction model and outputting a second pre-judgment result when the first pre-judgment result does not exist in the preset first diagnosis condition;
the second identification module is used for identifying whether a second pre-judgment result exists in a preset second diagnosis condition or not;
and the second determination module is used for determining that the target patient is an abnormal diagnosis when the second pre-judgment result exists in the preset second diagnosis condition.
9. An electronic device, characterized in that the electronic device comprises a processor and a memory, the processor being configured to implement the method for identifying an abnormal medical visit according to any one of claims 1 to 7 when executing a computer program stored in the memory.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the method for identifying an abnormal medical visit according to any one of claims 1 to 7.
CN202110633650.XA 2021-06-07 2021-06-07 Abnormal diagnosis recognition method and device, electronic equipment and storage medium Pending CN113284614A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110633650.XA CN113284614A (en) 2021-06-07 2021-06-07 Abnormal diagnosis recognition method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110633650.XA CN113284614A (en) 2021-06-07 2021-06-07 Abnormal diagnosis recognition method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113284614A true CN113284614A (en) 2021-08-20

Family

ID=77283725

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110633650.XA Pending CN113284614A (en) 2021-06-07 2021-06-07 Abnormal diagnosis recognition method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113284614A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109636641A (en) * 2018-12-13 2019-04-16 平安医疗健康管理股份有限公司 Medical insurance method for detecting abnormality, device, equipment and medium based on big data analysis
CN109685670A (en) * 2018-12-13 2019-04-26 平安医疗健康管理股份有限公司 Social security violation detection method, device, equipment and computer readable storage medium
CN111783871A (en) * 2020-06-29 2020-10-16 平安医疗健康管理股份有限公司 Abnormal data identification method based on supervised learning model and related equipment
CN111785384A (en) * 2020-06-29 2020-10-16 平安医疗健康管理股份有限公司 Abnormal data identification method based on artificial intelligence and related equipment
CN112435745A (en) * 2020-12-18 2021-03-02 深圳赛安特技术服务有限公司 Consultation strategy recommendation method and device, electronic equipment and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109636641A (en) * 2018-12-13 2019-04-16 平安医疗健康管理股份有限公司 Medical insurance method for detecting abnormality, device, equipment and medium based on big data analysis
CN109685670A (en) * 2018-12-13 2019-04-26 平安医疗健康管理股份有限公司 Social security violation detection method, device, equipment and computer readable storage medium
CN111783871A (en) * 2020-06-29 2020-10-16 平安医疗健康管理股份有限公司 Abnormal data identification method based on supervised learning model and related equipment
CN111785384A (en) * 2020-06-29 2020-10-16 平安医疗健康管理股份有限公司 Abnormal data identification method based on artificial intelligence and related equipment
CN112435745A (en) * 2020-12-18 2021-03-02 深圳赛安特技术服务有限公司 Consultation strategy recommendation method and device, electronic equipment and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈清凤等: "大数据下医保欺诈的有效识别模型", 《汕头大学学报(自然科学版)》 *

Similar Documents

Publication Publication Date Title
CN112700838B (en) Big data-based medication scheme recommendation method and device and related equipment
CA2897897C (en) Medical database and system
CN112216361A (en) Follow-up plan list generation method, device, terminal and medium based on artificial intelligence
CN111986744B (en) Patient interface generation method and device for medical institution, electronic equipment and medium
CN112614578B (en) Doctor intelligent recommendation method and device, electronic equipment and storage medium
CN112214613A (en) Artificial intelligence-based medication recommendation method and device, electronic equipment and medium
US20180210925A1 (en) Reliability measurement in data analysis of altered data sets
CA2952079A1 (en) Method and system for intelligent completion of medical record based on big data analytics
CN113674858A (en) Online medical prescription medication intelligent checking method, device, equipment and storage medium
CN109255721A (en) Insurance recommended method, equipment, server and readable medium based on Cost Forecast
CN112582071A (en) Healthcare network
CN111696663A (en) Disease risk analysis method and device, electronic equipment and computer storage medium
CN112634889A (en) Electronic case logging method, device, terminal and medium based on artificial intelligence
CN116524995A (en) Medicine curative effect prediction method based on artificial intelligence and related equipment
CN114220541A (en) Disease prediction method, disease prediction device, electronic device, and storage medium
CN111933246B (en) Medical prescription analysis method, system, electronic device and storage medium
JP7044113B2 (en) Presentation method, presentation system, and program
CN112530602A (en) Method and device for analyzing side effect of medicine, electronic equipment and computer storage medium
CN115831298A (en) Clinical trial patient recruitment method and device based on hospital management information system
CN113593722B (en) System and method for patient pre-established medical care plan communication
CN113284614A (en) Abnormal diagnosis recognition method and device, electronic equipment and storage medium
CN113724891A (en) Hospital epidemic situation monitoring method, device and related equipment
Joseph et al. A rules based algorithm to generate problem lists using emergency department medication reconciliation
CN111400759A (en) Visiting time table generation method and device, storage medium and electronic equipment
CN117809841B (en) Skin special patient management method and system based on large model technology

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
TA01 Transfer of patent application right

Effective date of registration: 20220919

Address after: Room 2601 (Unit 07), Qianhai Free Trade Building, No. 3048, Xinghai Avenue, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong 518000

Applicant after: Shenzhen Ping An Smart Healthcare Technology Co.,Ltd.

Address before: 1-34 / F, Qianhai free trade building, 3048 Xinghai Avenue, Mawan, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000

Applicant before: Ping An International Smart City Technology Co.,Ltd.

TA01 Transfer of patent application right
RJ01 Rejection of invention patent application after publication

Application publication date: 20210820

RJ01 Rejection of invention patent application after publication