CN112635011A - Disease diagnosis method, disease diagnosis system, and readable storage medium - Google Patents
Disease diagnosis method, disease diagnosis system, and readable storage medium Download PDFInfo
- Publication number
- CN112635011A CN112635011A CN202011637337.5A CN202011637337A CN112635011A CN 112635011 A CN112635011 A CN 112635011A CN 202011637337 A CN202011637337 A CN 202011637337A CN 112635011 A CN112635011 A CN 112635011A
- Authority
- CN
- China
- Prior art keywords
- disease
- information
- patient
- diagnosis
- data set
- 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
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
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- 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
-
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Embodiments of the present invention provide a disease diagnosis method, a disease diagnosis system, and a readable storage medium. Wherein the disease diagnosis method comprises the following steps: acquiring medical record information of a patient and chief complaint information of the patient; constructing patient portrait information according to medical record information and chief complaint information; determining a disease diagnosis result of the patient according to the patient image information; patient portrait information is constructed according to medical record information of a patient and chief complaint information of the patient, so that disease information of the patient is structured, clear and labeled, a doctor can conveniently and rapidly position personal information of the patient, and diagnosis efficiency and diagnosis accuracy of the doctor are improved. According to the disease diagnosis result, a disease knowledge map is constructed, a disease treatment method is automatically recommended, disease-related symptoms are displayed, a disease diagnosis knowledge card, a knowledge card of similar diseases and an identification treatment method are automatically recommended, the diagnosis efficiency is improved, the labor cost is reduced, and the condition that the patient is affected by manual misdiagnosis and timely hospitalization is avoided.
Description
Technical Field
The present invention relates to the field of computers, and in particular, to a disease diagnosis method, a disease diagnosis system, and a readable storage medium.
Background
Neurodegenerative diseases refer to nervous system degenerative diseases caused by neuron degeneration and apoptosis, mainly include two types of dyskinesia and cognitive disorder, specifically diseases such as Parkinson's disease, progressive supranuclear palsy, corticobasal degeneration, frontotemporal dementia, Parkinson's syndrome and other diagnosis and typing. The diseases are mostly caused by hidden attacks, the disease course is slow, the clinical manifestations of all disease types are similar, the diseases cannot be distinguished through conventional clinical examination and examination means, and clinicians with abundant experience often need to comprehensively judge according to the information of the patient's medical history, clinical symptoms, physical signs and the like.
However, the diagnosis is performed only by the clinician, on one hand, the diagnosis efficiency is low, and on the other hand, the diagnosis result of the clinician is only used as the final diagnosis result of the patient, so that the diagnosis accuracy cannot be guaranteed, and if misdiagnosis occurs, the patient can be affected to see the diagnosis in time.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art or the related art.
To this end, a first aspect of embodiments of the present invention is to propose a disease diagnosis method.
A second aspect of embodiments of the present invention is to provide a disease diagnosis system.
A third aspect of embodiments of the present invention is to provide a readable storage medium.
In view of this, according to a first aspect of embodiments of the present invention, there is provided a disease diagnosis method including: acquiring medical record information of a patient and chief complaint information of the patient; constructing patient portrait information according to medical record information and chief complaint information; a disease diagnosis of the patient is determined based on the patient image information, wherein the patient image information includes at least one condition tab page including condition information of the patient.
According to the disease diagnosis method provided by the embodiment of the invention, the patient portrait information is constructed according to the medical record information of the patient and the chief complaint information of the patient, and the disease information of the patient is displayed on the patient portrait in the form of the label page. On the other hand, the server extracts the disease information of the patient from the portrait information of the patient, realizes automatic diagnosis of the patient and outputs a disease diagnosis result, so that the diagnosis efficiency is improved, the labor cost is reduced, and the influence of manual misdiagnosis on timely hospitalization of the patient can be avoided. Furthermore, the doctor can also carry out comprehensive diagnosis by combining the disease diagnosis result output by the server and the personal information of the patient, so that the diagnosis efficiency of the doctor can be improved, and the doctor can also carry out recheck in time when the diagnosis result of the doctor is inconsistent with the diagnosis result of the server, thereby improving the accuracy of the comprehensive diagnosis result and avoiding the influence on the diagnosis time of the patient due to misdiagnosis.
In addition, the disease diagnosis method according to the above-mentioned aspect of the present invention may further include the following additional features:
in the above technical solution, the disease diagnosis method further comprises: and constructing disease knowledge map information according to the disease diagnosis result, wherein the disease knowledge map information comprises one or more of disease knowledge information, disease symptom information, disease treatment information and medicine information.
In the technical scheme, the disease knowledge map information is constructed through the disease diagnosis result, so that a doctor can be assisted to quickly know the basic knowledge of the disease, and medicine information required by different diseases, treatment method information corresponding to the disease and symptom information corresponding to the disease are quickly positioned, and a more targeted treatment scheme is provided for a patient. Furthermore, the medical doctor can be helped to know the disease information of the related disease species of the same type of disease as the disease of the patient, for example, the definition of the related disease and the symptom information of the related disease, so that different disease species can be effectively, quickly and accurately discriminated, and the diagnosis efficiency and the diagnosis accuracy are improved. Specifically, the disease knowledge information, disease symptom information, disease treatment information, and drug information are presented in the form of a knowledge card. Further, the disease diagnosis method provided by the embodiment of the invention constructs the disease knowledge map according to the disease diagnosis result, and achieves the purposes of automatically recommending a disease treatment method, displaying disease-related symptoms, diagnosing a disease knowledge card, a knowledge card of similar diseases and identifying the treatment method.
In any of the above technical solutions, the step of constructing the disease knowledge map information according to the disease diagnosis result specifically includes: determining disease name information according to a disease diagnosis result; generating medicine map information of at least one medicine according to the disease name information; and/or generating disease profile information for at least one disease condition based on the disease name information; and/or generating treatment map information of at least one treatment means according to the disease name information; generating disease knowledge profile information from one or more of the drug profile information, the disorder profile information, and the therapy profile information.
According to the technical scheme, the disease name information is determined through the disease diagnosis result information, and one or more of medicine map information, disease state map information and treatment map information are generated according to the disease name information, so that the medicine knowledge map information is formed by one or more of the medicine map information, the disease state map information and the treatment map information, a doctor is assisted to quickly know basic knowledge of diseases, medicine information required by different diseases, treatment method information corresponding to the diseases and symptom information corresponding to the diseases are quickly positioned, and a more targeted treatment scheme is provided for a patient.
In any of the above technical solutions, the step of constructing the patient portrait according to the medical record information and the chief complaint information specifically includes: extracting disease keywords according to the medical record information and the chief complaint information; preprocessing the disease keywords to generate disease information; patient image information of the patient is generated based on the disease information.
In the technical scheme, the portrait information of the patient is constructed through the medical record information and the chief complaint information of the patient, so that the chief complaint information and the medical history information of the patient can be structured, clear and labeled, and a doctor can conveniently and rapidly position the personal information of the patient. Furthermore, disease keywords are extracted from case information and chief complaint information, and are preprocessed, so that the portrait information of the patient comprises all disease information of the patient, and the accuracy of a disease diagnosis result is greatly improved. Furthermore, by standardizing disease keywords, words related to diseases in case information and chief complaint information of patients can be unified and standardized, disease diagnosis can be conveniently carried out in the later period, and the accuracy of disease diagnosis results can be improved. Specifically, the step of preprocessing the condition keywords includes normalizing the condition keywords, for example, converting "headache" into "headache".
In any of the above aspects, before the step of determining a disease diagnosis result of the patient based on the patient image information, the disease diagnosis method further includes: acquiring disease information of at least two patients to generate a prediction model data set; extracting disease key words from the prediction model data set to generate a disease data set; grouping the disease data sets to generate a training data set and a prediction data set; extracting characteristic quantity of the training data set to generate a characteristic data set; and generating a first disease prediction model according to the training data set, the characteristic data set, the prediction data set and a preset rule.
According to the technical scheme, the disease information of at least two patients is acquired to generate prediction model data, the prediction model data is preprocessed and machine learning training is carried out, so that a first disease prediction model is generated, different disease information is extracted from the portrait information of the patients, automatic prediction of disease types is carried out, diagnosis by doctors is efficiently assisted, and diagnosis efficiency and diagnosis accuracy are improved. In the embodiment, the machine learning is trained by using sample data to generate the first disease prediction model, and technologies such as natural language processing, data mining, machine learning, deep learning and the like are combined, so that intelligent diagnosis and typing of neurodegenerative diseases are realized, and the diagnosis efficiency and the diagnosis accuracy are improved.
In any of the above technical solutions, the step of extracting a disease condition keyword from the prediction model data set to generate a disease condition data set specifically includes: extracting disease key words from the prediction model data set; preprocessing the disease keywords to generate disease standard words; and carrying out data normalization processing on the disease standard words to generate a disease data set.
According to the technical scheme, disease keywords are extracted from the prediction model data set and preprocessed, so that disease standard words are generated, the disease keywords are converted into the disease standard words, the disease of a patient is more standard, and the accuracy of a prediction result is improved when a disease is predicted. Further, data normalization processing is carried out through the disease standard words to generate a disease data set, so that measurement units of the disease data set are unified, training of a machine learning model can be carried out, and a disease prediction model is generated. Specifically, the step of preprocessing the condition keywords includes normalizing the condition keywords, for example, converting "headache" into "headache".
In any of the above technical solutions, the step of determining a disease diagnosis result of the patient based on the patient image information specifically includes: acquiring disease information of a patient according to the portrait information of the patient; the disease condition information is input into a first disease prediction model, and the first disease prediction model outputs a first disease diagnosis result, wherein the first disease diagnosis result comprises first disease name information, and the first disease diagnosis result further comprises at least one of first prediction accuracy, first recall rate and first prediction score.
According to the technical scheme, the disease information of the patient is acquired according to the portrait information of the patient, the disease information of the patient is input into the first disease prediction model, the first disease prediction model outputs the first disease name information and a prediction accuracy index for measuring the prediction accuracy of the first disease prediction model, so that a doctor can judge whether the first disease name information output by the first disease prediction model is used or not according to the prediction accuracy index, and the accuracy and the efficiency of a diagnosis result provided for the patient are improved. Specifically, the prediction accuracy indicator includes at least one of a first prediction accuracy, a first recall, a first prediction score. In one embodiment, an index may be used to measure the prognosis of the first disease prediction model to improve diagnostic efficiency. In another embodiment, multiple indices may also be used to scale the prediction of the first disease prediction model to provide accuracy of the diagnostic result.
In any of the above aspects, the step of determining a disease diagnosis result of the patient based on the patient image information includes: acquiring disease information of a patient according to the portrait information of the patient; and inputting the disease information into a second disease prediction model, and outputting a second disease diagnosis result by the second disease prediction model, wherein the second disease diagnosis result comprises second disease name information, and the second disease diagnosis result further comprises at least one of second prediction accuracy, second recall rate and second prediction score.
According to the technical scheme, the disease information of the patient is acquired according to the portrait information of the patient, the disease information of the patient is input into the second disease prediction model, the second disease prediction model outputs the name information of the second disease and a prediction accuracy index for measuring the prediction accuracy of the second disease prediction model, so that a doctor can judge whether the name information of the second disease output by the second disease prediction model is used or not according to the prediction accuracy index, and the accuracy and the efficiency of a diagnosis result provided for the patient are improved. Specifically, the prediction accuracy indicator includes at least one of a second prediction accuracy, a second recall, and a second prediction score.
In any of the above embodiments, the method for diagnosing a disease further comprises: acquiring disease information of a patient, and displaying the disease information on a disease label page.
According to the technical scheme, the disease information of the patient can be more comprehensive by acquiring the disease information of the patient and displaying the disease information on the disease label page, so that the accuracy of a disease diagnosis result is improved.
According to a second aspect of embodiments of the present invention, there is provided a disease diagnosis system including: a memory storing programs or instructions; a processor, wherein the processor executes the program or the instructions to implement the steps of the disease diagnosis method according to any one of the aspects of the first aspect.
The embodiment of the invention provides a disease diagnosis system, which comprises a memory and a processor. The steps of the disease diagnosis method in any one of the first aspect can be implemented when the processor executes the program or the instructions, so that all the beneficial technical effects of the disease diagnosis method provided in any one of the first aspect are achieved, and are not described herein again.
According to a third aspect of the embodiments of the present invention, there is provided a readable storage medium, on which a program or instructions are stored, which when executed by a processor, implement the steps of the disease diagnosis method provided in any one of the aspects of the first aspect.
The readable storage medium provided in the embodiments of the present invention can implement the steps of the disease diagnosis method provided in any one of the technical solutions of the first aspect, and therefore, all the beneficial technical effects of the disease diagnosis method provided in any one of the technical solutions of the first aspect are achieved, and are not described herein again.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 shows a flow diagram of a disease diagnosis method of one embodiment of the present invention;
FIG. 2 shows a flow chart of a disease diagnosis method of yet another embodiment of the present invention;
FIG. 3 shows a flow chart of a disease diagnosis method of yet another embodiment of the present invention;
FIG. 4 shows a flow chart of a disease diagnosis method of yet another embodiment of the present invention;
FIG. 5 shows a flow chart of a disease diagnosis method of yet another embodiment of the present invention;
FIG. 6 shows a flow chart of a disease diagnosis method of yet another embodiment of the present invention;
FIG. 7 shows a flow chart of a disease diagnosis method of yet another embodiment of the present invention;
FIG. 8 shows a flow chart of a disease diagnosis method of yet another embodiment of the present invention;
fig. 9 shows a block diagram of a disease diagnosis system of a further embodiment of the present invention.
Wherein, the corresponding relation between the reference signs and the component names is as follows:
900 disease diagnosis system, 902 memory, 904 processor.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
A disease diagnosis method, a disease diagnosis system, and a readable storage medium provided according to some embodiments of the present invention are described below with reference to fig. 1 to 9.
Example one
As shown in fig. 1, an embodiment provides a disease diagnosis method including:
102, acquiring medical record information of a patient and chief complaint information of the patient;
104, constructing patient portrait information according to medical record information and chief complaint information;
and step 106, determining a disease diagnosis result of the patient according to the patient image information, wherein the patient image information comprises at least one disease label page, and the disease label page comprises disease information of the patient.
According to the disease diagnosis method provided by the embodiment of the invention, the patient portrait information is constructed according to the medical record information of the patient and the chief complaint information of the patient, and the disease information of the patient is displayed on the patient portrait in the form of the label page. On the other hand, the server extracts the disease information of the patient from the portrait information of the patient, realizes automatic diagnosis of the patient and outputs a disease diagnosis result, so that the diagnosis efficiency is improved, the labor cost is reduced, and the influence of manual misdiagnosis on timely hospitalization of the patient can be avoided. Furthermore, the doctor can also carry out comprehensive diagnosis by combining the disease diagnosis result output by the server and the personal information of the patient, so that the diagnosis efficiency of the doctor can be improved, and the doctor can also carry out recheck in time when the diagnosis result of the doctor is inconsistent with the diagnosis result of the server, thereby improving the accuracy of the comprehensive diagnosis result and avoiding the influence on the diagnosis time of the patient due to misdiagnosis.
Example two
On the basis of the first embodiment, the second embodiment provides a disease diagnosis method, further defining that the disease diagnosis method further comprises: and constructing disease knowledge map information according to the disease diagnosis result, wherein the disease knowledge map information comprises one or more of disease knowledge information, disease symptom information, disease treatment information and medicine information.
In one embodiment, as shown in fig. 2, the disease diagnosis method comprises:
And 208, constructing disease knowledge graph information according to the disease diagnosis result, wherein the disease knowledge graph information comprises one or more of disease knowledge information, disease symptom information, disease treatment information and medicine information.
In the embodiment, the disease knowledge map information is constructed through the disease diagnosis result, so that a doctor can be assisted to quickly know the basic knowledge of the disease, and quickly locate the medicine information required by different diseases, the treatment method information corresponding to the disease and the symptom information corresponding to the disease, thereby providing a more targeted treatment scheme for a patient. Furthermore, the medical doctor can be helped to know the disease information of the related disease species of the same type of disease as the disease of the patient, for example, the definition of the related disease and the symptom information of the related disease, so that different disease species can be effectively, quickly and accurately discriminated, and the diagnosis efficiency and the diagnosis accuracy are improved. In one embodiment, the disease knowledge information, disease symptom information, disease treatment information, and drug information are presented in the form of a knowledge card. Further, the disease diagnosis method provided by the embodiment of the invention constructs the disease knowledge map according to the disease diagnosis result, and achieves the purposes of automatically recommending a disease treatment method, displaying disease-related symptoms, diagnosing a disease knowledge card, a knowledge card of similar diseases and identifying the treatment method.
In the embodiment, the construction of the patient image information is a disease information data source of a disease diagnosis result, the disease diagnosis result is a disease name information source of the disease knowledge map information, and the patient image information, the disease diagnosis result and the disease knowledge map information are matched with each other, so that on one hand, the diagnosis efficiency and the diagnosis accuracy can be improved, and on the other hand, reference suggestions can be given from basic disease knowledge, disease symptom information, basic disease knowledge and symptom information, a disease treatment method and a disease symptom-oriented medicine according to the diagnosis result, and the disease treatment efficiency, accuracy and effectiveness are improved.
In one embodiment, the disease knowledge information is obtained based on disease name information. The disease name information comprises disease names and ICD codes corresponding to diseases, and disease knowledge information is obtained through the disease name information, so that the obtained disease knowledge information is more comprehensive, a user can more comprehensively know the definition and symptom information of each disease, and each disease is effectively screened.
In one embodiment, the disease knowledge map information further comprises disease-related symptom information. The disease-related symptom information can use a TFIDF algorithm to rank and classify TFIDF values of different symptoms corresponding to different diseases, wherein the higher the TFIDF value of a disease corresponding to a symptom is, the greater the correlation between the symptom and the disease of the patient is, the higher the symptom ranked in the top 3 of the TFIDF value is, the higher the ranked in the 3-5 of the TFIDF value is, and the higher the ranked in the 5-10 of the TFIDF value is.
In one embodiment, the disease knowledge map information further comprises disease screening and surgical project information. And (3) carrying out data search by combining chemical examination items and physical examination items corresponding to the diseases with ICD codes corresponding to the diseases by using a form tower pattern matching algorithm, and matching the examination items of the diseases similar to the disease names by using the form tower pattern matching algorithm if the corresponding examination items of certain diseases cannot be inquired by the ICD codes corresponding to the diseases.
In one embodiment, the disease knowledge map information comprises disease drug information. The disease drug information uses the type of the disease ICD code as the information of the searched drug, and screens the first 50 related drugs as the information of the disease drug by using a sorting method.
In one embodiment, the disease knowledge map information further includes one or more of knowledge introduction information (such as clinical symptom information, ICD code information, disease type information, differential diagnosis information, and the like) corresponding to a disease, chemical examination item information of the disease, surgical mode information of the disease, list information of drugs for treating the disease, and information of high-degree, and very high-degree symptoms of the disease, and by setting the aforementioned information in the disease knowledge map information, a doctor can conveniently and rapidly make a treatment plan for a patient, and accuracy, effectiveness, and pertinence of the treatment plan are provided.
In the embodiment, the existing information of the electronic medical record of the patient and the chief complaint information of the patient are input into the server, so that the automatic prediction of the disease types is realized, the knowledge map information of different diseases is displayed in a visual and structured graph, the decision of a doctor is assisted, and the diagnosis efficiency and the diagnosis accuracy are greatly improved.
Further, in this embodiment, the step of constructing the disease knowledge map information according to the disease diagnosis result specifically includes: determining disease name information according to a disease diagnosis result; generating medicine map information of at least one medicine according to the disease name information; and/or generating disease profile information for at least one disease condition based on the disease name information; and/or generating treatment map information of at least one treatment means according to the disease name information; generating disease knowledge profile information from one or more of the drug profile information, the disorder profile information, and the therapy profile information. The disease name information is determined through the disease diagnosis result information, and one or more of medicine map information, disease state map information and treatment map information are generated according to the disease name information, so that the doctor is assisted to quickly know basic knowledge of the disease by forming one or more of the medicine map information, the disease state map information and the treatment map information into the disease knowledge map information, and medicine information, treatment method information corresponding to the disease and symptom information corresponding to the disease required by different diseases are quickly positioned, thereby providing a more targeted treatment scheme for the patient.
It should be noted that the medicine map information includes medicine knowledge map nodes and connection information. The disease state map information comprises disease state knowledge map nodes and connecting line information. The treatment map information includes treatment knowledge map nodes and link information.
In one embodiment, the step of generating drug map information of at least one drug according to the disease name information specifically includes: searching medicine information corresponding to the disease by combining the ICD corresponding to the disease and a format tower pattern matching algorithm; and screening out the medicine names, the medicine specifications, the national medicine standard word sizes and the manufacturers of the first 50 medicines according to the national medicine standard word sizes and the sequence, and generating medicine knowledge map nodes and connection information.
In one embodiment, the step of generating disease profile information for at least one disease condition based on the disease name information specifically comprises: searching symptom information according to the disease name and the corresponding ICD code; and sorting the symptom information according to the TFIDF value, and screening out symptoms with higher correlation to form disease knowledge graph nodes and connection information. Wherein, the higher the TFIDF value of a disease corresponding to a certain symptom, the greater the correlation between the symptom and the disease of the patient, the symptom with the TFIDF value ranking 3 is the very high correlation symptom, the higher correlation symptom with the TFIDF value ranking 3-5 is the high correlation symptom, and the high correlation symptom with the TFIDF value ranking 5-10 is the high correlation symptom.
In one embodiment, the step of generating treatment map information of at least one treatment means according to the disease name information specifically includes: searching relevant examination items, examination items and recommended operations of the diseases according to the disease names and the corresponding ICD codes; and creating related treatment knowledge map nodes and connection information according to the relation between the operation and the disease. The relationship between the operation and the disease includes indications, contraindications and the like.
In one embodiment, the correspondence of the structure is formed by the drug knowledge-graph nodes and link information, the disease knowledge-graph nodes and link information, and the treatment knowledge-graph nodes and link information.
In one embodiment, as shown in fig. 3, the step of constructing disease knowledge map information according to the disease diagnosis result specifically includes:
308, generating treatment map information of at least one treatment means according to the disease name information;
and step 310, generating disease knowledge graph information according to the medicine graph information, the disease graph information and the treatment graph information.
In one embodiment, as shown in fig. 4, the step of constructing disease knowledge map information according to the disease diagnosis result specifically includes:
EXAMPLE III
As shown in fig. 5, on the basis of any of the above embodiments, the third embodiment provides a disease diagnosis method, further defining the step of constructing a patient image according to medical record information and chief complaint information, and specifically including:
in step 506, patient image information of the patient is generated based on the disease information.
In the embodiment, the patient portrait information is constructed through the medical record information and the chief complaint information of the patient, so that the chief complaint information and the medical history information of the patient can be structured, clear and labeled, and a doctor can conveniently and quickly locate the personal information of the patient. Furthermore, disease keywords are extracted from case information and chief complaint information, and are preprocessed, so that the portrait information of the patient comprises all disease information of the patient, and the accuracy of a disease diagnosis result is greatly improved. Furthermore, by preprocessing the disease keywords, words related to diseases in case information and chief complaint information of the patient can be unified and standard, disease diagnosis can be conveniently carried out in the later period, and the accuracy of disease diagnosis results can be improved. Specifically, the step of preprocessing the condition keywords includes normalizing the condition keywords, for example, converting "headache" into "headache".
In this embodiment, the condition keywords include one or more of symptom information, present medical history information, past medical history information, personal medical history information, family medical history information, marriage and childbirth history information, index abnormality information (such as blood pressure, blood sugar, and the like), and examination abnormality information.
In one embodiment, the construction of patient profile information may incorporate rule matching and similarity algorithms for the extraction and construction of condition keywords. Specifically, the construction of the patient representation information mainly includes the following aspects: on the first hand, extracting disease keywords according to the patient's chief complaint information and medical record information: in the process of extracting the disease keywords, the disease keywords are extracted by using a rule matching algorithm and a similarity algorithm (mainly using a lattice tower mode algorithm), for example, the part hypernyms: a waist part; the word of the degree of the part: severe; time: 4 months, etc. In a second aspect, the step of normalizing the disease condition keyword comprises: different disease keywords (such as parts and chemical inspection) are utilized to perform network crawling and manual arrangement of respective synonym dictionaries, and words corresponding to the disease keywords are standardized, such as headache is converted into headache. Furthermore, after the disease information is generated, the disease information is generated into a disease label page, so that the disease information is displayed on the portrait information of the patient in the form of the label page, the disease information of the patient is more structured, clearer and labeled, a doctor can conveniently and rapidly position the personal information of the patient, and the diagnosis efficiency and the diagnosis accuracy of the doctor are improved.
Example four
As shown in fig. 6, on the basis of any one of the above embodiments, a fourth embodiment provides a disease diagnosis method, further defining that before the step of determining a disease diagnosis result of the patient based on the patient image information, the disease diagnosis method further includes:
In the embodiment, the disease information of at least two patients is acquired to generate the prediction model data, the prediction model data is preprocessed, and machine learning training is performed, so that a first disease prediction model is generated, different disease information is extracted from the patient portrait information, the disease type is automatically predicted, a doctor is efficiently assisted to diagnose, and the diagnosis efficiency and the diagnosis accuracy are improved. In the embodiment, the machine learning is trained by using sample data to generate the first disease prediction model, and technologies such as natural language processing, data mining, machine learning, deep learning and the like are combined, so that intelligent diagnosis and typing of neurodegenerative diseases are realized, and the diagnosis efficiency and the diagnosis accuracy are improved.
In the embodiment, the patient portrait is constructed through the personal medical record information and the chief complaint information of the patient, and the disease label page in the patient portrait information is subjected to disease information extraction, so that the diagnosis result of the corresponding neurodegenerative disease is automatically calculated, and further, the corresponding disease knowledge map information can be constructed according to the disease diagnosis result, so as to assist a doctor in confirming the diagnosis scheme.
In this embodiment, the step of obtaining the disease information of at least two patients to generate the prediction model data set specifically includes: acquiring at least three thousand patient chief complaint information and disease diagnosis result data sets generated by a hospital, and classifying according to patient IDs of patients through the chief complaint information and the disease diagnosis result data sets to form a prediction model data set, wherein the disease information of the patients comprises the patient IDs, symptoms and diagnosis results.
In this embodiment, the step of extracting a disease keyword from the prediction model data set to generate a disease data set specifically includes: and extracting symptom keywords by using a format tower pattern matching algorithm and rules, and carrying out standardization processing on the symptom keywords to generate symptom standard words. Further, a TFIDF algorithm is used for data normalization to generate a disease data set.
In this embodiment, the step of performing grouping processing on the disease condition data set to generate a training data set and a prediction data set specifically includes: and randomly grouping the disease data sets according to a preset proportion to generate a training data set and a prediction data set. In one embodiment, the preset ratio comprises 0.8: 0.2.
In this embodiment, the step of extracting feature quantities from the training data set to generate a feature data set specifically includes: and extracting the disease standard words and the disease degree words as characteristic quantities to generate a characteristic data set. Specifically, after carrying out data normalization processing on the independent variable (namely, the disease standard word) by using a TFIDF algorithm, dividing the independent variable into a training data set and a prediction data set, and extracting the disease standard word and a disease degree word from the training data set as model features. Dependent variables (diagnosis) are processed in digital form, such as 0-multisystemic atrophy, 1-progressive supranuclear palsy, 2-parkinsonism, 3-parkinson's disease, 4-frontotemporal dementia, 5-corticobasal degeneration.
In this embodiment, the step of generating the first disease prediction model according to the training data set, the feature data set, the prediction data set, and the preset rule specifically includes: inputting the training data set into a multinomialNB model for training to obtain model prediction optimal parameters for establishing a first disease prediction model, and inputting the prediction data set into the multinomialNB model to obtain a prediction accuracy index for measuring the accuracy of a model prediction result, wherein the prediction accuracy index comprises prediction accuracy (accuracy), prediction accuracy (precision), recall rate (call) and a prediction Score (namely F1Score (F1 Score)).
In this embodiment, when extracting the disease degree words, the regular expression of the disease degree words (such as progressive, episodic, recurrent, etc.) and the degree word library (derived from the segmentation words) are defined, and the corresponding degree words of different diseases are extracted separately.
In this embodiment, in the process of generating patient image information, natural language processing and chinese medical terminology are combined, tagging processing is performed on patient complaint information, and patient image information including a disease tag page such as symptom duration and symptom occurrence degree is constructed. Furthermore, automatic diagnosis and typing of neurodegenerative diseases and automatic recommendation and display of corresponding knowledge maps are realized by identifying the portrait information of the patient and extracting disease information.
Further, by applying unstructured information and a large amount of patient complaint information existing in the electronic medical record of the neurodegenerative disease patient to the generation of the patient portrait information, the individual conditions of the patient with high clinical symptom similarity and at the time point of the course of disease can be displayed more accurately, and the patient portrait information including disease classification, time information extraction and patient personal information structuring can be rapidly constructed, so that the patient disease classification can be accurately judged according to the patient portrait information of different patients, the corresponding disease knowledge map and the corresponding treatment method can be intelligently displayed, and the diagnosis efficiency and the diagnosis accuracy of doctors are improved.
According to the disease diagnosis method provided by the embodiment of the invention, the corresponding category of the corresponding neurodegenerative disease is automatically diagnosed by combining the image information of the patient and utilizing an artificial intelligence method; in the neurodegenerative disease knowledge graph part, automatic display and search of corresponding knowledge graphs are constructed from the aspects of treatment methods, medicine recommendation, surgical treatment, inspection, chemical examination and the like by taking diseases as the center, so that the efficiency and the accuracy of disease diagnosis are improved, an auxiliary effect is realized on the construction of a treatment scheme of a patient, and the accuracy and the efficiency of the construction of the treatment scheme are improved.
In this embodiment, the first disease prediction model comprises a MultinomialNB prediction model.
Further, as shown in fig. 7, in this embodiment, the step of extracting a disease keyword from the prediction model data set to generate a disease data set specifically includes:
In the embodiment, disease keywords are extracted from the prediction model data set, and are preprocessed to generate disease standard words, so that the disease of the patient is more standard by converting the disease keywords into the disease standard words, and the accuracy of a prediction result is improved when disease prediction is performed. Further, data normalization processing is carried out through the disease standard words to generate a disease data set, so that measurement units of the disease data set are unified, training of a machine learning model can be carried out, and a disease prediction model is generated. Specifically, the step of preprocessing the condition keywords includes normalizing the condition keywords, for example, converting "headache" into "headache".
In one embodiment, the disease keywords may be extracted using a trellis pattern matching algorithm and rule matching, and the disease keywords may be normalized. Any one of the disease standard words is selected as a disease standard word of a similar group of symptoms, and meanwhile, manual screening is combined, so that a dictionary of all disease standard words corresponding to multi-system atrophy, progressive supranuclear palsy, Parkinson's disease, frontotemporal dementia and corticobasal degeneration is finally generated, namely, a dictionary of the disease standard words of each disease type is generated, and a disease data set of each disease type is generated by performing data normalization processing on the disease standard dictionary.
Further, as shown in fig. 8, in this embodiment, the step of determining a disease diagnosis result of the patient according to the patient image information specifically includes:
In the embodiment, the disease information of the patient is acquired according to the portrait information of the patient, the disease information of the patient is input into the first disease prediction model, and the first disease prediction model outputs the first disease name information and a prediction accuracy index for measuring the prediction accuracy of the first disease prediction model, so that a doctor can judge whether the first disease name information output by the first disease prediction model is used according to the prediction accuracy index, and the accuracy and the efficiency of a diagnosis result provided for the patient are improved. Specifically, the prediction accuracy indicator includes at least one of a first prediction accuracy, a first recall, a first prediction score. In one embodiment, an index may be used to measure the prognosis of the first disease prediction model to improve diagnostic efficiency. In another embodiment, multiple indices may also be used to scale the prediction of the first disease prediction model to provide accuracy of the diagnostic result.
EXAMPLE five
In any of the above embodiments, the step of determining a diagnosis result of the disease of the patient based on the patient image information includes: acquiring disease information of a patient according to the portrait information of the patient; and inputting the disease information into a second disease prediction model, and outputting a second disease diagnosis result by the second disease prediction model, wherein the second disease diagnosis result comprises second disease name information, and the second disease diagnosis result further comprises at least one of second prediction accuracy, second recall rate and second prediction score.
In the embodiment, the disease information of the patient is acquired according to the patient image information, the disease information of the patient is input into the second disease prediction model, and the second disease prediction model outputs the second disease name information and a prediction accuracy index for measuring the prediction accuracy of the second disease prediction model, so that a doctor can judge whether the second disease name information output by the second disease prediction model is used according to the prediction accuracy index, and the accuracy and the efficiency of a diagnosis result provided for the patient are improved. Specifically, the prediction accuracy indicator includes at least one of a second prediction accuracy, a second recall, and a second prediction score. In one embodiment, an index may be used to measure the prognosis of the second disease prediction model to improve diagnostic efficiency. In another embodiment, multiple indices may also be used for prediction of the beam second disease prediction model to provide accuracy of the diagnostic result.
In one embodiment, the prediction of disease outcome may be performed using only the second disease prediction model, which may improve diagnostic efficiency and reduce diagnostic costs. In another embodiment, the first disease prediction model and the second disease prediction model can be used simultaneously to predict the disease outcome, and the first disease prediction model and the second disease prediction model can be used simultaneously to predict the disease outcome, so that the accuracy of the diagnosis result can be improved. When the disease outcome prediction is performed by using the first disease prediction model and the second disease prediction model at the same time, the final disease diagnosis result is determined by at least one of the first prediction accuracy and the second prediction accuracy, the first recall rate and the second recall rate, the first prediction score and the second recall rate. Specifically, the higher the numerical values of the prediction accuracy, the prediction accuracy rate, and the prediction score are, the more accurate the disease diagnosis result is represented. The lower the recall value, the more accurate the disease diagnosis. When the accuracy of the disease diagnosis results of the two disease prediction models is compared using a plurality of parameters, the judgment can be made with reference to the integrated score.
In one embodiment, the second disease prediction model comprises the TFIDF algorithm.
EXAMPLE six
On the basis of any of the above embodiments, the disease diagnosis method further comprises: acquiring disease information of a patient, and displaying the disease information on a disease label page.
In the embodiment, the disease information of the patient is more comprehensive by acquiring the disease information of the patient and displaying the disease information on the disease label page, so that the accuracy of the disease diagnosis result is improved. In one embodiment, the doctor can randomly add the disease information of the patient by clicking different disease label pages on the patient image, and the disease information corresponds to the patient's chief complaint information, thereby improving the accuracy of the disease diagnosis result.
EXAMPLE seven
As shown in fig. 9, the seventh embodiment provides a disease diagnosis system 900, including: a memory 902, the memory 902 storing programs or instructions; processor 904, processor 904 executing the program or instructions to implement the steps of the disease diagnosis method of any of the above-mentioned embodiments.
Embodiments of the invention provide a disease diagnostic system 900 that includes a memory 902 and a processor 904. The steps of the disease diagnosis method in any of the above technical solutions can be implemented when the processor 904 executes the program or the instructions, so that all the beneficial technical effects of the disease diagnosis method provided in any of the above technical solutions are achieved, and are not described herein again.
Example eight
An eighth embodiment provides a readable storage medium, on which a program or instructions are stored, the program or instructions, when executed by a processor, implement the steps of the disease diagnosis method provided in any of the above-mentioned technical solutions.
The readable storage medium provided by the embodiment of the present invention can implement the steps of the disease diagnosis method provided in any one of the above technical solutions, and therefore, all the beneficial technical effects of the disease diagnosis method provided in any one of the above technical solutions are achieved, and are not described herein again.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (11)
1. A method of disease diagnosis, comprising:
acquiring medical record information of a patient and chief complaint information of the patient;
constructing patient portrait information according to the medical record information and the chief complaint information;
determining a disease diagnosis result of the patient based on the patient profile information,
wherein the patient representation information includes at least one condition tab page including condition information of the patient.
2. The method for disease diagnosis according to claim 1, further comprising:
constructing disease knowledge map information according to the disease diagnosis result,
wherein the disease knowledge map information comprises one or more of disease knowledge information, disease symptom information, disease treatment information, and drug information.
3. The disease diagnostic method according to claim 2, wherein the step of constructing disease knowledge map information based on the disease diagnostic result specifically comprises:
determining disease name information according to the disease diagnosis result;
generating medicine map information of at least one medicine according to the disease name information; and/or
Generating disease pattern information of at least one disease according to the disease name information; and/or
Generating treatment map information of at least one treatment means according to the disease name information;
generating the disease knowledge profile information from one or more of the drug profile information, the condition profile information, and the therapy profile information.
4. The disease diagnosis method of claim 1, wherein the step of constructing a patient representation based on the medical record information and the complaint information comprises:
extracting disease keywords according to the medical record information and the chief complaint information;
preprocessing the disease keywords to generate disease information;
generating patient profile information for the patient based on the medical condition information.
5. The disease diagnostic method according to claim 1, wherein before the step of determining a disease diagnostic result of the patient based on the patient image information, the disease diagnostic method further comprises:
acquiring disease information of at least two patients to generate a prediction model data set;
extracting disease key words from the prediction model data set to generate a disease data set;
performing packet processing on the disease data set to generate a training data set and a prediction data set;
extracting characteristic quantity from the training data set to generate a characteristic data set;
and generating a first disease prediction model according to the training data set, the feature data set, the prediction data set and a preset rule.
6. The method for disease diagnosis according to claim 5, wherein the step of extracting disease keywords from the prediction model data set to generate a disease data set specifically comprises:
extracting disease key words from the prediction model data set;
preprocessing the disease keywords to generate disease standard words;
and carrying out data normalization processing on the disease standard words to generate a disease data set.
7. The disease diagnosis method according to claim 5, wherein the step of determining the disease diagnosis result of the patient based on the patient image information comprises:
acquiring disease information of the patient according to the patient portrait information;
inputting the condition information into the first disease prediction model, the first disease prediction model outputting a first disease diagnosis,
wherein the first disease diagnosis result comprises first disease name information, and the first disease diagnosis result further comprises at least one of a first prediction accuracy, a first recall rate, and a first prediction score.
8. The disease diagnosis method according to claim 1 or 7, wherein the step of determining the disease diagnosis result of the patient based on the patient image information includes:
acquiring disease information of the patient according to the patient portrait information;
inputting the condition information into a second disease prediction model, the second disease prediction model outputting a second disease diagnosis,
wherein the second disease diagnosis result comprises second disease name information, and the second disease diagnosis result further comprises at least one of a second prediction accuracy, a second recall rate, and a second prediction score.
9. The disease diagnostic method according to any one of claims 1 to 7, further comprising:
acquiring disease information of the patient, and displaying the disease information on the disease label page.
10. A disease diagnostic system, comprising:
a memory storing programs or instructions;
a processor executing the program or instructions to carry out the steps of the disease diagnosis method according to any one of claims 1 to 9.
11. A readable storage medium, characterized in that a program or instructions are stored thereon, which when executed by a processor, implement the steps of the disease diagnosis method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011637337.5A CN112635011A (en) | 2020-12-31 | 2020-12-31 | Disease diagnosis method, disease diagnosis system, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011637337.5A CN112635011A (en) | 2020-12-31 | 2020-12-31 | Disease diagnosis method, disease diagnosis system, and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112635011A true CN112635011A (en) | 2021-04-09 |
Family
ID=75290230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011637337.5A Pending CN112635011A (en) | 2020-12-31 | 2020-12-31 | Disease diagnosis method, disease diagnosis system, and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112635011A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112992362A (en) * | 2021-04-19 | 2021-06-18 | 北京妙医佳健康科技集团有限公司 | Body state evaluation device, electronic equipment and storage medium |
| CN113053468A (en) * | 2021-05-31 | 2021-06-29 | 之江实验室 | Drug new indication discovering method and system fusing patient image information |
| CN113488161A (en) * | 2021-07-05 | 2021-10-08 | 中国人民解放军总医院第一医学中心 | Temporomandibular joint disorder treatment regimen recommendation apparatus, device and storage medium |
| CN113488126A (en) * | 2021-07-27 | 2021-10-08 | 心医国际数字医疗系统(大连)有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
| CN113782189A (en) * | 2021-09-16 | 2021-12-10 | 平安国际智慧城市科技股份有限公司 | Intelligent auxiliary diagnosis and treatment method and device based on regional disease map |
| CN114300083A (en) * | 2021-11-16 | 2022-04-08 | 北京左医科技有限公司 | Medical record construction method and system |
| CN115762812A (en) * | 2022-11-27 | 2023-03-07 | 北京健康在线技术开发有限公司 | Digital diagnosis and treatment method, system, equipment and medium for stroke patient |
| TWI800971B (en) * | 2021-11-03 | 2023-05-01 | 財團法人資訊工業策進會 | Disability level automatic judgment device and disability level automatic judgment method |
| CN116612879A (en) * | 2023-07-19 | 2023-08-18 | 北京惠每云科技有限公司 | Diagnostic result prediction method, diagnostic result prediction device, electronic equipment and storage medium |
-
2020
- 2020-12-31 CN CN202011637337.5A patent/CN112635011A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112992362A (en) * | 2021-04-19 | 2021-06-18 | 北京妙医佳健康科技集团有限公司 | Body state evaluation device, electronic equipment and storage medium |
| CN113053468A (en) * | 2021-05-31 | 2021-06-29 | 之江实验室 | Drug new indication discovering method and system fusing patient image information |
| CN113053468B (en) * | 2021-05-31 | 2021-09-03 | 之江实验室 | Drug new indication discovering method and system fusing patient image information |
| CN113488161A (en) * | 2021-07-05 | 2021-10-08 | 中国人民解放军总医院第一医学中心 | Temporomandibular joint disorder treatment regimen recommendation apparatus, device and storage medium |
| CN113488126A (en) * | 2021-07-27 | 2021-10-08 | 心医国际数字医疗系统(大连)有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
| CN113782189A (en) * | 2021-09-16 | 2021-12-10 | 平安国际智慧城市科技股份有限公司 | Intelligent auxiliary diagnosis and treatment method and device based on regional disease map |
| TWI800971B (en) * | 2021-11-03 | 2023-05-01 | 財團法人資訊工業策進會 | Disability level automatic judgment device and disability level automatic judgment method |
| CN114300083B (en) * | 2021-11-16 | 2022-10-18 | 北京左医科技有限公司 | Medical record construction method and system |
| CN114300083A (en) * | 2021-11-16 | 2022-04-08 | 北京左医科技有限公司 | Medical record construction method and system |
| CN115762812A (en) * | 2022-11-27 | 2023-03-07 | 北京健康在线技术开发有限公司 | Digital diagnosis and treatment method, system, equipment and medium for stroke patient |
| CN115762812B (en) * | 2022-11-27 | 2023-06-23 | 北京健康在线技术开发有限公司 | Digital diagnosis and treatment method, system, equipment and medium for stroke patient |
| CN116612879A (en) * | 2023-07-19 | 2023-08-18 | 北京惠每云科技有限公司 | Diagnostic result prediction method, diagnostic result prediction device, electronic equipment and storage medium |
| CN116612879B (en) * | 2023-07-19 | 2023-09-26 | 北京惠每云科技有限公司 | Diagnostic result prediction method, diagnostic result prediction device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112635011A (en) | Disease diagnosis method, disease diagnosis system, and readable storage medium | |
| CN108831559B (en) | Chinese electronic medical record text analysis method and system | |
| CN111710420B (en) | Complication onset risk prediction method, system, terminal and storage medium based on electronic medical record big data | |
| CN106068509B (en) | System and method for creating a longitudinal view of patient findings | |
| JP2020516997A (en) | System and method for model-assisted cohort selection | |
| JP2017174405A (en) | System and method for evaluating patient's treatment risk using open data and clinician input | |
| DE112014000897T5 (en) | Learning health systems and procedures | |
| CN110299209B (en) | Similar medical record searching method, device and equipment and readable storage medium | |
| CN113724848A (en) | Medical resource recommendation method, device, server and medium based on artificial intelligence | |
| US11527312B2 (en) | Clinical report retrieval and/or comparison | |
| Arbet et al. | Lessons and tips for designing a machine learning study using EHR data | |
| US20220172841A1 (en) | Methods of identifying individuals at risk of developing a specific chronic disease | |
| Guo et al. | A disease inference method based on symptom extraction and bidirectional Long Short Term Memory networks | |
| Benhar et al. | A systematic mapping study of data preparation in heart disease knowledge discovery | |
| CN111180026A (en) | Special diagnosis and treatment view system and method | |
| Mridha et al. | Automated stroke prediction using machine learning: An explainable and exploratory study with a web application for early intervention | |
| Sedghi et al. | Mining clinical text for stroke prediction | |
| Abaho et al. | Assessment of contextualised representations in detecting outcome phrases in clinical trials | |
| US11714964B2 (en) | Text processing method and apparatus | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| WO2023217737A1 (en) | Health data enrichment for improved medical diagnostics | |
| Shruthi et al. | A Method for Predicting and Classifying Fetus Health Using Machine Learning | |
| Pichon et al. | Cognitive Function Characterization Using Electronic Health Records Notes | |
| Rajathi et al. | Named Entity Recognition-based Hospital Recommendation | |
| Gancheva et al. | X-Ray Images Analytics Algorithm based on Machine Learning |
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 |