CN118761596B - Intelligent triage method and system - Google Patents
Intelligent triage method and system Download PDFInfo
- Publication number
- CN118761596B CN118761596B CN202411216229.9A CN202411216229A CN118761596B CN 118761596 B CN118761596 B CN 118761596B CN 202411216229 A CN202411216229 A CN 202411216229A CN 118761596 B CN118761596 B CN 118761596B
- Authority
- CN
- China
- Prior art keywords
- triage
- patient
- chromosome
- information
- disease
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 201000010099 disease Diseases 0.000 claims description 68
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 68
- 210000000349 chromosome Anatomy 0.000 claims description 54
- 230000006870 function Effects 0.000 claims description 29
- 230000035772 mutation Effects 0.000 claims description 20
- 108090000623 proteins and genes Proteins 0.000 claims description 19
- 230000036541 health Effects 0.000 claims description 16
- 208000024891 symptom Diseases 0.000 claims description 12
- 238000003745 diagnosis Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 9
- 238000010845 search algorithm Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000003058 natural language processing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 206010008479 Chest Pain Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 150000002500 ions Chemical class 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Pathology (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of medical treatment, and particularly discloses an intelligent triage method and system, wherein the method comprises the steps of S1, obtaining patient condition information, identifying key information in the condition information, S2, constructing a dynamic condition model according to historical data, medical knowledge and key information of a patient, S3, reasoning the key information according to a large model and a knowledge base, generating multiple condition hypotheses of the patient and credibility of each condition hypothesis, the large model being used for identifying and predicting the possibility of condition development, the knowledge base being used for providing relevant medical rules and facts, S4, analyzing the emergency degree and triage requirements of the patient by using the large model according to the condition model and the condition hypotheses, and generating one or more triage schemes, S5, obtaining a triage report of the patient according to the triage scheme, wherein the triage report at least comprises multiple items of basic information, condition description, triage suggestion, emergency degree, treatment suggestion, required medical resources and attention items of the patient.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to an intelligent triage method and system.
Background
The aim of triage is to improve the medical efficiency and quality, reduce the waiting time and death risk of patients and optimize the resource utilization. However, the conventional diagnosis method generally depends on manual experience and judgment, and has problems of shortage of human resources, subjectivity, inconsistency, error, delay and the like.
Therefore, how to automatically generate reasonable, effective and interpretable triage strategies by combining a large model with a knowledge base by using artificial intelligence technology is a research problem with important significance and challenges.
Disclosure of Invention
Aiming at the problems, the invention aims to provide an intelligent triage method and system, which automatically generate a reasonable and effective triage scheme according to the illness state information of a patient through the combination of a large model and a knowledge base, reduce the waiting time of the patient and improve the medical efficiency.
The intelligent diagnosis method provided by the invention comprises the following steps:
s1, acquiring illness state information of a patient, and identifying key information in the illness state information;
S2, constructing a dynamic disease model according to the historical data, medical knowledge and the key information of the patient;
S3, reasoning the key information according to a large model and a knowledge base, and generating a plurality of disease hypotheses of a patient and credibility of each disease hypothesis;
s4, analyzing the emergency degree and triage requirements of the patient by using a large model according to the disease model and the disease hypothesis, and generating one or more triage schemes;
And S5, sorting and obtaining a triage report of the patient according to the triage scheme, wherein the triage report at least comprises a plurality of items of basic information, illness state description, triage advice, emergency degree, treatment advice, required medical resources and notes of the patient.
In one possible implementation, the S1 includes:
analyzing the illness state information by using a natural language processing technology to obtain first information;
identifying the semantics and the context of the patient by using the BERT pre-training language model to obtain second information;
Extracting keywords from the illness state information to obtain third information;
And obtaining the key information according to the first information and/or the second information and/or the third information, wherein the key information at least comprises symptoms, duration and severity.
In one possible implementation manner, the S1 further includes:
And the condition information of the voice format of the patient is converted into condition information of a text format through a deep learning algorithm convolutional neural network CNN.
In one possible implementation, the disease model includes at least basic information, symptoms, signs, past medical history, and family medical history of the patient, and the S2 includes:
Combining the key information with the historical data through the illness state model to obtain an illness state view;
Assessing the current health condition of the patient by the disease model, the health condition including severity of symptoms and possible disease;
Identifying potential health risks and situations requiring urgent intervention in the current health condition of the patient through the disease model;
and updating the disease model in real time according to the new disease information.
In one possible implementation, the S3 includes:
constructing the knowledge base by using an ontology modeling tool;
Analyzing the key information by using the large model, and extracting possible disease assumptions from the knowledge base;
And evaluating the credibility of each disease hypothesis through a evidence reasoning algorithm.
In one possible implementation, the S4 includes:
Constructing an objective function with the constraint conditions of medical resource availability and patient priority, wherein the constraint conditions of the objective function are that the cure rate of the patient is maximized and the waiting time of the patient is minimized;
Searching an optimal or suboptimal triage scheme in a feasible solution space of the objective function by using a heuristic search algorithm, and determining a triage grade by combining relevant knowledge in a medical knowledge graph.
In one possible implementation, the searching for the optimal or suboptimal triage solution in the feasible solutions of the objective function using a heuristic search algorithm includes:
randomly generating a plurality of feasible solutions according to the objective function to form an initial population;
calculating selection probability according to the fitness of each feasible solution, and selecting a plurality of feasible solutions from the initial population according to the selection probability to generate a temporary population;
randomly selecting a first chromosome and a second chromosome from the temporary population as parents;
randomly selecting a crossover point, exchanging genes of the first chromosome and the second chromosome after the crossover point, and generating a first new chromosome and a second new chromosome;
Randomly selecting a gene in the first new chromosome and the second new chromosome by taking the mutation rate as probability to perform mutation operation to obtain a first mutation chromosome and a second mutation chromosome, wherein the mutation operation comprises any one of randomly changing gene values and exchanging gene positions;
Adding the first variant chromosome and the second variant chromosome to a new generation population;
When the maximum iteration times or the change rate of the fitness is smaller than a preset value, outputting an optimal solution, namely a triage scheme, otherwise, taking the new generation population as the initial population.
In one possible implementation, the calculating the selection probability according to the fitness of each individual includes:
The selection probability Pselect (c) is calculated from the fitness function F (c), as follows:
;
wherein N is the number of triage schemes, c is the chromosome coded by each triage scheme, c j represents the gene of the j decision in the triage scheme, and fitness F (c) is calculated for each chromosome c, and j is a positive integer;
the fitness function F (c) has the following formula:
;
where Oi (c) is an evaluation function of the ith optimization objective, wi is a weight of the ith optimization objective, and i is a positive integer.
In one possible implementation, the S5 includes:
generating a structured triage report according to a template engine, a natural language generation technology and the triage scheme;
And checking the triage report through manual checking and/or machine checking.
The invention also provides an intelligent triage system for realizing any one of the intelligent triage methods, comprising:
The information acquisition module is used for acquiring the illness state information of the patient and identifying key information in the illness state information;
The model construction module is used for constructing a dynamic illness state model according to the historical data, medical knowledge and the key information of the patient;
the information reasoning module is used for reasoning the key information according to a large model and a knowledge base, and generating a plurality of disease hypotheses of a patient and credibility of each disease hypothesis;
The disease analysis module is used for analyzing the emergency degree and triage requirements of the patient by utilizing the large model according to the disease model and the disease hypothesis, and generating one or more triage schemes;
the report generation module is used for sorting and obtaining the triage report of the patient according to the triage scheme, wherein the triage report at least comprises a plurality of items of basic information, illness state description, triage advice, emergency degree, treatment advice, required medical resources and notes of the patient.
The invention aims to provide an intelligent triage method and system, which construct a disease model according to disease information of each patient, automatically generate a reasonable and effective triage scheme according to the disease information of the patient by combining a large model with a knowledge base, reduce waiting time of the patient and improve medical efficiency.
Drawings
Fig. 1 is a schematic flow chart of an intelligent diagnosis method according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in further detail below with reference to the accompanying drawings and examples. The following detailed description of the embodiments and the accompanying drawings are provided to illustrate the principles of the invention and are not intended to limit the scope of the invention, i.e. the invention is not limited to the preferred embodiments described, which is defined by the claims.
In the description of the present invention, it should be noted that the meaning of "a plurality" is two or more, unless otherwise indicated, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance, and the specific meaning of the above terms in the present invention will be understood as appropriate to one of ordinary skill in the art.
Fig. 1 is a flow chart of an intelligent triage method according to an embodiment of the present invention, as shown in fig. 1, the intelligent triage method provided by the present invention includes:
s1, acquiring illness state information of a patient, and identifying key information in the illness state information;
in one example, the condition information includes basic information such as age, gender, past medical history, etc., complaints such as fever, chest distress, etc., signs such as blood pressure, heart rate, etc., auxiliary exams such as blood routine, electrocardiogram, etc.
In one possible implementation, S1 includes parsing the condition information using natural language processing techniques to obtain first information, such as medical terms and symptoms, identifying the patient' S semantics and context using a BERT pre-training language model to obtain second information, such as severity and urgency of symptoms, extracting keywords from the condition information to obtain third information, such as symptoms, duration, past medical history, obtaining key information based on the first information and/or the second information and/or the third information, the key information including at least symptoms, duration, severity.
In one example, after speech-to-text conversion using a deep learning algorithm convolutional neural network, the output of RNN or CNN is reordered using an N-gram language model or a deep language model to improve recognition accuracy, the performance of the model is evaluated on a separate test set, and the accuracy of recognition is measured using an index, such as word error rate.
In one possible implementation, since the patient or caller may communicate through telephone, limb gestures or on-line text, when the illness state information is in a voice format, the illness state information in the voice format needs to be converted into text format, and the limb information is the same. After conversion, the accuracy of the illness state information can be ensured, and information misunderstanding is avoided. S1 further comprises the step of converting illness state information of a voice format of a patient into illness state information of a text format through a deep learning algorithm convolutional neural network CNN.
S2, constructing a dynamic disease model according to historical data, medical knowledge and key information of a patient;
In one possible implementation, S2 includes combining key information and historical data through a disease model to obtain a disease view, which can help understand the health of the patient. The method comprises the steps of evaluating the current health condition of a patient through a disease model, wherein the health condition comprises severity of symptoms and possible diseases, identifying potential health risks and situations requiring urgent intervention in the current health condition of the patient through the disease model, and updating the disease model in real time according to new disease information.
The disease model at least comprises basic information, symptoms, physical signs, past medical history and family medical history of the patient, can identify potential health risks and emergency degree, and provides support for triage schemes.
Therefore, by analyzing patient data, the disease model can assist doctors in quickly identifying possible diseases and health risks, and personalized treatment schemes can be recommended according to specific conditions of patients, so that basis is provided for preventive medical treatment. By giving priority to high-risk patients, the disease model is beneficial to optimizing the distribution of medical resources, automating the disease evaluation process, reducing the workload of doctors and improving the efficiency of medical services. By constructing a patient condition model, a medical professional can more accurately assess patient condition, make more informed clinical decisions, and provide more personalized medical services. At the same time, this also helps to improve the overall quality and efficiency of the medical service.
S3, reasoning key information according to the large model and the knowledge base, and generating a plurality of disease assumptions of the patient and credibility of each disease assumption;
Wherein a large model is used to identify and predict the likelihood of progression of a condition, a large model refers to a machine learning model with large scale parameters and complex computational structures, such as ChatGPT, and a knowledge base is used to provide relevant medical rules and facts, such as a library of medical books, a library of cases.
In one possible implementation, S3 includes building a knowledge base using an ontology modeling tool, such as using OWL or RDF formats, analyzing key information using a large model, extracting possible disease hypotheses from the knowledge base, and evaluating the credibility of each disease hypothesis through a evidence reasoning algorithm.
S4, analyzing the emergency degree and triage requirements of the patient by using the large model according to the disease model and the disease hypothesis to generate one or more triage schemes, wherein the triage schemes need to consider various factors such as the disease severity, the availability of medical resources, the arrival time of the patient at a hospital and the like.
In one possible implementation, S4 includes constructing an objective function to maximize the cure rate of the patient and minimize the waiting time of the patient, constraining conditions of the objective function to availability of medical resources and priority of the patient, searching for an optimal or suboptimal diagnosis scheme in a feasible solution space of the objective function using a heuristic search algorithm, such as a multi-objective genetic algorithm or a multi-objective particle swarm optimization algorithm, and determining a diagnosis level in combination with relevant knowledge in a medical knowledge graph.
The heuristic search algorithm is an algorithm based on visual or experience construction, gives a feasible solution of each instance of the combination optimization problem to be solved at acceptable cost, and the deviation degree of the feasible solution and the optimal solution cannot be estimated generally. The multi-objective genetic algorithm is based on the genetic algorithm, the selective regeneration method is improved, each individual is layered according to the dominant and non-dominant relations, and then the selective operation is carried out. The multi-target particle swarm optimization algorithm can maintain a group of non-inferior solution sets in the process of ions, so that a series of optimal solutions are obtained, and the requirements of different fields are met.
In one possible implementation, finding the optimal or suboptimal triage solution among the feasible solutions of the objective function using a heuristic search algorithm includes:
randomly generating a plurality of feasible solutions according to the objective function to form an initial population;
calculating selection probability according to the fitness of each feasible solution, and selecting a plurality of feasible solutions from the initial population according to the selection probability to generate a temporary population;
Randomly selecting a first chromosome and a second chromosome from the temporary population as parents;
Randomly selecting a crossover point, and exchanging genes of the first chromosome and the second chromosome after the crossover point to generate a first new chromosome and a second new chromosome;
Randomly selecting a gene in the first new chromosome and the second new chromosome by taking the mutation rate as probability to perform mutation operation to obtain a first mutation chromosome and a second mutation chromosome, wherein the mutation operation comprises any one of randomly changing gene values and exchanging gene positions;
Adding the first variant chromosome and the second variant chromosome to a new generation population;
When the maximum iteration times or the change rate of the fitness is smaller than a preset value, outputting an optimal solution, namely a triage scheme, otherwise, taking the new generation population as an initial population.
In one possible implementation, calculating the selection probability according to the fitness of each individual includes:
The selection probability Pselect (c) is calculated from the fitness function F (c), as follows:
;
wherein N is the number of triage schemes, c is the chromosome coded by each triage scheme, c j represents the gene of the j decision in the triage scheme, and fitness F (c) is calculated for each chromosome c, and j is a positive integer;
the fitness function F (c) has the following formula:
;
Where Oi (c) is the evaluation function of the ith optimization objective, wi is the weight of the ith optimization objective, for balancing the importance of different objectives, i is a positive integer.
The purpose of making triage grade decisions by using the large model is to improve the efficiency and accuracy of triage flow by an automatic and intelligent means and ensure that patients can obtain proper medical services in time according to the severity of illness. By optimizing medical resource allocation, the waiting time of patients is reduced, the overall quality of medical service is improved, powerful decision support is provided for medical staff, and the transparency and the interpretability of a triage scheme are enhanced. In addition, the invention also focuses on fairness, reduces human prejudice, improves patient safety, and rapidly and effectively responds in emergency, thereby realizing overall enhancement of the response capacity and service quality of the medical system.
S5, sorting and obtaining a triage report of the patient according to the triage scheme, wherein the triage report at least comprises a plurality of items of basic information, illness state description, triage advice, emergency degree, treatment advice, required medical resources and notes of the patient.
In one possible implementation, S5 includes generating a structured triage report according to a template engine, natural language generation techniques, and triage schemes, and auditing the triage report by manual auditing and/or machine auditing.
The template engine is realized by converting template codes in a specified format into a business data internet algorithm with the aim of separating a business logic layer from a presentation layer. The natural language generation technique is a technique of converting structured information understood by a computer into natural language text so that the generated text has natural, coherent and accurate expression.
In one possible implementation, information from different sources can also be integrated by data fusion techniques to ensure the comprehensiveness of the triage report. Personalized treatment advice is provided using a clinical decision support system.
The role of triage reporting is to integrate critical medical information as a bridge for communication between doctors, patients and other healthcare workers, while providing decision support to help medical teams make evidence-based diagnosis and treatment options. By automatically generating the triage report, the quality and the efficiency of the medical records are improved, the accuracy and the integrity of information are ensured, the measures of patient privacy can be protected, and the trust of the patient to medical services is enhanced. In addition, it promotes patient education, enabling the patient to better understand his health status and necessary medical procedures, thereby actively participating in his own health management.
The invention also provides an intelligent triage system for realizing any one of the intelligent triage methods, comprising:
the information acquisition module is used for acquiring the illness state information of the patient and identifying key information in the illness state information;
the model construction module is used for constructing a dynamic illness state model according to the historical data, medical knowledge and key information of the patient;
The information reasoning module is used for reasoning the key information according to the large model and the knowledge base, and generating a plurality of disease hypotheses of the patient and the credibility of each disease hypothesis;
the disease analysis module is used for analyzing the emergency degree and triage requirements of the patient by using the large model according to the disease model and the disease hypothesis to generate one or more triage schemes;
the report generation module is used for sorting and obtaining a triage report of the patient according to the triage scheme, wherein the triage report at least comprises a plurality of pieces of basic information, illness state description, triage advice, emergency degree, treatment advice, required medical resources and notes of the patient.
The invention aims to provide an intelligent triage method and system, which construct a disease model according to disease information of each patient, automatically generate a reasonable and effective triage scheme according to the disease information of the patient by combining a large model with a knowledge base, reduce waiting time of the patient and improve medical efficiency.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. An intelligent triage method is characterized by comprising the following steps:
s1, acquiring illness state information of a patient, and identifying key information in the illness state information;
S2, constructing a dynamic disease model according to the historical data, medical knowledge and the key information of the patient;
S3, reasoning the key information according to a large model and a knowledge base, and generating a plurality of disease hypotheses of a patient and credibility of each disease hypothesis;
s4, analyzing the emergency degree and triage requirements of the patient by using a large model according to the disease model and the disease hypothesis, and generating one or more triage schemes;
S5, sorting and obtaining a triage report of the patient according to the triage scheme, wherein the triage report at least comprises a plurality of items of basic information, illness state description, triage advice, emergency degree, treatment advice, required medical resources and notes of the patient;
the step S4 comprises the following steps:
Constructing an objective function with the constraint conditions of medical resource availability and patient priority, wherein the constraint conditions of the objective function are that the cure rate of the patient is maximized and the waiting time of the patient is minimized;
Searching an optimal or suboptimal triage scheme in a feasible solution space of the objective function by using a heuristic search algorithm, and determining triage grades by combining relevant knowledge in a medical knowledge graph;
the searching the optimal or suboptimal diagnosis scheme in the feasible solutions of the objective function by using a heuristic search algorithm comprises the following steps:
randomly generating a plurality of feasible solutions according to the objective function to form an initial population;
calculating selection probability according to the fitness of each feasible solution, and selecting a plurality of feasible solutions from the initial population according to the selection probability to generate a temporary population;
randomly selecting a first chromosome and a second chromosome from the temporary population as parents;
randomly selecting a crossover point, exchanging genes of the first chromosome and the second chromosome after the crossover point, and generating a first new chromosome and a second new chromosome;
Randomly selecting a gene in the first new chromosome and the second new chromosome by taking the mutation rate as probability to perform mutation operation to obtain a first mutation chromosome and a second mutation chromosome, wherein the mutation operation comprises any one of randomly changing gene values and exchanging gene positions;
Adding the first variant chromosome and the second variant chromosome to a new generation population;
When the maximum iteration times or the change rate of the fitness is smaller than a preset value, outputting an optimal solution, namely a triage scheme, otherwise, taking the new generation population as the initial population.
2. The intelligent triage method according to claim 1, wherein the S1 comprises:
analyzing the illness state information by using a natural language processing technology to obtain first information;
identifying the semantics and the context of the patient by using the BERT pre-training language model to obtain second information;
Extracting keywords from the illness state information to obtain third information;
And obtaining the key information according to the first information and/or the second information and/or the third information, wherein the key information at least comprises symptoms, duration and severity.
3. The intelligent triage method according to claim 1, wherein the S1 further comprises:
And the condition information of the voice format of the patient is converted into condition information of a text format through a deep learning algorithm convolutional neural network CNN.
4. The intelligent triage method according to claim 1, wherein the disease model includes at least basic information, symptoms, signs, past medical history and family medical history of the patient, and the S2 includes:
Combining the key information with the historical data through the illness state model to obtain an illness state view;
Assessing the current health condition of the patient by the disease model, the health condition including severity of symptoms and possible disease;
Identifying potential health risks and situations requiring urgent intervention in the current health condition of the patient through the disease model;
and updating the disease model in real time according to the new disease information.
5. The intelligent triage method according to claim 1, wherein the S3 comprises
Constructing the knowledge base by using an ontology modeling tool;
Analyzing the key information by using the large model, and extracting possible disease assumptions from the knowledge base;
And evaluating the credibility of each disease hypothesis through a evidence reasoning algorithm.
6. The intelligent triage method according to claim 1, wherein the calculating the selection probability according to the fitness of each individual includes:
The selection probability Pselect (c) is calculated from the fitness function F (c), as follows:
wherein N is the number of triage schemes, c is the chromosome coded by each triage scheme, c j represents the gene of the j decision in the triage scheme, and fitness F (c) is calculated for each chromosome c, and j is a positive integer;
the fitness function F (c) has the following formula:
F(c)=wi·Oi(c)
where Oi (c) is an evaluation function of the ith optimization objective, wi is a weight of the ith optimization objective, and i is a positive integer.
7. The intelligent triage method according to claim 1, wherein the S5 includes:
generating a structured triage report according to a template engine, a natural language generation technology and the triage scheme;
And checking the triage report through manual checking and/or machine checking.
8. An intelligent triage system for implementing the intelligent triage method according to any one of claims 1-7, comprising:
The information acquisition module is used for acquiring the illness state information of the patient and identifying key information in the illness state information;
The model construction module is used for constructing a dynamic illness state model according to the historical data, medical knowledge and the key information of the patient;
the information reasoning module is used for reasoning the key information according to a large model and a knowledge base, and generating a plurality of disease hypotheses of a patient and credibility of each disease hypothesis;
The disease analysis module is used for analyzing the emergency degree and triage requirements of the patient by utilizing the large model according to the disease model and the disease hypothesis, and generating one or more triage schemes;
The report generation module is used for sorting and obtaining a triage report of the patient according to the triage scheme, wherein the triage report at least comprises a plurality of items of basic information, illness state description, triage advice, emergency degree, treatment advice, required medical resources and notes of the patient;
the disease analysis module is also used for constructing an objective function according to the maximum cure rate of the patient and the minimum waiting time of the patient, wherein the constraint condition of the objective function is the availability of medical resources and the priority of the patient;
Searching an optimal or suboptimal triage scheme in a feasible solution space of the objective function by using a heuristic search algorithm, and determining triage grades by combining relevant knowledge in a medical knowledge graph;
the searching the optimal or suboptimal diagnosis scheme in the feasible solutions of the objective function by using a heuristic search algorithm comprises the following steps:
randomly generating a plurality of feasible solutions according to the objective function to form an initial population;
calculating selection probability according to the fitness of each feasible solution, and selecting a plurality of feasible solutions from the initial population according to the selection probability to generate a temporary population;
randomly selecting a first chromosome and a second chromosome from the temporary population as parents;
randomly selecting a crossover point, exchanging genes of the first chromosome and the second chromosome after the crossover point, and generating a first new chromosome and a second new chromosome;
Randomly selecting a gene in the first new chromosome and the second new chromosome by taking the mutation rate as probability to perform mutation operation to obtain a first mutation chromosome and a second mutation chromosome, wherein the mutation operation comprises any one of randomly changing gene values and exchanging gene positions;
Adding the first variant chromosome and the second variant chromosome to a new generation population;
When the maximum iteration times or the change rate of the fitness is smaller than a preset value, outputting an optimal solution, namely a triage scheme;
Otherwise, the new generation population is taken as the initial population.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411216229.9A CN118761596B (en) | 2024-09-02 | 2024-09-02 | Intelligent triage method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411216229.9A CN118761596B (en) | 2024-09-02 | 2024-09-02 | Intelligent triage method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118761596A CN118761596A (en) | 2024-10-11 |
| CN118761596B true CN118761596B (en) | 2024-12-20 |
Family
ID=92941983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411216229.9A Active CN118761596B (en) | 2024-09-02 | 2024-09-02 | Intelligent triage method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118761596B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119480122A (en) * | 2025-01-16 | 2025-02-18 | 吉林大学第一医院 | An intelligent emergency pre-examination and triage system based on big data |
| CN119740934B (en) * | 2025-03-06 | 2025-06-20 | 中国人民解放军总医院 | Patient condition assessment method and system based on multi-source information fusion mechanism |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114171176A (en) * | 2021-12-15 | 2022-03-11 | 华中科技大学同济医学院附属协和医院 | An internet-based hospital triage data processing method and system |
| CN116825312A (en) * | 2023-07-24 | 2023-09-29 | 广州腾方医信科技有限公司 | Triage system and triage method based on credit-invasive environment |
| CN118280562A (en) * | 2024-05-24 | 2024-07-02 | 湘江实验室 | Knowledge graph driven medical large model diagnosis method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8131656B2 (en) * | 2006-01-31 | 2012-03-06 | The Board Of Trustees Of The University Of Illinois | Adaptive optimization methods |
| CN112349410B (en) * | 2020-11-13 | 2024-04-09 | 北京京东尚科信息技术有限公司 | Training method, triage method and system for triage model of department triage |
-
2024
- 2024-09-02 CN CN202411216229.9A patent/CN118761596B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114171176A (en) * | 2021-12-15 | 2022-03-11 | 华中科技大学同济医学院附属协和医院 | An internet-based hospital triage data processing method and system |
| CN116825312A (en) * | 2023-07-24 | 2023-09-29 | 广州腾方医信科技有限公司 | Triage system and triage method based on credit-invasive environment |
| CN118280562A (en) * | 2024-05-24 | 2024-07-02 | 湘江实验室 | Knowledge graph driven medical large model diagnosis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118761596A (en) | 2024-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118761596B (en) | Intelligent triage method and system | |
| CN112567395B (en) | Artificial intelligence application for computer aided scheduling system | |
| EP3624133A1 (en) | Care path analysis and management platform | |
| WO2021167979A1 (en) | Medical machine learning system and method | |
| CN114724710A (en) | Emergency scheme recommendation method and device for emergency events and storage medium | |
| CN118098643A (en) | Emergency patient medical treatment guiding system and method | |
| CN119170218A (en) | Construction method of auxiliary treatment system based on trauma patients | |
| Kadhim et al. | Machine learning prediction of brain stroke at an early stage | |
| Yothapakdee et al. | Improving the efficiency of machine learning models for predicting blood glucose levels and diabetes risk | |
| CN119129728B (en) | Method and system for constructing brain disease nursing knowledge base | |
| CN119622555A (en) | A knowledge and data-integrated chronic disease collaborative management method and system | |
| CN118736721B (en) | Management method based on physical examination queuing call system | |
| CN118824457A (en) | A critical care auxiliary diagnosis and treatment management method and system based on patient surface information | |
| Devarapalli et al. | Identification of AIDS disease severity based on computational intelligence techniques using clonal selection algorithm | |
| Do et al. | Predicting lung healthiness risk scores to identify probability of an asthma attack | |
| CN116913486A (en) | Medical service intelligent scheduling method and device, electronic equipment and storage medium | |
| Saryazdi et al. | Identification and validation of key predictive factors for heart attack diagnosis using machine learning and fuzzy clustering | |
| Farooq et al. | A novel cardiovascular decision support framework for effective clinical risk assessment | |
| Sharma et al. | A multi-level decision-making framework for heart-related disease prediction and recommendation | |
| Zahidi et al. | Analyzing Classification Models: Random Forest vs. Neural Networks in Health Prediction | |
| Elbatanouny et al. | An interpretable machine learning model to predict hospitalizations | |
| CN113823410A (en) | Information recommendation method and device, storage medium and electronic equipment | |
| Landi et al. | The evolution of mining electronic health records in the era of deep learning | |
| Devare | Heart Disease Prediction Using Binary Classification | |
| Priyanka et al. | Enhancing Disease Diagnosis with Machine Learning Based Symtom Prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |