A method and system for matching risk events in patients with acute chest pain
By establishing a database and using a risk identification mechanism model to assess the risk factors of patients with acute chest pain, the problem of ineffective triage of patients with acute chest pain during hospital admission was solved, achieving more efficient condition assessment and triage.
Patent Information
- Application Number
- CN202410690511.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-30
- Publication Date
- 2026-11-17
AI Technical Summary
In existing technologies, patients with acute chest pain cannot undergo effective condition assessment and risk event identification during hospital transport, resulting in the inability to receive timely and scientific triage.
Establish a database to store patients' historical medical data and risk event data. Through risk identification mechanism models and data models, identify risk factors in real-time medical data, generate risk factor correlation chains, conduct risk assessments, and output medical treatment triage guidelines.
This improves the triage efficiency of patients with acute chest pain during the hospital transport process, ensuring that patients receive timely and effective treatment.
Smart Images

Figure CN123120340A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of medical technology, and in particular relates to a method and system for matching risk events in patients with acute chest pain. Background Technology
[0002] In recent years, with the rapid aging of my country's population and the increase in the incidence of cardiovascular diseases, more and more patients are seeking medical attention for chest pain. Chest pain is a major early manifestation of many diseases such as acute coronary syndrome, pulmonary embolism, and acute aortic dissection. When patients experience acute chest pain, timely hospitalization is the most effective way to treat them.
[0003] After being transported to the hospital, doctors can quickly and effectively provide timely treatment to stabilize the patient's vital signs based on their professional skills. However, the earlier the patient's condition is assessed during the transport process, the earlier the patient can be treated scientifically, thereby achieving the goal of efficient and reasonable triage of chest pain patients. Under current technology, assessing the condition of patients with acute chest pain and making accurate subsequent identifications are only possible in pre-hospital emergency care and emergency departments. Before, during, and before the patient seeks medical attention on their own, ambulances can only make preliminary judgments on the patient's vital signs and cannot further identify the risk events associated with the patient's acute chest pain. Summary of the Invention
[0004] The technical problem solved by this invention is to provide a method and system for matching risk events in patients with acute chest pain, so as to solve the problem of lack of effective triage for patients with acute chest pain in hospitals.
[0005] The basic solution provided by this invention is a method for matching risk events in patients with acute chest pain, comprising:
[0006] S1: Establish a database that stores the target patient's historical medical data and risk event data of patients with acute chest pain; and receive real-time medical data uploaded from external diagnostic and treatment devices and transmit it to the database for storage.
[0007] S2: Call the risk identification mechanism model to identify risk factors in the uploaded real-time medical data. The template of the risk factor is obtained by inversion based on the risk event data of patients with acute chest pain.
[0008] S3: Call the risk identification data model and use the risk factors output from the risk identification mechanism model as input to the risk identification data model; the risk identification data model generates a risk factor association chain for the input risk factors according to a preset association algorithm, and then performs a risk assessment on the risk factor association chain according to a preset risk level, and outputs the risk assessment result;
[0009] S4: Based on the risk assessment results, target patients are triaged for medical treatment.
[0010] Furthermore, S1 includes:
[0011] S1-1: Obtain the target patient's historical medical records, including local hospital medical records and out-of-town hospital medical records, extract the target patient's historical medical data from the historical medical records, encrypt the data, and then transmit it to the database for storage;
[0012] S1-2: Obtain medical treatment process data of patients with acute chest pain from local and remote medical records, extract acute chest pain knowledge data from the acute chest pain disease knowledge base, combine the medical treatment process data of patients with acute chest pain with the acute chest pain knowledge data to generate risk event data of patients with acute chest pain, and transmit it to the database for storage.
[0013] S1-3: Receive real-time medical data uploaded by the target patient from external diagnostic and treatment equipment, and transmit it to the database for storage.
[0014] Furthermore, in S1-3, the real-time medical data includes subjective eyewitness data and objective diagnosis and treatment data. The subjective eyewitness data is medical data on the causes, manifestations, and outcomes of acute chest pain symptoms in the target patient, obtained through monitoring equipment, accompanying personnel, and the patient's family members.
[0015] The objective diagnostic data refers to the medical data obtained by medical staff when they use medical diagnostic equipment to monitor the target patient after contact with the patient.
[0016] Furthermore, S2 includes:
[0017] S2-1: Construct a risk identification mechanism model, train it based on risk event data of patients with acute chest pain, match the medical treatment process data of patients with acute chest pain with acute chest pain knowledge data, generate acute chest pain risk characteristics, and use them as risk factor templates;
[0018] S2-2: Input the real-time medical data of the target patient into the risk identification mechanism model. Subjective eyewitness data is preprocessed by the data preprocessing model before being input into the risk identification mechanism model, and subjective risk factors are output. Objective diagnosis and treatment data are directly input into the risk identification mechanism model, and objective risk factors are output.
[0019] Furthermore, S3 includes:
[0020] S3-1: Construct a risk identification data model based on a deep learning network. The risk identification data model receives subjective risk factors and objective risk factors, and finds matching objective risk factors from subjective risk factors through a preset association algorithm; and finds matching subjective risk factors from objective risk factors to generate multiple risk factor association chains.
[0021] S3-2: Construct a risk event assessment module. In the risk event assessment module, risk event assessment levels are preset based on acute chest pain knowledge data. The risk event assessment levels include individual scores and combined scores of several risk factors, and the corresponding risk levels are divided according to the total score.
[0022] S3-3: The risk event assessment module calls the risk event assessment level to assess the risk factor association chain and generate the corresponding risk assessment results.
[0023] An acute chest pain patient risk event matching system, applied to the above-mentioned acute chest pain patient risk event matching method, includes a server, the server including a database, a data receiving module, and a model building module;
[0024] The data receiving module is used to receive real-time medical data uploaded from external diagnostic and treatment equipment and transmit it to the database for storage;
[0025] The database is used to store the transmitted real-time medical data, as well as the target patient's historical medical data and risk event data for patients with acute chest pain.
[0026] The model building module is used to build a risk identification mechanism model and a risk identification data model. The risk identification mechanism model is used to identify risk factors in real-time medical data. The risk identification data model receives the identified risk factors, generates risk factor association chains according to a preset association algorithm, and then performs risk assessment on the risk factor association chains according to a preset risk level, and outputs the risk assessment results.
[0027] The medical terminal is used to receive risk assessment results and generate patient triage guidelines.
[0028] Furthermore, the database stores the target patient's historical medical data and acute chest pain patient risk event data specifically as follows:
[0029] Obtain the target patient's historical medical records, including local hospital records and out-of-town hospital records; extract the target patient's historical medical data from the historical medical records; encrypt the data and then transmit it to the database for storage.
[0030] Data on the medical treatment process of patients with acute chest pain from local and remote medical records is obtained, and knowledge data on acute chest pain is extracted from the acute chest pain disease knowledge base. The medical treatment process data of patients with acute chest pain is combined with the knowledge data on acute chest pain to generate risk event data of patients with acute chest pain, which is then transmitted to the database for storage.
[0031] Furthermore, the real-time medical data includes subjective eyewitness data and objective diagnosis and treatment data. The subjective eyewitness data is medical data on the causes, manifestations, and outcomes of acute chest pain symptoms in the target patient, obtained through monitoring equipment, accompanying personnel, and the patient's family members.
[0032] The objective diagnostic data refers to the medical data obtained by medical staff when they use medical diagnostic equipment to monitor the target patient after contact with the patient.
[0033] Furthermore, the risk identification mechanism model is also used to receive subjective eyewitness data and objective diagnosis and treatment data from the real-time medical data of the target patient. The subjective eyewitness data is preprocessed by the data preprocessing model and then input into the risk identification mechanism model to output subjective risk factors; the objective diagnosis and treatment data is directly input into the risk identification mechanism model to output objective risk factors.
[0034] Furthermore, the risk identification data model receives subjective risk factors and objective risk factors, and through a preset association algorithm, finds matching objective risk factors from subjective risk factors; and finds matching subjective risk factors from objective risk factors, generating multiple risk factor association chains.
[0035] The principle and advantages of this invention are as follows: In this application, for the effective triage of patients after they experience acute chest pain symptoms, from the time they are transported by ambulance to the time they are contacted before hospital admission, the invention first acquires the patient's historical medical data, acute chest pain patient risk event data, and real-time medical data. These data are then processed through a risk identification mechanism model and a risk identification data model to generate a risk factor association chain. The association chain is used to assess the patient's risk status. The resulting risk assessment results can determine the triage process of the patient after admission by ambulance, greatly improving the efficiency of hospitals in receiving acute chest pain patients. Attached Figure Description
[0036] Figure 1 This is a flowchart of an embodiment of the present invention. Detailed Implementation
[0037] The following detailed description illustrates the specific implementation method:
[0038] The basic implementation examples are as follows: Figure 1 As shown: A method for matching risk events in patients with acute chest pain, comprising:
[0039] S1: Establish a database that stores the target patient's historical medical data and risk event data for patients with acute chest pain; and receive real-time medical data uploaded from external diagnostic and treatment devices and transmit it to the database for storage; S1 includes:
[0040] S1-1: Obtain the target patient's historical medical records, including local hospital medical records and out-of-town hospital medical records, extract the target patient's historical medical data from the historical medical records, encrypt the data, and then transmit it to the database for storage;
[0041] S1-2: Obtain medical treatment process data of patients with acute chest pain from local and remote medical records, extract acute chest pain knowledge data from the acute chest pain disease knowledge base, combine the medical treatment process data of patients with acute chest pain with the acute chest pain knowledge data to generate risk event data of patients with acute chest pain, and transmit it to the database for storage.
[0042] S1-3: Receive real-time medical data uploaded by the target patient from external diagnostic and treatment equipment, and transmit it to the database for storage.
[0043] In this embodiment, the target patient's historical medical records may include instances of treatment at local hospitals and treatment at hospitals in other locations. Therefore, there will be medical records at local hospitals and medical records at hospitals in other locations. Based on the sharing technology of existing medical systems, the medical records of the target patient can be shared. Therefore, the acquisition of the target patient's historical medical records in this application includes the target patient's medical records at local hospitals and hospitals in other locations.
[0044] Medical records can effectively reveal the surgical history, genetic history, and behavioral history of patients with acute chest pain, serving as reference data for the development of acute chest pain symptoms. However, simply knowing the target patient's medical history is insufficient, as it lacks support from medical literature. Therefore, an acute chest pain disease knowledge base was constructed, which collected medical literature related to acute chest pain diseases, including myocardial infarction, chest pain, cardiovascular diseases, and pulmonary embolism.
[0045] In medical literature, each type of disease has its corresponding risk events. For example, for patients with a history of myocardial infarction, behaviors that are likely to trigger acute chest pain in their daily lives can be considered as risk events before the onset of acute chest pain. Similarly, for other diseases such as cardiovascular disease and pulmonary embolism, the triggering events and behaviors that cause acute chest pain symptoms can be considered as their corresponding risk events.
[0046] Risk events for acute chest pain in medical literature are based on general data and do not match the performance of the target patients. Therefore, by matching the target patients' medical treatment process data with the risk events in the medical literature, we can identify the risk events that the target patients may have experienced after previous medical treatments, and these risk events are scientifically based, referable, authentic, and effective.
[0047] Finally, real-time medical data was obtained from the interactions between healthcare professionals and the target patient after the onset of acute chest pain.
[0048] This application addresses how to prevent, manage, and alert patients before the onset of acute chest pain symptoms. While existing technologies can address this, this application focuses on the effective triage of patients during the period from ambulance transport to pre-hospital contact after the onset of acute chest pain symptoms. Therefore, all information throughout this process is crucial and can influence the development of the patient's condition. Specifically, the patient's actions before the onset of acute chest pain symptoms can be obtained through methods such as monitoring footage, conversations with accompanying personnel, and whether the patient is carrying medical equipment. The monitoring footage will record the patient's actions before the onset of acute chest pain symptoms. The patient's experiences during illness, conversations with accompanying persons can reveal the patient's behavior during illness, and the medical equipment carried by the patient can indicate whether the patient has other illnesses and determine whether they are caused by other illnesses. Therefore, based on the above description, this type of data, which is not collected by ambulances or medical personnel using diagnostic equipment, belongs to subjective eyewitness data. In addition, it also includes objective diagnostic data. The objective diagnostic data described in this application refers to real-time diagnostic data of the patient's current status obtained by medical personnel during the ambulance's transport of the patient to the hospital using equipped diagnostic equipment, such as thermometers, heart rate monitoring devices, and blood pressure monitoring devices. This type of data is called objective diagnostic data.
[0049] In the above, this application uses subjective eyewitness data and objective diagnostic and treatment data to fully record the patient's information before and after the onset of acute chest pain symptoms, so as to provide complete data for subsequent risk assessment.
[0050] S2: The risk identification mechanism model is invoked to identify risk factors in the uploaded real-time medical data. The templates for these risk factors are derived from risk event data of patients with acute chest pain. S2 includes:
[0051] S2-1: Construct a risk identification mechanism model, train it based on risk event data of patients with acute chest pain, match the medical treatment process data of patients with acute chest pain with acute chest pain knowledge data, generate acute chest pain risk characteristics, and use them as risk factor templates;
[0052] S2-2: Input the real-time medical data of the target patient into the risk identification mechanism model. Subjective eyewitness data is preprocessed by the data preprocessing model before being input into the risk identification mechanism model, and subjective risk factors are output. Objective diagnosis and treatment data are directly input into the risk identification mechanism model, and objective risk factors are output.
[0053] In this embodiment, the risk identification mechanism model used is constructed through a deep learning network model to generate acute chest pain risk features. Specifically, after the risk identification mechanism model is generated, it is trained using risk event data of acute chest pain patients. The training samples are obtained by combining the historical medical treatment process data of acute chest pain patients with acute chest pain knowledge data. On the one hand, it includes treatment process data with patient characteristics, and on the other hand, it includes knowledge data about acute chest pain from medical literature, making the risk identification mechanism model more targeted in recognizing acute chest pain features.
[0054] Next, the real-time medical data of the target patient is input into the trained risk identification mechanism model. The real-time medical data includes subjective eyewitness data and objective diagnosis and treatment data. The subjective eyewitness data is preprocessed, such as language extraction and audio-visual data to text conversion, and then input into the risk identification mechanism model. The output is a subjective risk factor. For example, the monitoring screen shows that the patient has sudden acute chest pain without external influence, and the accompanying family members told the medical staff who came to the rescue that the patient has a history of coronary heart disease. Therefore, the subjective risk factor is acute chest pain caused by a history of coronary heart disease. As can be seen from the above, this type of risk, which is determined by external subjective factors without diagnosis and treatment, is referred to as a subjective risk factor in this application.
[0055] When objective diagnostic and treatment data is input into the risk identification mechanism model, objective risk factors can be identified. Specifically, the patient undergoes a preliminary examination using the diagnostic and treatment equipment equipped in the ambulance. For example, the patient is examined using a blood pressure monitor, pulse oximeter, and consciousness check. When the patient exhibits altered consciousness or significantly abnormal blood pressure, it can be preliminarily determined that the patient has relatively severe acute chest pain symptoms. Therefore, altered consciousness and significantly abnormal blood pressure are the objective risk factors in this application, and the accompanying risk events indicate that the patient has a higher risk of acute chest pain symptoms.
[0056] S3: Invoke the risk identification data model, using the risk factors output from the risk identification mechanism model as input; the risk identification data model generates a risk factor association chain based on the input risk factors according to a preset association algorithm, then performs a risk assessment on the risk factor association chain according to a preset risk level, and outputs the risk assessment result; wherein, S3 includes:
[0057] S3-1: Construct a risk identification data model based on a deep learning network. The risk identification data model receives subjective risk factors and objective risk factors, and finds matching objective risk factors from subjective risk factors through a preset association algorithm; and finds matching subjective risk factors from objective risk factors to generate multiple risk factor association chains.
[0058] S3-2: Construct a risk event assessment module. In the risk event assessment module, risk event assessment levels are preset based on acute chest pain knowledge data. The risk event assessment levels include individual scores and combined scores of several risk factors, and the corresponding risk levels are divided according to the total score.
[0059] S3-3: The risk event assessment module calls the risk event assessment level to assess the risk factor association chain and generate the corresponding risk assessment results.
[0060] In this embodiment, the risk identification data model is also constructed using a deep learning network model. Specifically, the risk identification data model receives subjective and objective risk factors output by the risk identification mechanism model, and matches the subjective and objective risk factors using an association algorithm. Specifically, the subjective risk factors mainly describe the patient's acute chest pain symptoms caused by external factors, while the objective risk factors are the patient's medical data after diagnosis using diagnostic equipment. Assuming that the subjective risk factors include four types (A, B, C, and D), and the objective risk factors include four indicators (a, b, c, and d) of the patient, the association algorithm... In the process of the procedure, subjective risk factor A is coronary heart disease, and its corresponding patient indicators include blood pressure and blood oxygen levels. Among the objective risk factors, a is blood pressure and b is blood oxygen levels. Therefore, subjective risk factor A, objective risk factor a, and objective risk factor b form a risk factor association chain. Similarly, objective risk factor a is blood pressure, and blood pressure is used to determine the type of disease, such as coronary heart disease and hypertension. In subjective risk factors, A represents coronary heart disease and B represents hypertension. Therefore, objective risk factor a, subjective risk factor A, and subjective risk factor B form a risk factor association chain.
[0061] The constructed risk event identification module presets risk event assessment levels based on acute chest pain knowledge data. In this embodiment, 0-30 represents low risk, 30-70 represents medium risk, and 70-100 represents high risk. Each subjective and objective risk factor also has a corresponding score. Multiple risk factor association chains are generated, their scores are added together, and the highest and lowest-scoring risk factor association chains are extracted. The remaining chains are then averaged to obtain the patient's average risk event score. The risk event identification module compares the average risk event score with the highest value of the extracted risk factor association chains. If the comparison result is not within a preset error threshold, it indicates that the risk event assessment is valid, and the average risk event score is used as the patient's risk level. If it is not within the preset error threshold, it indicates that the risk event assessment needs to be reviewed again by the attending physician. The result is then sent to the hospital platform receiving the patient for evaluation by the attending physician.
[0062] S4: Based on the risk assessment results, target patients are triaged for medical treatment.
[0063] In this embodiment, triage includes immediate admission to the intensive care unit or emergency room, monitoring and completion of relevant examinations, and routine medical treatment. The triage criteria in this application refer to existing related technologies. For example, the risk assessment results for immediate admission to the intensive care unit or emergency room are: (1) altered consciousness; (2) low arterial oxygen saturation (<90%), respiratory failure; (3) significantly abnormal blood pressure; (4) serious arrhythmia affecting hemodynamics; (5) history of coronary heart disease, which is not relieved by nitrate drugs in this attack; (6) history of Marfan syndrome, accompanied by severe hypertension; (7) accompanied by dyspnea and fullness of the chest on the affected side.
[0064] The risk assessment results for monitoring and completing relevant examinations include: (1) sudden onset of chest pain that is not relieved and is caused by long-term bed rest or long-distance travel; (2) sudden onset of chest pain that is not relieved and is caused by a confirmed tumor or lower extremity venous thrombosis; (3) sudden onset of chest pain accompanied by shortness of breath and no history of coronary heart disease; (4) accompanied by hemoptysis; (5) surgery within the past 4 weeks and a history of immobilization; (6) multiple cardiovascular risk factors; (7) poor long-term control of hypertension.
[0065] The risk assessment results of routine medical visits include: (1) chest pain without the above conditions; (2) chest pain with chest wall tenderness; (3) chest pain related to breathing; and (4) mild chest pain lasting more than a week.
[0066] In another embodiment of this example, an acute chest pain patient risk event matching system is also included, applied to the above-described acute chest pain patient risk event matching method, including a server and a medical end, wherein the server includes a database, a data receiving module, and a model building module;
[0067] The data receiving module is used to receive real-time medical data uploaded from external diagnostic and treatment equipment and transmit it to the database for storage;
[0068] The database is used to store the transmitted real-time medical data, as well as the target patient's historical medical data and risk event data for patients with acute chest pain. Specifically, the database stores the target patient's historical medical data and risk event data for patients with acute chest pain as follows:
[0069] Obtain the target patient's historical medical records, including local hospital records and out-of-town hospital records; extract the target patient's historical medical data from the historical medical records; encrypt the data and then transmit it to the database for storage.
[0070] Acquire medical treatment process data of patients with acute chest pain from local and remote medical records, extract acute chest pain knowledge data from the acute chest pain disease knowledge base, combine the medical treatment process data of patients with acute chest pain and the acute chest pain knowledge data to generate risk event data of patients with acute chest pain, and transmit it to the database for storage.
[0071] Real-time medical data includes subjective eyewitness data and objective diagnostic and treatment data. The subjective eyewitness data refers to the medical data obtained through monitoring equipment, accompanying personnel, and the patient's family members regarding the causes, manifestations, and outcomes of acute chest pain symptoms in the target patient. The objective diagnostic and treatment data refers to the medical data obtained by medical staff when monitoring the target patient using medical diagnostic and treatment equipment after contact with the patient.
[0072] The model building module is used to build a risk identification mechanism model and a risk identification data model. The risk identification mechanism model is used to identify risk factors in real-time medical data. The risk identification data model receives the identified risk factors, generates risk factor association chains according to a preset association algorithm, and then performs risk assessment on the risk factor association chains according to a preset risk level, and outputs the risk assessment results.
[0073] The risk identification mechanism model also receives subjective eyewitness data and objective diagnosis and treatment data from the target patient's real-time medical data. Subjective eyewitness data is preprocessed by a data preprocessing model before being input into the risk identification mechanism model, outputting subjective risk factors. Objective diagnosis and treatment data is directly input into the risk identification mechanism model, outputting objective risk factors. The risk identification data model receives subjective and objective risk factors and, through a pre-defined association algorithm, finds matching objective risk factors from subjective risk factors and matching subjective risk factors from objective risk factors, generating multiple risk factor association chains.
[0074] The medical terminal is used to receive risk assessment results and generate patient triage guidelines.
[0075] The above are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.
Claims
1. A method for matching risk events in patients with acute chest pain, characterized in that: include: S1: Establish a database that stores the target patient’s historical medical data and risk event data of patients with acute chest pain; It also receives real-time medical data uploaded from external diagnostic and treatment devices and transmits it to the database for storage. S2: Call the risk identification mechanism model to identify risk factors in the uploaded real-time medical data. The template of the risk factor is obtained by inversion based on the risk event data of patients with acute chest pain. S3: Call the risk identification data model and use the risk factors output from the risk identification mechanism model as input to the risk identification data model; The risk identification data model generates a risk factor association chain for the input risk factors according to a preset association algorithm, then performs a risk assessment on the risk factor association chain according to a preset risk level, and outputs the risk assessment result. S4: Based on the risk assessment results, target patients are triaged for medical treatment.
2. The method for matching risk events in patients with acute chest pain according to claim 1, characterized in that: S1 includes: S1-1: Obtain the target patient's historical medical records, including local hospital medical records and out-of-town hospital medical records, extract the target patient's historical medical data from the historical medical records, encrypt the data, and then transmit it to the database for storage; S1-2: Obtain medical treatment process data of patients with acute chest pain from local and remote medical records, extract acute chest pain knowledge data from the acute chest pain disease knowledge base, combine the medical treatment process data of patients with acute chest pain with the acute chest pain knowledge data to generate risk event data of patients with acute chest pain, and transmit it to the database for storage. S1-3: Receive real-time medical data uploaded by the target patient from external diagnostic and treatment equipment, and transmit it to the database for storage.
3. The method for matching risk events in patients with acute chest pain according to claim 2, characterized in that: In S1-3, real-time medical data includes subjective eyewitness data and objective diagnosis and treatment data. The subjective eyewitness data is medical data on the causes, manifestations and results of acute chest pain symptoms of the target patient obtained through monitoring equipment, accompanying personnel and patient's family members. The objective diagnostic data refers to the medical data obtained by medical staff when they use medical diagnostic equipment to monitor the target patient after contact with the patient.
4. The method for matching risk events in patients with acute chest pain according to claim 3, characterized in that: S2 includes: S2-1: Construct a risk identification mechanism model, train it based on risk event data of patients with acute chest pain, match the medical treatment process data of patients with acute chest pain with acute chest pain knowledge data, generate acute chest pain risk characteristics, and use them as risk factor templates; S2-2: Input the real-time medical data of the target patient into the risk identification mechanism model. Subjective eyewitness data is preprocessed by the data preprocessing model before being input into the risk identification mechanism model, and subjective risk factors are output. Objective diagnosis and treatment data are directly input into the risk identification mechanism model, and objective risk factors are output.
5. The method for matching risk events in patients with acute chest pain according to claim 4, characterized in that: S3 includes: S3-1: Construct a risk identification data model based on a deep learning network. The risk identification data model receives subjective risk factors and objective risk factors, and finds matching objective risk factors from subjective risk factors through a preset association algorithm; and finds matching subjective risk factors from objective risk factors to generate multiple risk factor association chains. S3-2: Construct a risk event assessment module. In the risk event assessment module, risk event assessment levels are preset based on acute chest pain knowledge data. The risk event assessment levels include individual scores and combined scores of several risk factors, and the corresponding risk levels are divided according to the total score. S3-3: The risk event assessment module calls the risk event assessment level to assess the risk factor association chain and generate the corresponding risk assessment results.
6. A risk event matching system for patients with acute chest pain, applied to the risk event matching method for patients with acute chest pain as described in any one of claims 1-5, characterized in that: It includes a server-side component and a medical-side component. The server-side component includes a database, a data receiving module, and a model building module. The data receiving module is used to receive real-time medical data uploaded from external diagnostic and treatment equipment and transmit it to the database for storage; The database is used to store the transmitted real-time medical data, as well as the target patient's historical medical data and risk event data of patients with acute chest pain. The model building module is used to build a risk identification mechanism model and a risk identification data model. The risk identification mechanism model is used to identify risk factors in real-time medical data. The risk identification data model receives the identified risk factors, generates risk factor association chains according to a preset association algorithm, and then performs risk assessment on the risk factor association chains according to a preset risk level, and outputs the risk assessment results. The medical terminal is used to receive risk assessment results and generate patient triage guidelines.
7. The risk event matching system for patients with acute chest pain according to claim 6, characterized in that: The database stores the target patient's historical medical data and risk event data for patients with acute chest pain, specifically: Obtain the target patient's historical medical records, including local hospital records and out-of-town hospital records; extract the target patient's historical medical data from the historical medical records; encrypt the data and then transmit it to the database for storage. Data on the medical treatment process of patients with acute chest pain from local and remote medical records is obtained, and knowledge data on acute chest pain is extracted from the acute chest pain disease knowledge base. The medical treatment process data of patients with acute chest pain is combined with the knowledge data on acute chest pain to generate risk event data of patients with acute chest pain, which is then transmitted to the database for storage.
8. The risk event matching system for patients with acute chest pain according to claim 7, characterized in that: The real-time medical data includes subjective eyewitness data and objective diagnosis and treatment data. The subjective eyewitness data is medical data on the causes, manifestations and outcomes of acute chest pain symptoms in the target patient, obtained through monitoring equipment, accompanying personnel and patient's family members. The objective diagnostic data refers to the medical data obtained by medical staff when they use medical diagnostic equipment to monitor the target patient after contact with the patient.
9. The risk event matching system for patients with acute chest pain according to claim 8, characterized in that: The risk identification mechanism model is also used to receive subjective eyewitness data and objective diagnosis and treatment data from the real-time medical data of the target patient. The subjective eyewitness data is preprocessed by the data preprocessing model and then input into the risk identification mechanism model to output subjective risk factors; the objective diagnosis and treatment data is directly input into the risk identification mechanism model to output objective risk factors.
10. The acute chest pain patient risk event matching system according to claim 9, characterized in that: The risk identification data model receives subjective risk factors and objective risk factors, and finds matching objective risk factors from the subjective risk factors through a preset association algorithm. And find matching subjective risk factors from objective risk factors to generate multiple risk factor association chains.
