AI-integrated acute chest pain rapid identification and evaluation system and method

Abstract

The invention belongs to the technical field of medical health management, and particularly relates to an AI-integrated acute chest pain rapid identification and evaluation system and method, and the method comprises the steps: firstly monitoring the sign data of a target patient in real time; then generating a distributed file storage unit according to a preset AI prompt word, and respectively storing the monitored sign data of the target patient according to the category of the AI prompt word; meanwhile, historical diagnosis data of the acute chest pain patient in the target hospital is stored; then, a big data AI model is generated, and the big data AI model is accessed to the Internet and a distributed file storage unit for training; and finally, inputting the physical sign data of the data into the trained big data AI model, and outputting an acute chest pain recognition result of the target patient. According to the system, the physiological parameters of the patient can be monitored in real time, and meanwhile, key data during morbidity are uploaded to the medical emergency center, so that early recognition, quick response and precise treatment are realized, and the treatment efficiency and success rate are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the field of medical health management technology, and in particular to an acute chest pain rapid identification and evaluation system and method integrated with AI. Background Art

[0002] Acute chest pain is an emergency symptom of cardiovascular disease. Its suddenness and high risk require that the treatment process must be rapid and accurate. At present, although there are chest pain centers and chest pain treatment units, there are deficiencies in information collection, positioning and rapid response in the early stage of the patient's illness. Especially in the case of inconvenient transportation, the time interval from the patient's perception of symptoms to professional treatment is long, which directly affects the treatment effect and the patient's quality of life. Summary of the invention

[0003] The technical problem solved by the present invention is to provide an acute chest pain rapid identification and evaluation system and method integrated with AI to monitor the patient's physiological parameters in real time, and upload key data at the time of onset to the medical emergency center, thereby achieving early identification, rapid response and precise treatment, and significantly improving the treatment efficiency and success rate.

[0004] The basic solution provided by the present invention: an acute chest pain rapid identification and assessment system integrated with AI, comprising:

[0005] Monitoring module: used to monitor the vital signs data of target patients in real time;

[0006] Data storage module: used to generate a distributed file storage unit according to preset AI prompt words, and store the vital sign data of the monitored target patients according to the AI ​​prompt word categories; the data storage module is also used to store the historical diagnosis data of acute chest pain patients in the target hospital;

[0007] AI module: used to generate big data AI models and access the Internet and data storage modules for training;

[0008] Data analysis module: used to input the vital sign data in the data storage module into the trained big data AI model, and output the acute chest pain identification results of the target patient.

[0009] Furthermore, the monitoring module includes a physiological characteristic monitoring unit, a biomarker identification unit and a clinical sign recording unit. The physiological characteristic monitoring unit is used to obtain the physiological characteristic parameters of the target patient based on the diagnostic and treatment equipment; the biomarker identification unit is used to obtain the biomarker identification result of the target patient based on the identification equipment; the clinical characteristic recording unit is used to record the clinical characteristics of the target patient in a multi-source manner and construct a clinical characteristic knowledge graph.

[0010] Furthermore, the data storage module includes a distributed storage unit and a historical data storage unit. The distributed storage unit is used to construct a storage file according to a preset AI prompt word, and bind the storage file identification and reading information according to the corresponding AI prompt word; the distributed storage unit is also used to store the vital sign data of the target patient according to the storage file category; the historical data storage unit is used to store the historical diagnosis data of acute chest pain patients in the target hospital.

[0011] Furthermore, the AI ​​module includes an AI model construction unit, a corpus generation unit, and an AI model training unit. The AI ​​model construction unit is used to construct a big data AI model; the corpus generation unit is used to generate a corpus based on literature data in the field of acute chest pain and historical diagnosis data of acute chest pain patients in various hospitals; the AI ​​model training unit is used to divide the data stored in the corpus into diagnostic process data and corresponding diagnostic result data, and input them into the big data AI model for training.

[0012] Furthermore, the data analysis module includes a biomarker analysis unit, a physiological feature recognition unit, and a clinical feature recognition unit, wherein the biomarker analysis unit is used to construct a biomarker analysis model based on a big data AI model, analyze the biomarker identification results of the target patient, and generate a biomarker diagnosis result of the target patient;

[0013] The physiological characteristic recognition unit is used to build a physiological characteristic recognition model based on the big data AI model, diagnose and identify the physiological characteristic parameters of the target patient, and generate a physiological diagnosis result of the target patient;

[0014] The clinical feature recognition unit is used to build an acute chest pain clinical feature recognition model based on a big data AI model, analyze the clinical feature knowledge graph of the target patient, and generate the chest pain clinical feature performance results of the target patient.

[0015] The AI-integrated acute chest pain rapid identification and assessment method is applied to the AI-integrated acute chest pain rapid identification and assessment system, including:

[0016] S1: Real-time monitoring of the target patient’s vital sign data;

[0017] S2: Generate a distributed file storage unit according to the preset AI prompt words, and store the vital sign data of the monitored target patients according to the AI ​​prompt word categories; and store the historical diagnosis data of acute chest pain patients in the target hospital at the same time;

[0018] S3: Generates big data AI models and connects to the Internet and distributed file storage units for training;

[0019] S4: Input the vital sign data into the trained big data AI model and output the acute chest pain recognition results of the target patient.

[0020] An electronic device includes a processor and a memory, wherein the memory stores programs or instructions, and the processor executes the above-mentioned AI-integrated rapid identification and assessment method for acute chest pain by calling the programs or instructions stored in the memory.

[0021] A computer-readable storage medium stores a program or instruction that enables a computer to execute the AI-integrated rapid identification and assessment method for acute chest pain as described above.

[0022] The principles and advantages of the present invention are as follows: in the scheme of the present invention, after acquiring the vital sign data of the target patient, a big data AI model is constructed to perform rapid assessment and diagnosis of acute chest pain. Specifically, the acquired vital sign data include physiological sign parameters, biomarker identification results, and clinical characteristic knowledge graphs. Based on these vital sign data, on the one hand, the trained big data AI model can quickly identify and evaluate the condition of the target patient. On the other hand, these data are distributed and classified and stored according to preset AI prompt words, which can improve the efficiency of subsequent big data AI models in data extraction.

[0023] As for how to train the big data AI model, in addition to connecting the big data AI model to the Internet for training, this application also connects the big data AI model to the historical diagnosis data of acute chest pain patients in the target medical institution for training. The big data AI model obtained in this way, whether in terms of analysis data or diagnosis results, is more in line with the actual situation of the actual target medical institution.

[0024] In the specific analysis and evaluation process of the big data AI model, a biomarker analysis model, a physiological characteristic recognition model, and an acute chest pain clinical characteristic recognition model were constructed based on the big data AI model. In this way, the biomarker diagnosis results of the target patients, the physiological diagnosis results of the target patients, and the chest pain clinical characteristic performance results of the target patients were obtained as the rapid identification and evaluation results of the target patients, thereby improving the treatment efficiency and success rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a functional block diagram of an embodiment of the present invention;

[0026] Figure 2 is a flowchart of an embodiment of the present invention;

[0027] Figure 3 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following is further described in detail through specific implementation methods:

[0029] The symbols in the drawings of the specification include: electronic device 400 , processor 401 , memory 402 , input device 403 , and output device 404 .

[0030] Embodiment 1:

[0031] Embodiment 1 is basically as shown in the attached Figure 1 As shown: an acute chest pain rapid identification and assessment system integrating AI, including a monitoring module, a data storage module, an AI model and a data analysis module, wherein:

[0032] The monitoring module is used to monitor the vital sign data of the target patient in real time. In this embodiment, the monitoring module includes a physiological characteristic monitoring unit, a biomarker identification unit and a clinical characteristic recording unit. The physiological characteristic monitoring unit is used to obtain the physiological characteristic parameters of the target patient based on the diagnostic and treatment equipment; the biomarker identification unit is used to obtain the biomarker identification result of the target patient based on the identification equipment; the clinical characteristic recording unit is used to record the clinical characteristics of the target patient in a multi-source manner and construct a clinical characteristic knowledge graph.

[0033] Specifically, physiological characteristic parameters include electrocardiogram, X-ray examination, etc. of the target patient, and biomarker identification includes protein markers or enzyme markers. Such markers can effectively reflect the identification of acute chest pain, risk stratification and treatment decisions of the target patient; the clinical characteristic knowledge graph determines the clinical characteristic indicators of acute chest pain according to the acute chest pain diagnosis process, and describes it in a tree diagram. For example, according to the existing acute chest pain diagnosis process, the patient's acute chest pain clinical characteristic indicators include pain location, pain nature, past history, etc., and in the clinical characteristics of the pain location, the target patient presents left chest pain, the pain nature is squeezing pain and is often accompanied by a sense of oppression or suffocation, and there is a history of angina pectoris in the patient's past history. Therefore, through this type of knowledge graph, the symptoms of the target patient can be effectively recorded, and the recording method adopts a multi-source recording method in this application, for example, including recording voice information after questioning the target patient in a conscious state, and extracting keywords in the voice information through a semantic analysis algorithm; or manually questioning the accompanying personnel and manually recording.

[0034] The data storage module is used to generate a distributed file storage unit according to preset AI prompt words, and store the vital sign data of the monitored target patients according to the AI ​​prompt word categories; the data storage module is also used to store the historical diagnosis data of acute chest pain patients in the target hospital; wherein the data storage module includes a distributed storage unit and a historical data storage unit, the distributed storage unit is used to construct a storage file according to the preset AI prompt words, and bind the storage file identification and reading information according to the corresponding AI prompt words; the distributed storage unit is also used to store the vital sign data of the target patients according to the storage file categories; the historical data storage unit is used to store the historical diagnosis data of acute chest pain patients in the target hospital.

[0035] In this embodiment, the preset AI prompt words are preset based on the indicator characteristics of acute chest pain, and are bound to the recognition and reading information of the constructed storage file, which facilitates rapid identification when extracting data later. The historical diagnosis data of acute chest pain patients in the target hospital is helpful for the subsequent training of the AI ​​model.

[0036] The AI ​​module is used to generate a big data AI model and access the Internet and data storage module for training; wherein, the AI ​​module includes an AI model construction unit, a corpus generation unit, and an AI model training unit, wherein the AI ​​model construction unit is used to construct and generate a big data AI model; the corpus generation unit is used to generate a corpus based on literature data in the field of acute chest pain and historical diagnosis data of acute chest pain patients in various hospitals; the AI ​​model training unit is used to divide the data stored in the corpus into diagnostic process data and corresponding diagnostic result data, and input them into the big data AI model for training.

[0037] In this embodiment, the constructed big data AI model is generated based on the existing AI model. The difference is that the construction of the corpus and the training process of the model are different. Specifically, the corpus is generated based on literature data in the field of acute chest pain and historical diagnosis data of acute chest pain in various hospitals. These data often include pre-hospital diagnosis records, treatment records, and rehabilitation records of medical patients. In order to better train the big data AI model, these data are divided into diagnosis process data and corresponding diagnosis result data. The purpose of this division is that the big data AI model can better summarize and generate user needs in the actual diagnosis process during the training process. For example, in the pre-hospital evaluation process, the big data AI model pays more attention to the pre-hospital diagnosis content in the diagnosis process data during analysis and processing, and will not call too much subsequent diagnosis result data, thereby reducing resource waste.

[0038] Data analysis module: used to input the vital sign data in the data storage module into the trained big data AI model, and output the acute chest pain recognition result of the target patient, wherein the data analysis module includes a biomarker analysis unit, a physiological feature recognition unit and a clinical feature recognition unit, and the biomarker analysis unit is used to construct a biomarker analysis model based on the big data AI model, analyze the biomarker identification results of the target patient, and generate the biomarker diagnosis results of the target patient;

[0039] The physiological characteristic recognition unit is used to build a physiological characteristic recognition model based on the big data AI model, diagnose and identify the physiological characteristic parameters of the target patient, and generate a physiological diagnosis result of the target patient;

[0040] The clinical feature recognition unit is used to build an acute chest pain clinical feature recognition model based on a big data AI model, analyze the clinical feature knowledge graph of the target patient, and generate the chest pain clinical feature performance results of the target patient.

[0041] In the present application, compared with the existing analysis model that performs mixed analysis on the user's disease data and results in low accuracy, the present application differentiates the data required for the diagnosis of acute chest pain into physiological diagnosis, biomarker diagnosis and chest pain clinical manifestation diagnosis. In other embodiments of this embodiment, it can be differentiated into more types of data types according to different medical institution systems, and then differentiated through corresponding recognition models, so that the diagnosis is more targeted and the results are clearer.

[0042] like Figure 2 As shown, in another embodiment of this embodiment, it also includes an acute chest pain rapid identification and evaluation method integrated with AI, which is applied to the above-mentioned acute chest pain rapid identification and evaluation system integrated with AI, including:

[0043] S1: Real-time monitoring of the target patient’s vital sign data;

[0044] S2: Generate a distributed file storage unit according to the preset AI prompt words, and store the vital sign data of the monitored target patients according to the AI ​​prompt word categories; and store the historical diagnosis data of acute chest pain patients in the target hospital at the same time;

[0045] S3: Generates big data AI models and connects to the Internet and distributed file storage units for training;

[0046] S4: Input the vital sign data into the trained big data AI model and output the acute chest pain recognition results of the target patient.

[0047] Also included is an electronic device such as Figure 3 As shown, the electronic device 400 includes one or more processors 401 and a memory 402 .

[0048] The processor 401 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 400 to perform desired functions.

[0049] The memory 402 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 401 may run the program instructions to implement the acute chest pain rapid identification and assessment method with integrated AI of any embodiment of the present invention described above and / or other desired functions. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0050] In one example, the electronic device 400 may further include: an input device 403 and an output device 404, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, etc. The output device 404 may output various information to the outside, including early warning information, braking force, etc. The output device 404 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0051] Of course, to simplify, Figure 3 Only some of the components related to the present invention in the electronic device 400 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 400 may also include any other appropriate components.

[0052] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method for rapid identification and assessment of acute chest pain integrating AI provided in any embodiment of the present invention.

[0053] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0054] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the method for rapid identification and assessment of acute chest pain with integrated AI provided in any embodiment of the present invention.

[0055] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0056] Embodiment 2:

[0057] The difference between Example 2 and Example 1 is that it also includes a data structuring module and an evaluation and optimization module. The data structuring module is used to split the acute chest pain recognition results and the historical diagnostic data of acute chest pain patients stored in the data storage module according to the diagnostic process generated by the target medical institution and reorganize them into diagnostic structured data; the evaluation and optimization module is used to match the diagnostic structured data of the acute chest pain recognition results with the structured data of the historical diagnostic data, and push the historical diagnostic data that meets the matching requirements to the doctor based on the matching results.

[0058] In this embodiment, the use of structured data helps to improve the matching accuracy between diagnostic data. When the historical diagnostic results in the matching results are pushed to doctors, doctors in remote areas with scarce medical resources can more effectively receive detailed information on real cases, which helps doctors in such medical institutions make correct diagnoses.

[0059] The above are only embodiments of the present invention. Common knowledge such as the known specific structures and characteristics in the scheme is not described in detail here. Ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. An AI-integrated rapid recognition and assessment system for acute chest pain, characterized by: include: Monitoring module: used to monitor the vital signs data of target patients in real time; Data storage module: used to generate a distributed file storage unit according to preset AI prompt words, and store the vital sign data of the monitored target patients according to the AI ​​prompt word categories; the data storage module is also used to store the historical diagnosis data of acute chest pain patients in the target hospital; AI module: used to generate big data AI models and access the Internet and data storage modules for training; Data analysis module: used to input the vital sign data in the data storage module into the trained big data AI model, and output the acute chest pain identification results of the target patient.

2. The AI-integrated acute chest pain rapid identification and assessment system according to claim 1 is characterized by: The monitoring module includes a physiological characteristic monitoring unit, a biomarker identification unit and a clinical sign recording unit, wherein the physiological characteristic monitoring unit is used to obtain physiological characteristic parameters of the target patient based on the diagnosis and treatment equipment; The biomarker identification unit is used to obtain the biomarker identification result of the target patient based on the identification device; the clinical characteristic recording unit is used to record the clinical characteristics of the target patient in a multi-source manner and construct a clinical characteristic knowledge graph.

3. The AI-integrated acute chest pain rapid identification and assessment system according to claim 2 is characterized by: The data storage module includes a distributed storage unit and a historical data storage unit. The distributed storage unit is used to construct a storage file according to a preset AI prompt word, and bind the storage file identification and reading information according to the corresponding AI prompt word; the distributed storage unit is also used to store the vital sign data of the target patient according to the storage file category; the historical data storage unit is used to store the historical diagnosis data of acute chest pain patients in the target hospital.

4. The AI-integrated acute chest pain rapid identification and assessment system according to claim 3 is characterized by: The AI ​​module includes an AI model construction unit, a corpus generation unit, and an AI model training unit. The AI ​​model construction unit is used to construct a big data AI model; the corpus generation unit is used to generate a corpus based on literature data in the field of acute chest pain and historical diagnosis data of acute chest pain patients in various hospitals; the AI ​​model training unit is used to divide the data stored in the corpus into diagnostic process data and corresponding diagnostic result data, and input them into the big data AI model for training.

5. The AI-integrated acute chest pain rapid identification and assessment system according to claim 4 is characterized by: The data analysis module includes a biomarker analysis unit, a physiological feature recognition unit, and a clinical feature recognition unit. The biomarker analysis unit is used to build a biomarker analysis model based on a big data AI model, analyze the biomarker identification results of the target patient, and generate a biomarker diagnosis result of the target patient; The physiological characteristic recognition unit is used to build a physiological characteristic recognition model based on the big data AI model, diagnose and identify the physiological characteristic parameters of the target patient, and generate a physiological diagnosis result of the target patient; The clinical feature recognition unit is used to build an acute chest pain clinical feature recognition model based on a big data AI model, analyze the clinical feature knowledge graph of the target patient, and generate the chest pain clinical feature performance results of the target patient.

6. A method for rapid identification and assessment of acute chest pain integrated with AI, applied to a system for rapid identification and assessment of acute chest pain integrated with AI as described in any one of claims 1 to 5 above, characterized in that: include: S1: Real-time monitoring of the target patient’s vital sign data; S2: Generate a distributed file storage unit according to the preset AI prompt words, and store the vital sign data of the monitored target patients according to the AI ​​prompt word categories; and store the historical diagnosis data of acute chest pain patients in the target hospital at the same time; S3: Generates big data AI models and connects to the Internet and distributed file storage units for training; S4: Input the vital sign data into the trained big data AI model and output the acute chest pain recognition results of the target patient.

7. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores programs or instructions, and the processor executes the method for rapid identification and assessment of acute chest pain with integrated AI as described in claim 6 above by calling the programs or instructions stored in the memory.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, which enables a computer to execute the AI-integrated rapid identification and assessment method for acute chest pain as described in claim 6 above.

Images