Chest pain type determination system, program product, electronic device, and storage medium

Abstract

The invention provides a chest pain type determination system, a program product, an electronic device and a storage medium, the program product comprises a computer program or instruction, and when the computer program or instruction is executed by a processor, the following method steps are executed: determining a chest pain risk level according to multivariate medical information of a patient; if the level is the first level, analyzing multivariate medical information according to first guide information for any preset type of high-risk chest pain disease to obtain a preliminary result; according to the preliminary results corresponding to the various types of high-risk chest pain diseases, determining a target high-risk chest pain type; if the first level is the first level, analyzing the multivariate medical information by referring to second guide information for any preset type of low-risk chest pain disease to obtain a preliminary result; and determining a target low-risk chest pain type according to the preliminary results corresponding to the various types of low-risk chest pain diseases. And determining a corresponding diagnosis and treatment strategy for each target chest pain type. Therefore, the target chest pain type can be quickly and accurately determined, and a diagnosis and treatment strategy can be given, so that a doctor can be assisted to quickly and accurately diagnose and treat.

Description

Technical Field

[0001] This application relates to the field of information processing, and more specifically, to a chest pain type determination system, program product, electronic device, and storage medium. Background Technology

[0002] Chest pain is a common symptom in the emergency department, and its causes are complex, encompassing a broad spectrum from life-threatening emergencies to benign functional disorders. Based on clinical risk assessments using relevant technologies, chest pain can be categorized into high-risk and low-risk types. High-risk chest pain is characterized by rapid onset, rapid progression, and extremely high mortality, requiring physicians to make an accurate diagnosis and initiate targeted treatment within a very short timeframe. Any delay or misdiagnosis can lead to irreversible and serious consequences. Similarly, low-risk chest pain also requires prompt and accurate diagnosis and targeted treatment.

[0003] It is evident that both high-risk and low-risk chest pain require doctors to make rapid and accurate diagnoses. However, the diagnostic techniques available to assist doctors in this process are not very effective. Summary of the Invention

[0004] The purpose of this application is to provide a chest pain type determination system, program product, electronic device and storage medium to quickly and accurately determine the target chest pain type, so as to assist doctors in making a quick and accurate diagnosis.

[0005] In a first aspect, embodiments of this application provide a chest pain type determination system, comprising: a case summary module for acquiring diverse medical information of a patient; a chest pain diagnosis module for determining a chest pain risk level based on the diverse medical information; the chest pain risk level includes a first level and a second level, wherein the risk level of the first level is greater than the risk level of the second level; if the chest pain risk level is the first level, then for any preset type of high-risk chest pain disease, the diverse medical information is analyzed with reference to first guidance information for identifying such high-risk chest pain disease to obtain a preliminary result indicating whether it is such high-risk chest pain disease; and, based on the preliminary results corresponding to each type of high-risk chest pain disease, a target high-risk chest pain type is determined; if the chest pain risk level is the second level, then for any preset type of low-risk chest pain disease, the diverse medical information is analyzed with reference to second guidance information for identifying such low-risk chest pain disease to obtain a preliminary result indicating whether it is such low-risk chest pain disease; and, based on the preliminary results corresponding to each type of low-risk chest pain disease, a target low-risk chest pain type is determined.

[0006] Optionally, it also includes: a scale scoring module, used to score the acquired multivariate medical information based on different preset scoring rules; wherein the medical information corresponding to different preset scoring rules is different; for any score, if the score is greater than the corresponding scoring threshold, an early warning is issued.

[0007] Optionally, it also includes: a treatment planning module, used to determine the treatment strategy corresponding to the target high-risk chest pain type or the target low-risk chest pain type based on the equipped medical means information.

[0008] Secondly, embodiments of this application provide a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the following method steps are performed: acquiring multiple medical information of a patient; determining a chest pain risk level based on the multiple medical information; the chest pain risk level includes a first level and a second level, wherein the risk level of the first level is greater than the risk level of the second level; if the chest pain risk level is the first level, then for any preset type of high-risk chest pain disease, analyzing the multiple medical information with reference to first guidance information for identifying that type of high-risk chest pain disease to obtain a preliminary result indicating whether it is that type of high-risk chest pain disease; and determining a target high-risk chest pain type based on the preliminary results corresponding to each type of high-risk chest pain disease; if the chest pain risk level is the second level, then for any preset type of low-risk chest pain disease, analyzing the multiple medical information with reference to second guidance information for identifying that type of low-risk chest pain disease to obtain a preliminary result indicating whether it is that type of low-risk chest pain disease; and determining a target low-risk chest pain type based on the preliminary results corresponding to each type of low-risk chest pain disease. The process described above for determining the type of chest pain simulates the logical thinking of a more experienced physician during diagnosis. This is not only easier to understand but also helps improve the efficiency and accuracy of identifying the target chest pain type. Furthermore, the use of diverse medical information broadens the diagnostic dimensions, and relevant guidelines were consulted during the determination of the target chest pain type, thereby further improving the accuracy of the target chest pain type identification.

[0009] Optionally, acquiring the patient's diverse medical information includes: acquiring the patient's key indicator information; and acquiring the patient's abnormal non-key indicator information; wherein, in the process of determining or excluding any type of chest pain, the importance of the key indicator information is greater than the importance of the non-key indicator information. This adaptive acquisition of different medical information balances the efficiency and accuracy of determining the target chest pain type.

[0010] Optionally, after acquiring the patient's diverse medical information, the method further includes: scoring the acquired diverse medical information based on different preset scoring rules; wherein the different preset scoring rules correspond to different medical information; and for any score, if the score is greater than the corresponding scoring threshold, an early warning is issued. This adds a scoring process to the determination of the target chest pain type, which helps improve the accuracy of the target chest pain type. Furthermore, when the score is greater than the corresponding scoring threshold, it can be determined that the patient is in a high-risk condition, thus enabling an early warning, which helps assist doctors in making timely relevant diagnostic and treatment measures.

[0011] Optionally, the multivariate medical information includes electrocardiogram (ECG) information; and the step of determining the chest pain risk level based on the multivariate medical information includes: analyzing the ECG information with reference to guidelines related to chest pain diseases to identify abnormal ECG information; and determining the chest pain risk level based on the abnormal ECG information and other medical information. This approach focuses on analyzing ECG information and combining it with other medical information to determine the chest pain risk level, which helps improve the accuracy of chest pain risk assessment.

[0012] Optionally, the method further includes: identifying emergency interventions based on the abnormal electrocardiogram information and other medical information, and marking the emergency interventions; and / or, if the chest pain risk level is the first level, determining action guidance information. This allows for the marking of emergency interventions and the determination of action guidance information at high-risk levels, which helps assist doctors in providing timely and targeted treatment.

[0013] Optionally, the types of high-risk chest pain diseases include STEMI, NSTEMI, AD, UA, and APE; and, for any of the preset types of high-risk chest pain diseases, the multivariate medical information is analyzed with reference to first guidance information used to identify that type of high-risk chest pain disease to obtain a preliminary result characterizing whether it is that type of high-risk chest pain disease, including: for some or all of the high-risk chest pain diseases among STEMI, NSTEMI, and UA, the medical information related to that type of high-risk chest pain disease is analyzed with reference to the first guidance information to determine whether the patient has ACS; wherein, if the patient has ACS, high-risk is preliminarily determined. The chest pain conditions can be classified as STEMI, NSTEMI, or UA, or all of these. For high-risk chest pain conditions of type APE, medical information related to this type of high-risk chest pain is analyzed according to the first guideline to determine whether pulmonary embolism is present. If pulmonary embolism is present, the high-risk chest pain condition is preliminarily identified as type APE. For high-risk chest pain conditions of type AD, medical information related to this type of high-risk chest pain is analyzed according to the first guideline to determine whether acute aortic syndrome is present. If acute aortic syndrome is present, the high-risk chest pain condition is preliminarily identified as type AD. This allows for adaptive analysis of relevant medical information according to the first guideline for each type of high-risk chest pain condition, facilitating the preliminary determination of whether it is the corresponding type of high-risk chest pain condition. This approach helps improve the accuracy and completeness of the determination process and reduces the risk of missed or misdiagnosis.

[0014] Optionally, the types of low-risk chest pain diseases include non-ACS-related types, respiratory system-related types, vascular system-related types, digestive system-related types, chest wall disease-related types, and other disease-related types; and, for any preset type of low-risk chest pain disease, the multivariate medical information is analyzed with reference to the second guideline information used to identify that type of low-risk chest pain disease to obtain a preliminary result characterizing whether it is that type of low-risk chest pain disease, including: for non-ACS-related low-risk chest pain diseases, analyzing medical information related to that type of low-risk chest pain disease with reference to the second guideline information to preliminarily determine whether the patient has non-ACS-related low-risk chest pain disease; for respiratory system-related low-risk chest pain diseases, analyzing medical information related to that type of low-risk chest pain disease with reference to the second guideline information to preliminarily determine whether the patient has respiratory system-related low-risk chest pain disease. For low-risk chest pain related to the vascular system, the medical information related to this type of low-risk chest pain is analyzed in accordance with the second guideline information to preliminarily determine whether the patient has a low-risk chest pain disease related to the vascular system; for low-risk chest pain related to the digestive system, the medical information related to this type of low-risk chest pain is analyzed in accordance with the second guideline information to preliminarily determine whether the patient has a low-risk chest pain disease related to the digestive system; for low-risk chest pain related to thoracic diseases, the medical information related to this type of low-risk chest pain is analyzed in accordance with the second guideline information to preliminarily determine whether the patient has a low-risk chest pain disease related to other diseases. In this way, for each type of low-risk chest pain, adaptive analysis of relevant medical information can be performed according to the second guideline information, facilitating the preliminary determination of whether the patient has a low-risk chest pain disease of the corresponding type. This helps improve the accuracy and completeness of the determination process and reduces the risk of missed or misdiagnosis.

[0015] Optionally, the method further includes: determining the treatment strategy corresponding to the target high-risk chest pain type or the target low-risk chest pain type based on the equipped medical information. This allows for the determination of the corresponding treatment strategy after identifying the target chest pain type, thereby helping doctors to quickly provide targeted treatment.

[0016] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the following method steps are performed: Obtain diverse medical information from patients; Based on the aforementioned multi-dimensional medical information, a chest pain risk level is determined; the chest pain risk level includes a first level and a second level, with the risk level of the first level being greater than that of the second level. If the chest pain risk level is the first level, then for any type of high-risk chest pain disease, the multivariate medical information is analyzed with reference to the first guideline information used to identify the type of high-risk chest pain disease to obtain a preliminary result indicating whether it is the type of high-risk chest pain disease; and, based on the preliminary results corresponding to each type of high-risk chest pain disease, the target high-risk chest pain type is determined. If the chest pain risk level is the second level, then for any preset type of low-risk chest pain disease, the multivariate medical information is analyzed with reference to the second guideline information used to identify the type of low-risk chest pain disease to obtain a preliminary result indicating whether it is the type of low-risk chest pain disease; and, based on the preliminary results corresponding to each type of low-risk chest pain disease, the target low-risk chest pain type is determined.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the following method steps: Obtain diverse medical information from patients; Based on the aforementioned multi-dimensional medical information, a chest pain risk level is determined; the chest pain risk level includes a first level and a second level, with the risk level of the first level being greater than that of the second level. If the chest pain risk level is the first level, then for any type of high-risk chest pain disease, the multivariate medical information is analyzed with reference to the first guideline information used to identify the type of high-risk chest pain disease to obtain a preliminary result indicating whether it is the type of high-risk chest pain disease; and, based on the preliminary results corresponding to each type of high-risk chest pain disease, the target high-risk chest pain type is determined. If the chest pain risk level is the second level, then for any preset type of low-risk chest pain disease, the multivariate medical information is analyzed with reference to the second guideline information used to identify the type of low-risk chest pain disease to obtain a preliminary result indicating whether it is the type of low-risk chest pain disease; and, based on the preliminary results corresponding to each type of low-risk chest pain disease, the target low-risk chest pain type is determined.

[0018] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of a method for determining the type of chest pain provided in an embodiment of this application; Figure 2 A structural block diagram of a chest pain type determination system provided in this application embodiment; Figure 3 This is a schematic diagram of an electronic device for performing a method for determining the type of chest pain, provided as an embodiment of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] It should be noted that, unless otherwise specified, the embodiments or technical features in the embodiments of this application may be combined.

[0024] In related technologies, measures intended to assist doctors in diagnosis are not very effective, specifically in quickly and accurately determining the type of chest pain (i.e., chest pain type), thus failing to truly help doctors make a rapid and accurate diagnosis. Specifically, determining the type of chest pain mainly faces the following challenges: (1) The symptoms of high-risk chest pain types are atypical, making identification difficult. Specifically, although the typical symptoms of high-risk chest pain diseases are clearly described in textbooks, the actual symptoms of patients vary greatly. Atypical symptoms are very likely to overlap with those of non-ACS (Acute Coronary Syndrome) cardiac chest pain (such as pericarditis, myocarditis), respiratory diseases (such as pneumonia, pleurisy, pneumothorax), digestive diseases (such as gastroesophageal reflux disease, hiatal hernia), thoracic diseases (such as costochondritis), and other non-cardiac chest pain, which increases the difficulty of identifying the type of chest pain.

[0025] (2) It is necessary to rely on multi-dimensional medical information to accurately determine the type of chest pain.

[0026] In response to the challenges mentioned above, different doctors may arrive at different diagnoses. Inexperienced doctors may also lead to misdiagnosis or missed diagnosis, thus failing to provide timely and targeted treatment for patients.

[0027] Among related technologies, the measures used to assist doctors in diagnosis mainly include the following categories: (1) No specific type of chest pain is determined; (2) Only high-risk chest pain types should be identified; (3) Determined based on a single piece of medical information; It is evident that the above measures cannot quickly and accurately determine the type of chest pain (high-risk chest pain type and low-risk chest pain type), and therefore cannot effectively assist doctors.

[0028] To address the aforementioned issues, this application provides a chest pain type determination system, program product, electronic device, and storage medium. Furthermore, this application conducts multi-dimensional analysis of the patient's medical information in accordance with national chest pain guidelines and simulates the doctor's thought process to determine the type. This helps improve the efficiency and accuracy of chest pain type determination, thereby assisting doctors in quickly and accurately diagnosing chest pain diseases.

[0029] It should be noted that the defects in the solutions in the above-mentioned related technologies were discovered by the inventors after long-term practice and careful research. Therefore, the discovery process of the above-mentioned problems and the solutions proposed by the embodiments of the present invention in the following text should all be contributions made by the inventors to the present invention during the process of the present invention.

[0030] In some application scenarios, the above-mentioned method for determining the type of chest pain can be applied to terminal devices (such as medical devices, desktop computers, laptops, etc. used to process medical information) or server devices (such as servers, server clusters, cloud platforms, etc. used to process medical information), without limitation. For ease of writing, this application will be described below using the application to medical devices as an example.

[0031] This application provides a calculator program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when these instructions are executed by a computer, the computer can perform the method steps of the chest pain type determination method described in the following embodiments. Figure 1 As shown, the method for determining the type of chest pain includes the following steps 101 to 104.

[0032] Step 101: Obtain diverse medical information from the patient; The aforementioned diverse medical information can be considered as multi-dimensional information related to the patient; it may include, for example, patient-related identity information, medical history information, chief complaint information, physical examination information, laboratory test information, electrocardiogram information, medical imaging information, and medical orders. Specifically, chief complaint information and / or medical history information may include, for example, the nature, location, radiation area, duration, triggering and relieving factors of pain, and past medical history (such as hypertension, diabetes, and coronary heart disease); physical examination information may include, for example, blood pressure, heart rate, heart murmurs, breath sounds, and limb pulses; laboratory test information may include, for example, myocardial injury markers (such as troponin), D-dimer, and arterial blood gas analysis; and medical imaging information may include, for example, chest X-ray, echocardiography, coronary CTA (Computed Tomography Angiography), pulmonary CTA, and aortic CTA.

[0033] In some application scenarios, medical devices can obtain patients' medical information through the hospital's management information system to obtain more detailed and diversified medical information.

[0034] Step 102: Determine the chest pain risk level based on the multivariate medical information; the chest pain risk level includes a first level and a second level, and the risk level of the first level is greater than that of the second level. The aforementioned first level may include, for example, high risk, extremely high risk, etc., which essentially indicate a high degree of risk. The aforementioned second level may include, for example, medium risk, low risk, etc., which essentially indicate a low degree of risk.

[0035] In some applications, medical devices can determine chest pain risk levels based on pre-set rules. For example, weights can be assigned to medical history, chief complaint, physical examination, laboratory tests, electrocardiogram (ECG), medical imaging, and medical orders. The number of abnormal cases in each type of information is then multiplied by its corresponding weight, and the chest pain risk level is determined based on the product. For instance, if the product is greater than a first threshold, it is classified as level one; if the product is less than the first threshold, it is classified as level two. The first threshold can be set to values ​​such as 10 or 13, depending on the specific circumstances.

[0036] Step 103: If the chest pain risk level is the first level, then for any type of high-risk chest pain disease, the multivariate medical information is analyzed with reference to the first guideline information used to identify the type of high-risk chest pain disease to obtain a preliminary result indicating whether it is the type of high-risk chest pain disease; and, based on the preliminary results corresponding to each type of high-risk chest pain disease, the target high-risk chest pain type is determined. The high-risk chest pain conditions mentioned above typically include five types: ST-segment elevation myocardial infarction (STEMI), non-ST-segment elevation myocardial infarction (NSTEMI), aortic dissection (AD), unstable angina (UA), and acute pulmonary embolism (APE).

[0037] The aforementioned first guideline information can be considered as relevant information regarding high-risk chest pain diseases recorded in chest pain-related guideline documents. It should be noted that the typical symptoms of high-risk chest pain diseases are clearly described in these guideline documents. Therefore, by referring to the symptom descriptions in these guideline documents, one can verify whether the patient's medical information matches the described symptoms. If they match, it can be preliminarily determined that the patient has the corresponding type of high-risk chest pain disease. For example, for APE (acute chest pain syndrome), one can verify whether the patient's medical information contains corresponding symptom information based on the symptoms described in the chest pain-related guideline documents for this type of high-risk chest pain disease. If so, it can be preliminarily determined that the patient has this type of high-risk chest pain disease.

[0038] Then, the medical device can combine multiple preliminary results to determine the specific type of high-risk chest pain. For example, if one preliminary result indicates acute chest pain (APE) and other preliminary results indicate no corresponding high-risk chest pain, APE can be identified, meaning the target high-risk chest pain type is APE. If one preliminary result indicates STEMI and another indicates NSTEMI, and other preliminary results indicate no corresponding high-risk chest pain, other types of high-risk chest pain can be ruled out. Furthermore, based on relevant medical information, the probability of each condition can be verified, and the type with the higher probability can be identified as the target high-risk chest pain type.

[0039] Step 104: If the chest pain risk level is the second level, then for any preset type of low-risk chest pain disease, the multivariate medical information is analyzed with reference to the second guideline information used to identify the type of low-risk chest pain disease to obtain a preliminary result indicating whether it is the type of low-risk chest pain disease; and, based on the preliminary results corresponding to each type of low-risk chest pain disease, the target low-risk chest pain type is determined.

[0040] The aforementioned low-risk chest pain types typically include six categories: non-ACS related types, respiratory system related types, vascular system related types, digestive system related types, chest wall disease related types, and other disease-related types.

[0041] The aforementioned second guideline information can be considered as relevant information regarding low-risk chest pain disorders as recorded in chest pain-related guideline documents. It should be noted that the typical symptoms of low-risk chest pain disorders are also clearly described in chest pain-related guideline documents. Therefore, by referring to the symptom descriptions recorded in chest pain-related guideline documents, one can verify whether the medical information matches the described symptoms. If they match, it can be preliminarily determined that it is a low-risk chest pain disorder corresponding to the matching symptoms.

[0042] Then, medical devices can combine multiple preliminary results to determine the target low-risk chest pain type. For example, if one preliminary result indicates a low-risk chest pain condition related to the respiratory system, and other preliminary results indicate no such condition, then the patient is identified as having a low-risk chest pain condition related to the respiratory system, meaning the target low-risk chest pain type is respiratory-related. Similarly, if one preliminary result indicates a respiratory-related condition, another indicates a digestive-related condition, and other preliminary results indicate no such condition, other types of low-risk chest pain can be ruled out. Further analysis of relevant medical information can then be conducted to verify the respective probabilities of each condition, and the type with the higher probability can be identified as the target low-risk chest pain type.

[0043] In this implementation, the patient's diverse medical information is first obtained, then the chest pain risk level is determined. For the high-risk first level, a high-risk chest pain disease is identified, and its specific type is further determined. For the low-risk second level, a low-risk chest pain disease is identified, and its specific type is further determined. It is evident that the above process for determining the chest pain type simulates the logical thinking of a more experienced physician during diagnosis. This facilitates understanding and helps improve the efficiency and accuracy of identifying the target chest pain type. Furthermore, the use of diverse medical information broadens the diagnostic dimensions, and relevant guidelines are referenced during the determination of the target chest pain type, further enhancing its accuracy.

[0044] It should be noted that steps 101 to 104 above can be implemented, for example, using a large language model. This leverages the powerful computing capabilities of the large language model to further improve the determination speed and accuracy. It is understood that the large language model is an existing model, and those skilled in the art, upon learning of the technical solutions described above and that they can be implemented using a large language model, can implement this technical solution independently without requiring creative effort.

[0045] In addition, the following technical solutions also exist in related technologies: (1) Use traditional clinical decision support systems (CDSS) to identify the type of chest pain. However, most of these systems are based on fixed rule bases or simple logic trees, which are not very flexible, difficult to handle complex and atypical clinical situations, and have lagging knowledge updates, making them unable to adapt to the rapid iteration of medical knowledge.

[0046] In this application, by leveraging the large language model, we can flexibly handle complex and atypical clinical situations by taking advantage of its own characteristics, and obtain the latest guideline information in a timely manner to help adapt to the rapid iteration of medical knowledge.

[0047] (2) AI-assisted diagnostic models based on electrocardiograms or medical images determine the type of target chest pain. For example, STEMI can be determined by a model that automatically identifies STEMI based on electrocardiograms. However, such models have the following significant drawbacks: First, the diagnostic dimensions are limited. For example, if the model determines the type of target chest pain solely based on electrocardiograms or imaging, it cannot provide a complete and comprehensive assessment.

[0048] Second, there is a lack of contextual understanding. For example, the model cannot make a comprehensive judgment by combining the patient's medical history, symptoms, and laboratory test results, resulting in low specificity and a high false positive rate.

[0049] In this application, the integration of diverse medical information can broaden the diagnostic dimensions and provide a basis for contextual understanding, thereby helping to improve the above situation.

[0050] (3) AI-assisted diagnostic models based on deep learning determine the type of target chest pain. However, most of these models are black box models, and their internal decision-making mechanisms are difficult to explain. Doctors cannot understand their thinking logic, which will bring certain obstacles to clinical application.

[0051] In this application, the process of determining the type of target chest pain simulates the logical thinking of a more experienced doctor during diagnosis, which is easier to understand and can therefore improve the aforementioned obstacles.

[0052] In some alternative implementations, during the process of acquiring diverse medical information about a patient using medical devices, specific key indicator information of the patient may be acquired; and abnormal non-key indicator information of the patient may also be acquired; wherein, in the process of determining or excluding any type of chest pain, the importance of the key indicator information is greater than the importance of the non-key indicator information.

[0053] The aforementioned key indicators, such as electrocardiogram (ECG) data, troponin, high-sensitivity troponin, N-terminal pro-brain natriuretic peptide (PTP), D-dimer, pH value, lactate, partial pressure of carbon dioxide, partial pressure of oxygen, and serum potassium, play a significant role in identifying or ruling out certain types of chest pain. Therefore, regardless of whether these key indicator information is abnormal, medical devices can acquire it, which to some extent helps improve the accuracy and efficiency of identifying the target chest pain type.

[0054] The aforementioned non-critical indicator information may include other indicators besides the critical ones. This information plays a relatively minor role in identifying or ruling out certain types of chest pain. Therefore, only abnormal information can be obtained to assist in identifying or ruling out certain types of chest pain, which can, to some extent, improve the efficiency and accuracy of identifying the target chest pain type.

[0055] It should be noted that in some application scenarios, the aforementioned key and non-key indicator information can be preset by doctors according to the actual situation, and then the medical device can obtain the specific content corresponding to the information.

[0056] In some application scenarios, medical devices can use large language models to acquire and summarize the aforementioned key indicator information as well as abnormal non-key indicator information, thereby further improving the efficiency of determination.

[0057] In this implementation, adaptive acquisition of different medical information is performed, thereby balancing the efficiency and accuracy of determining the target chest pain type.

[0058] In some optional implementations, after acquiring the patient's diverse medical information, the medical device can first score the acquired diverse medical information based on different preset scoring rules; where different preset scoring rules correspond to different medical information; then, for any score, if the score is greater than the corresponding scoring threshold, an alert can be issued.

[0059] The aforementioned preset scoring rules may include, for example, the HEART scoring rule, the Geneva scoring rule, the ADD-RS scoring rule (Aortic Dissection Detection Risk Score), the Wells scoring rule, and the sPESI scoring rule (Simplified Pulmonary Embolism Severity Index).

[0060] The HEART scoring system primarily considers a patient's angina condition, electrocardiogram (ECG), age, risk factors, and troponin levels. If a patient's HEART score exceeds a certain threshold, a warning message can be issued. The HEART score threshold can, for example, range from (7, 10).

[0061] The Geneva score primarily considers a patient's current medical history, age, heart rate, past medical history, surgical history, and limb condition when scoring. If a patient's Geneva score exceeds a corresponding threshold, a warning message can be issued. The Geneva score threshold can be, for example, 11 points or higher.

[0062] The ADD-RS scoring rule primarily considers medical information such as high-risk pain status, high-risk physical examination results, and high-risk underlying diseases when scoring. If a patient's ADD-RS score exceeds a corresponding scoring threshold, a warning message can be issued. The scoring threshold for the ADD-RS score can, for example, include 2 or 3.

[0063] The Wells scoring system primarily considers a patient's current medical history, age, heart rate, past medical history, surgical history, limb location, and diagnostic information. If a patient's Wells score reaches a high-risk level, a warning message is issued. If a patient's Wells score exceeds a corresponding scoring threshold, a warning message is also issued. The scoring threshold for the Wells score can be, for example, 7 points or higher.

[0064] The sPESI scoring system primarily considers a patient's medical history, age, pulse, blood pressure, and blood oxygen saturation. If a patient's sPESI score exceeds a corresponding threshold, a warning message can be issued. The sPESI score threshold can be, for example, 1 point or higher.

[0065] It is understood that the HEART scoring rules, Geneva scoring rules, ADD-RS scoring rules, Wells scoring rules, and sPESI scoring rules mentioned above are all commonly used rules in the medical field, and this application will not elaborate on their specific scoring processes. Furthermore, the warning information corresponding to each preset scoring rule can be the same or different; this application does not impose any restrictions on this. Further, the warning information may include, for example, an audible alarm or an alarm text message.

[0066] In this implementation, a scoring process is added to determine the target chest pain type, which helps improve the accuracy of the target chest pain type. Furthermore, when the score is greater than the corresponding scoring threshold, the patient can be identified as being in a high-risk condition, thus enabling early warning. This helps assist doctors in making timely relevant diagnostic and treatment measures.

[0067] In some alternative implementations, the multivariate medical information includes electrocardiogram (ECG) information; thus, when the medical device determines the chest pain risk level based on the multivariate medical information, it can first analyze the ECG information with reference to guidelines related to chest pain diseases to identify abnormal ECG information; then, based on the abnormal ECG information and other medical information, it can determine the chest pain risk level.

[0068] For example, medical devices can refer to electrocardiogram (ECG) guidelines provided in chest pain-related guidelines to identify abnormal ECG information related to chest pain. This abnormal ECG information may include, for example, abnormal ECG data (such as ST-segment elevation, PR interval prolongation), abnormal location (such as limb leads, precordial leads V1, V2, V3, etc.), and specific numerical values. Then, based on this abnormal ECG information and other medical information (such as the aforementioned non-critical indicators), the risk level of chest pain can be determined.

[0069] In this implementation, the focus is on analyzing electrocardiogram (ECG) information, and combining ECG information with other medical information to determine the chest pain risk level. This helps to improve the accuracy of the chest pain risk level.

[0070] Furthermore, the medical equipment can also alert doctors when a primary level of illness is identified, enabling them to promptly transfer the patient to the emergency room or chest pain center for treatment. Then, when a secondary level of illness is identified, it can alert doctors to transfer the patient to the appropriate department for treatment.

[0071] In some alternative implementations, the medical device may also determine emergency interventions based on the abnormal ECG information and other medical information, and mark the emergency interventions; and / or, if the chest pain risk level is the first level, determine action guidance information.

[0072] The aforementioned emergency interventions may include situations such as whether the patient is in shock or has severe tachycardia. Here, medical devices can determine emergency interventions, for example, by using currently acquired abnormal electrocardiogram information, patient complaints (e.g., rapid heartbeat, recent history of shock), and medical orders.

[0073] The aforementioned action guidelines may include, for example, the timeframe for completing the necessary imaging examinations and the timeframe for initiating emergency interventions for the patient.

[0074] In this implementation, emergency interventions can be marked, and action guidance information can be determined when the risk level is high. This helps doctors to take timely and targeted measures.

[0075] In some optional implementations, as mentioned above, the types of high-risk chest pain include STEMI, NSTEMI, AD, UA, and APE. Thus, when the medical device analyzes the multivariate medical information for any preset high-risk chest pain type, referring to the first guideline information used to identify that high-risk chest pain type, and obtains a preliminary result characterizing whether it is that high-risk chest pain type, the preliminary determination can be made by combining the acquired multivariate medical information and the score obtained through preset scoring rules. For example, the following sub-steps can be performed: Sub-step 1031: For some or all of the high-risk chest pain diseases among STEMI, NSTEMI, and UA, analyze the medical information related to the high-risk chest pain disease of that type with reference to the first guideline information to determine whether the patient has ACS disease; wherein, if the patient has ACS disease, the high-risk chest pain disease type is initially determined to be some or all of STEMI, NSTEMI, and UA. For example, information from the first guideline can be used to analyze and verify the results of tests and examinations based on myocardial injury (such as cTn (cardiac troponin) levels), myocardial ischemia (such as ECG changes or coronary artery stenosis; ECG is short for Electrocardiogram), and high-risk signals (such as non-ischemic chest pain, D-dimer positivity, and mediastinal widening) to determine whether a patient has coronary syndrome (ACS) and to provide the basis for the diagnosis. If ACS is confirmed, it can be preliminarily determined that the patient has some or all of the high-risk chest pain conditions of STEMI, NSTEMI, and UA.

[0076] In some applications, such as analyzing medical information based on relevant guidelines, it can determine whether a patient has a high-risk non-ACS disease closely related to ACS. If so, it can output a warning message to prompt the doctor to make a relevant diagnosis.

[0077] Sub-step 1032: For high-risk chest pain of type APE, analyze the medical information related to this type of high-risk chest pain with reference to the Wells score and the first guideline information to determine whether pulmonary embolism is present; if pulmonary embolism is present, the type of high-risk chest pain is preliminarily determined to be APE. For example, the first guideline information can be referenced, and the results of examinations such as right pulmonary artery filling defects, absence of breath sounds on the left side, and radiolucent areas on chest X-rays can be analyzed and verified. Then, the Wells score can be used to determine whether the patient has pulmonary embolism, and the guidance basis for the judgment can be provided. For example, if the first guideline information confirms pulmonary embolism and the Wells score indicates a high risk, then an initial diagnosis of acute pulmonary embolism can be made, thus obtaining a preliminary result of high-risk chest pain disease of the APE type.

[0078] In some application scenarios, such as analyzing medical information based on relevant guidelines, it can determine whether a patient has pneumothorax, a disease closely related to acute pulmonary embolism. If so, it can output a warning message to prompt the doctor to make a relevant diagnosis.

[0079] Sub-step 1033: For high-risk chest pain diseases of type AD, analyze the medical information related to this type of high-risk chest pain disease with reference to the first guideline information to determine whether acute aortic syndrome is present; if acute aortic syndrome is present, the type of high-risk chest pain disease is preliminarily determined to be type AD.

[0080] For example, medical equipment can refer to first-line guidelines and analyze and verify test results based on factors such as tearing pain, absence of pulse in the right radial artery, neurological signs, organ ischemia, and blood pressure asymmetry to determine whether a patient has acute aortic syndrome and provide guidelines for this determination. If acute aortic syndrome is present, a preliminary result indicating that the high-risk chest pain condition is AD type can be obtained.

[0081] In some application scenarios, such as analyzing medical information according to relevant guidelines, it can determine whether the patient has aortic wall hematoma or aortic penetrating ulcer, which are closely related to aortic dissection. If so, it can also output warning information to prompt the doctor to make a relevant diagnosis.

[0082] In this implementation, for each type of high-risk chest pain disease, an adaptive analysis of relevant medical information can be performed based on the first guideline information, which facilitates the preliminary determination of whether it is the corresponding type of high-risk chest pain disease. This helps to improve the accuracy and completeness of the determination process and reduce the risk of missed diagnosis or misdiagnosis.

[0083] In some alternative implementations, the types of low-risk chest pain include non-ACS-related types, respiratory-related types, vascular-related types, digestive-related types, thoracic-related types, and other disease-related types.

[0084] In this way, when the medical device analyzes the multivariate medical information for any preset type of low-risk chest pain disease, referring to the second guideline information used to identify that type of low-risk chest pain disease, and obtains a preliminary result characterizing whether it is a low-risk chest pain disease of that type, the preliminary determination can be made by combining the acquired multivariate medical information and the score obtained through preset scoring rules. For example, the following sub-steps can be performed: Sub-step 1041: For low-risk chest pain diseases that are not related to ACS, analyze the medical information related to this type of low-risk chest pain disease with reference to the information in the second guideline, and preliminarily determine whether the patient has a low-risk chest pain disease that is not related to ACS. For example, medical devices can refer to the second guideline information to analyze and verify whether the patient's chest pain symptoms are related to physical activity or emotional excitement, whether the pain is behind the sternum / precordial region, whether it is a squeezing, dull, or aching pain, whether it is relieved by rest or sublingual nitrates, whether there is chest tightness, palpitations, shortness of breath, dizziness, fatigue, lower extremity edema, whether there are abnormal blood pressure, abnormal heart rate, abnormal electrocardiogram, abnormal echocardiogram, abnormal cardiac enzymes, and past medical history. This analysis can help determine whether the patient has stable angina (SA), myocarditis, pericarditis, cardiomyopathy, arrhythmia, acute heart failure, hypertensive emergency, aortic valve disease, stress cardiomyopathy, etc., to determine if they have non-ACS-related cardiac diseases. If they do have non-ACS-related cardiac diseases, it can be further determined whether these diseases cause chest pain. If so, a preliminary result can be obtained that the type of low-risk chest pain is non-ACS-related, and the corresponding guideline basis for the judgment can be output.

[0085] Sub-step 1042: For low-risk chest pain diseases related to the respiratory system, analyze the medical information related to this type of low-risk chest pain disease with reference to the information in the second guideline, and preliminarily determine whether the patient has a low-risk chest pain disease related to the respiratory system. For example, medical devices can refer to the second guideline information to analyze and judge whether a patient has respiratory diseases such as pneumothorax, bronchitis, pneumonia, pleurisy, etc., and whether these diseases can cause chest pain, based on the correlation between chest pain and breathing and cough, the location and nature of chest pain, accompanying respiratory symptoms, causes and past medical history, and whether there are abnormalities in chest X-ray or chest CT, blood routine, pulmonary function and other examinations. If chest pain is caused, a preliminary result can be obtained that the type of low-risk chest pain disease is respiratory system related, and the guideline basis for the judgment can be output at the same time.

[0086] Sub-step 1043: For low-risk chest pain diseases related to the vascular system, analyze the medical information related to this type of low-risk chest pain disease with reference to the second guideline information to preliminarily determine whether the patient has a low-risk chest pain disease related to the vascular system. For example, medical devices can refer to the second guideline information to determine whether the pain is sudden and severe, whether the pain is behind the sternum, in the chest and back, or accompanied by radiating pain, whether there are key accompanying symptoms, triggers and past medical history, whether there are abnormalities in aortic CTA, ultrasound, MRI (Magnetic Resonance Imaging), etc., and whether the pain is still difficult to relieve after using antihypertensive / analgesic drugs. This allows for the assessment of whether the patient has vascular diseases such as aortic ulcer, aortic hematoma, aortic aneurysm, or stroke, and whether these diseases will cause chest pain. If chest pain is caused, a preliminary result can be obtained that the type of low-risk chest pain disease is vascular system-related, and the guideline basis for the assessment can be output at the same time.

[0087] Sub-step 1044: For low-risk chest pain diseases related to the digestive system, analyze the medical information related to this type of low-risk chest pain disease with reference to the information in the second guideline, and preliminarily determine whether the patient has a low-risk chest pain disease related to the digestive system. For example, medical devices can refer to the second guideline information and, based on chest pain-related characteristics, accompanying digestive system symptoms, and a history of digestive system diseases in the patient's medical history, determine whether the patient has digestive system diseases such as esophagitis, esophageal reflux, gastritis, gastric ulcer, duodenal ulcer, acute pancreatitis, cholecystitis, hiatal hernia, etc., and determine whether these diseases will cause chest pain. If chest pain is caused, a preliminary result can be obtained that the type of low-risk chest pain disease is related to the digestive system, and the guideline basis for the judgment can be output at the same time.

[0088] Sub-step 1045: For low-risk chest pain diseases related to thoracic diseases, analyze the medical information related to this type of low-risk chest pain disease with reference to the second guideline information to preliminarily determine whether the patient has low-risk chest pain diseases related to thoracic diseases. For example, medical devices can refer to the second guideline information to determine whether a patient has chest injuries, costochondritis, or other thoracic diseases based on the location, nature, characteristics, accompanying symptoms, medical history, and triggers of chest pain, and whether these diseases will cause chest pain. If chest pain is caused, a preliminary result can be obtained that the type of low-risk chest pain disease is related to thoracic diseases, and the guideline basis for the judgment can be output at the same time.

[0089] Sub-step 1046: For low-risk chest pain diseases of other disease-related types, analyze the medical information related to the low-risk chest pain diseases of that type with reference to the second guideline information to preliminarily determine whether the patient has the low-risk chest pain disease related to the other diseases.

[0090] For example, medical devices can refer to the second guideline information and, based on the correlation between chest pain and emotions, atypical manifestations of chest pain, anxiety-related accompanying symptoms, and the exclusion of evidence of organic diseases, determine whether the patient has anxiety, shingles, anemia, or other diseases, and whether these diseases will cause chest pain. If chest pain is caused, a preliminary result can be obtained that the type of low-risk chest pain disease is related to other diseases, and the guideline basis for the judgment can be output at the same time.

[0091] In this implementation, for each type of low-risk chest pain disease, an adaptive analysis of relevant medical information can be performed based on the information in the second guideline, which facilitates the preliminary determination of whether it is a low-risk chest pain disease of the corresponding type. This helps to improve the accuracy and completeness of the determination process and reduce the risk of missed diagnosis or misdiagnosis.

[0092] In some alternative implementations, the medical device can also determine the treatment strategy corresponding to the target high-risk chest pain type or the target low-risk chest pain type based on the medical information it is equipped with.

[0093] The aforementioned medical procedure information may include information on procedures such as open-chest surgery and chest decompression, or other available medications.

[0094] The aforementioned diagnostic and treatment strategies may include, for example, testing, examination, surgery, and medication.

[0095] In some application scenarios, medical devices can obtain information about the medical procedures they are equipped with based on the hospital's management information system, and then provide suggestions on testing, examination, surgery, medication, etc., with reference to relevant guidelines.

[0096] For example, for high-risk chest pain of STEMI type, suggestions on testing, examination, surgery, and medication can be given based on the medical means available in the hospital that can actually support it, and relevant original guidelines can be provided for doctors' reference.

[0097] For example, for high-risk chest pain of type NSTEMI, suggestions on testing, examination, surgery, and medication can be given based on the medical means available in the hospital that can actually support it, and relevant original guidelines can be provided for doctors' reference.

[0098] For example, for high-risk chest pain of type AD, the hospital can provide recommendations on testing, examination, surgery, and medication based on the available medical resources to support the diagnosis of high-risk chest pain of type AD. The relevant guidelines can also be provided for doctors' reference.

[0099] For example, for high-risk chest pain of type UA, suggestions on testing, examination, surgery, and medication can be given based on the medical means available in the hospital that can actually support it, and relevant original guidelines can be provided for doctors' reference.

[0100] For example, for high-risk chest pain of type APE, suggestions on testing, examination, surgery, and medication can be given based on the medical means available in the hospital that can actually support it, and relevant original guidelines can be provided for doctors' reference.

[0101] For example, for low-risk chest pain, the hospital can provide recommendations on testing, examination, surgery, and medication based on its available medical resources. The hospital can also provide relevant guidelines for doctors to refer to.

[0102] Understandably, if the analysis process reveals that the patient also has other underlying conditions that are not chest pain, treatment suggestions and medical contraindications can be provided by referring to the relevant guidelines and the medical means available to the hospital. The original text of the relevant guidelines can also be provided for the doctor's reference.

[0103] In this implementation, after determining the target type of chest pain, a corresponding treatment strategy can also be determined, which helps doctors to carry out targeted treatment more quickly.

[0104] It should be noted that chest pain, as a potentially life-threatening acute illness, requires doctors to make a diagnosis very quickly after seeing the patient. This may result in the absence of certain laboratory test results at the time of diagnosis. In such cases, medical devices, for example, can prompt doctors to order relevant tests if the corresponding test results are not available when analyzing information based on relevant guidelines. This allows for analysis of the obtained test results, identification of the target chest pain type, and appropriate treatment strategies.

[0105] It should be noted that, in any of the above implementation methods, in order to further improve the determination efficiency and accuracy, large language models can be used to assist in the implementation of the corresponding technical solutions, which will not be elaborated in this application.

[0106] Furthermore, since this application analyzes diverse medical information, even without certain medical information, it is possible to make a determination by combining other medical information, with only a slight difference in accuracy. Please refer to the table below, which shows the accuracy data for determining 94 typical chest pain cases in a hospital. This accuracy is obtained by comparing the target chest pain type result obtained through any of the above methods with the doctor's manually labeled diagnosis. If the target chest pain type result is the same as the doctor's labeled diagnosis, it is considered accurate; otherwise, it is considered inaccurate.

[0107]

[0108] It is evident that the accuracy of the target chest pain type obtained using any of the above implementation methods is relatively high.

[0109] Those skilled in the art will understand that, in the methods described in the specific embodiments, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0110] Please see Figure 2 The diagram illustrates a structural block diagram of a chest pain type determination system according to an embodiment of this application. This chest pain type determination system can be a module, program segment, or code on an electronic device. It should be understood that this device is similar to the one described above. Figure 1 The method implementation corresponds to this and can be executed. Figure 1 The various steps involved in the method implementation examples.

[0111] Optionally, the aforementioned chest pain type determination system includes a case summary module 201 and a chest pain diagnosis module 203. The case summary module 201 is used to acquire diverse medical information about the patient. The chest pain diagnosis module 203 includes a chest pain grading module, a high-risk chest pain determination module, and a low-risk chest pain determination module. The chest pain grading module is used to determine the chest pain risk level based on the diverse medical information; the chest pain risk level includes a first level and a second level, where the risk level of the first level is greater than that of the second level. The high-risk chest pain determination module includes a first preliminary determination module and a first final determination module. The first preliminary determination module is used to analyze the diverse medical information, referring to first guideline information used to identify high-risk chest pain diseases of any preset type, if the chest pain risk level is the first level. The system obtains preliminary results indicating whether the chest pain is of that type of high-risk chest pain disease; and a first final determination module is used to determine the target high-risk chest pain type based on the preliminary results corresponding to each type of high-risk chest pain disease; the low-risk chest pain determination module includes a second preliminary determination module and a second final determination module. The second preliminary determination module is used to analyze the multivariate medical information for any preset type of low-risk chest pain disease, referring to the second guideline information used to identify the low-risk chest pain disease of that type, if the chest pain risk level is the second level, to obtain preliminary results indicating whether the chest pain is of that type of low-risk chest pain disease; and the second final determination module is used to determine the target low-risk chest pain type based on the preliminary results corresponding to each type of low-risk chest pain disease.

[0112] Optionally, the case summary module 201 is further configured to: acquire key indicator information of the patient; and acquire abnormal non-key indicator information of the patient; wherein, in the process of determining or excluding any type of chest pain, the importance of the key indicator information is greater than the importance of the non-key indicator information.

[0113] Optionally, the system further includes a scale scoring module 202, which is used to: after acquiring the patient's multivariate medical information, score the acquired multivariate medical information according to different preset scoring rules; wherein, the medical information corresponding to different preset scoring rules is different; and for any score, if the score is greater than the corresponding scoring threshold, an early warning is issued.

[0114] Optionally, the multivariate medical information includes electrocardiogram (ECG) information; and the chest pain grading module further includes an ECG analysis submodule and a direct analysis submodule. The ECG analysis submodule is used to: analyze the ECG information with reference to guidelines related to chest pain diseases to identify abnormal ECG information; the direct analysis submodule is used to determine the chest pain risk level based on the abnormal ECG information and other medical information.

[0115] Optionally, the direct analysis submodule is further configured to: determine emergency intervention items based on the abnormal electrocardiogram information and other medical information, and mark the emergency intervention items; and / or, if the chest pain risk level is the first level, determine action guidance information.

[0116] Optionally, the types of high-risk chest pain diseases include STEMI, NSTEMI, AD, UA, and APE; and the first preliminary determination module includes an ACS analysis submodule, an APE analysis submodule, and an AAS (Acute Aortic) submodule. The Syndrome (Acute Aortic Syndrome) analysis submodule includes: The ACS analysis submodule is used to analyze medical information related to some or all types of high-risk chest pain diseases (STEMI, NSTEMI, UA) according to the first guideline information to determine whether ACS is present; if ACS is present, the high-risk chest pain disease type is preliminarily determined to be some or all of STEMI, NSTEMI, UA. The APE analysis submodule is used to analyze medical information related to APE type high-risk chest pain diseases according to the first guideline information to determine whether pulmonary embolism is present; if pulmonary embolism is present, the high-risk chest pain disease type is preliminarily determined to be APE. The AAS analysis submodule is used to analyze medical information related to AD type high-risk chest pain diseases according to the first guideline information to determine whether acute aortic syndrome is present; if acute aortic syndrome is present, the high-risk chest pain disease type is preliminarily determined to be AD.

[0117] Optionally, the types of low-risk chest pain diseases include non-ACS-related types, respiratory system-related types, vascular system-related types, digestive system-related types, chest wall disease-related types, and other disease-related types; and the second preliminary determination module includes a non-ACS cardiogenic chest pain analysis submodule, a chest pain analysis submodule caused by respiratory system diseases, a chest pain analysis submodule caused by vascular diseases, a chest pain analysis submodule caused by digestive system diseases, a chest pain analysis submodule caused by chest wall diseases, and a chest pain analysis submodule caused by other causes.

[0118] Among them, the non-ACS cardiogenic chest pain analysis submodule is used to analyze medical information related to low-risk chest pain diseases of non-ACS types, referring to the information in the second guideline, to preliminarily determine whether the patient has a low-risk chest pain disease of non-ACS. The chest pain analysis submodule caused by respiratory diseases is used to analyze medical information related to low-risk chest pain diseases of respiratory system type, referring to the second guideline information, to preliminarily determine whether a person has low-risk chest pain disease of respiratory system type. The submodule for analyzing chest pain caused by vascular diseases is used to analyze medical information related to low-risk chest pain diseases of the vascular system, referring to the information in the second guideline, to preliminarily determine whether a patient has a low-risk chest pain disease of the vascular system. The submodule for analyzing chest pain caused by digestive system diseases is used to analyze medical information related to low-risk chest pain diseases of the digestive system type, referring to the information in the second guideline, to preliminarily determine whether a patient has a low-risk chest pain disease related to the digestive system. The chest pain analysis submodule caused by thoracic diseases is used to analyze medical information related to low-risk chest pain diseases of the type related to thoracic diseases, referring to the information in the second guideline, to preliminarily determine whether the patient has low-risk chest pain diseases related to thoracic diseases. The "Other Causes of Chest Pain Analysis" submodule is used to analyze medical information related to low-risk chest pain diseases of other disease types, referring to the information in the second guideline, to preliminarily determine whether the patient has low-risk chest pain diseases related to the other diseases.

[0119] Optionally, the system further includes a treatment planning module 204, which is used to determine the treatment strategy corresponding to the target high-risk chest pain type or the target low-risk chest pain type based on the equipped medical information. Specifically, the treatment planning module 204 includes a STEMI treatment planning submodule, a NSTEMI treatment planning submodule, an AD treatment planning submodule, a UA treatment planning submodule, an APE treatment planning submodule, and a general practice treatment planning submodule.

[0120] The STEMI treatment plan submodule is used to provide recommendations for testing, examination, surgery, and medication when a patient is diagnosed with STEMI, a high-risk chest pain condition, based on the medical resources available in the hospital. It also provides relevant guidelines for doctors to refer to.

[0121] The NSTEMI treatment plan submodule is used to provide recommendations on testing, examination, surgery, and medication in cases of high-risk chest pain diagnosed as NSTEMI, and can also provide relevant original guidelines for doctors' reference.

[0122] The AD treatment plan submodule is used to provide recommendations for testing, examination, surgery, and medication when a patient is diagnosed with high-risk chest pain of AD type, based on the medical means available in the hospital. It can also provide relevant original guidelines for doctors to refer to.

[0123] The UA treatment plan submodule is used to provide recommendations for testing, examination, surgery, and medication when a patient is diagnosed with a high-risk chest pain condition of type UA, taking into account the medical resources available to the hospital. It can also provide relevant original guidelines for doctors' reference.

[0124] The APE treatment plan submodule is used to provide recommendations for testing, examination, surgery, and medication in cases of high-risk chest pain diagnosed as APE, based on the medical resources available in the hospital. It can also provide relevant original guidelines for doctors' reference.

[0125] The general practice treatment plan submodule is used to provide treatment suggestions and medical contraindications when it is determined during the analysis process that the patient has other underlying diseases. It refers to the relevant guidelines and the medical means that the hospital is equipped with to support these diseases. It can also provide the original text of the relevant guidelines for doctors to refer to.

[0126] It should be noted that those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system or device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0127] Please see Figure 3 , Figure 3 This application provides a schematic diagram of an electronic device for performing a method for determining the type of chest pain. The electronic device may include: at least one processor 301, such as a CPU; at least one communication interface 302; at least one memory 303; and at least one communication bus 304. The communication bus 304 is used to establish direct communication between these components. In this embodiment, the communication interface 302 is used for signaling or data communication with other node devices. The memory 303 may be a high-speed RAM or non-volatile memory, such as at least one disk storage device. Optionally, the memory 303 may also be at least one storage device located remotely from the aforementioned processor. The memory 303 stores computer-readable instructions. When these computer-readable instructions are executed by the processor 301, the electronic device can perform the methods provided in the above-described method embodiments. It is understood that the implementation process of each step described in the specific method embodiments can be referred to the relevant descriptions in the above embodiments, and will not be repeated here.

[0128] Understandable. Figure 3 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown. Figure 3 The components shown can be implemented using hardware, software, or a combination thereof.

[0129] This application provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it can perform the methods provided in the above-described method embodiments. It is understood that the implementation process of each step described in the specific method embodiments can be referred to the relevant descriptions in the above embodiments, and will not be repeated here.

[0130] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0131] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0132] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0133] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A system for determining the type of chest pain, characterized in that, include: The case summary module is used to obtain diverse medical information about patients; The chest pain diagnosis module is used to determine the chest pain risk level based on the aforementioned multi-dimensional medical information; The chest pain risk level includes a first level and a second level, with the risk level of the first level being greater than that of the second level. If the chest pain risk level is the first level, then for any preset type of high-risk chest pain disease, the multivariate medical information is analyzed with reference to the first guideline information used to identify the high-risk chest pain disease of that type, to obtain a preliminary result indicating whether it is a high-risk chest pain disease of that type; and, based on the preliminary results corresponding to each type of high-risk chest pain disease, the target high-risk chest pain type is determined; if the chest pain risk level is the second level, then for any preset type of low-risk chest pain disease, the multivariate medical information is analyzed with reference to the second guideline information used to identify the low-risk chest pain disease of that type, to obtain a preliminary result indicating whether it is a low-risk chest pain disease of that type; and, based on the preliminary results corresponding to each type of low-risk chest pain disease, the target low-risk chest pain type is determined.

2. The system according to claim 1, characterized in that, Also includes: The scale scoring module is used to score the acquired multi-dimensional medical information based on different preset scoring rules; different preset scoring rules correspond to different medical information; for any score, if the score is greater than the corresponding scoring threshold, an alert is issued.

3. The system according to claim 1, characterized in that, Also includes: The treatment plan module is used to determine the treatment strategy corresponding to the target high-risk chest pain type or the target low-risk chest pain type based on the equipped medical information.

4. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instruction is executed by the processor, the following method steps are performed: Obtain diverse medical information from patients; Based on the aforementioned multi-dimensional medical information, a chest pain risk level is determined; the chest pain risk level includes a first level and a second level, with the risk level of the first level being greater than that of the second level. If the chest pain risk level is the first level, then for any type of high-risk chest pain disease, the multivariate medical information is analyzed with reference to the first guideline information used to identify the type of high-risk chest pain disease to obtain a preliminary result indicating whether it is the type of high-risk chest pain disease; and, based on the preliminary results corresponding to each type of high-risk chest pain disease, the target high-risk chest pain type is determined. If the chest pain risk level is the second level, then for any preset type of low-risk chest pain disease, the multivariate medical information is analyzed with reference to the second guideline information used to identify the type of low-risk chest pain disease to obtain a preliminary result indicating whether it is the type of low-risk chest pain disease; and, based on the preliminary results corresponding to each type of low-risk chest pain disease, the target low-risk chest pain type is determined.

5. The computer program product according to claim 4, characterized in that, The acquisition of patients' diverse medical information includes: Obtain key patient indicators; and Obtain abnormal non-critical indicator information from patients; In the process of identifying or ruling out any type of chest pain, the importance of the key indicator information is greater than that of the non-key indicator information.

6. The computer program product according to claim 5, characterized in that, After obtaining the patient's diverse medical information, the method steps further include: The acquired multi-dimensional medical information is scored based on different preset scoring rules; the medical information corresponds to different preset scoring rules. If any score exceeds the corresponding score threshold, an alert will be issued.

7. The computer program product according to claim 6, characterized in that, The diverse medical information includes electrocardiogram (ECG) information; as well as The determination of chest pain risk level based on the aforementioned multi-dimensional medical information includes: The electrocardiogram (ECG) data was analyzed in accordance with guidelines related to chest pain to identify abnormal ECG information. Based on the abnormal electrocardiogram information and other medical information, the risk level of chest pain is determined.

8. The computer program product according to claim 7, characterized in that, The method steps also include: Based on the abnormal electrocardiogram information and other medical information, determine emergency interventions and mark the emergency interventions; and / or If the chest pain risk level is Level 1, then action guidance information is determined.

9. The computer program product according to claim 4, characterized in that, High-risk chest pain conditions include STEMI, NSTEMI, AD, UA, and APE; and For any predefined type of high-risk chest pain disease, the multivariate medical information is analyzed with reference to first guideline information used to identify that type of high-risk chest pain disease to obtain preliminary results characterizing whether it is that type of high-risk chest pain disease, including: For some or all of the high-risk chest pain diseases among STEMI, NSTEMI, and UA, the medical information related to the high-risk chest pain disease of that type is analyzed with reference to the information in the first guideline to determine whether the patient has ACS; if the patient has ACS, the high-risk chest pain disease is preliminarily determined to be some or all of STEMI, NSTEMI, and UA. For high-risk chest pain of type APE, medical information related to this type of high-risk chest pain is analyzed with reference to the information in the first guideline to determine whether pulmonary embolism is present; if pulmonary embolism is present, the type of high-risk chest pain is preliminarily determined to be type APE. For high-risk chest pain of type AD, medical information related to this type of high-risk chest pain is analyzed with reference to the information in the first guideline to determine whether acute aortic syndrome is present; if acute aortic syndrome is present, the type of high-risk chest pain is preliminarily determined to be type AD.

10. The computer program product according to claim 4, characterized in that, Low-risk chest pain disorders include non-ACS-related types, respiratory-related types, vascular-related types, digestive-related types, chest wall-related types, and other disease-related types; and For any predefined type of low-risk chest pain disease, the multivariate medical information is analyzed with reference to second guideline information used to identify that type of low-risk chest pain disease to obtain preliminary results characterizing whether it is that type of low-risk chest pain disease, including: For low-risk chest pain conditions that are not related to ACS, medical information related to this type of low-risk chest pain condition is analyzed in accordance with the information in the second guideline to preliminarily determine whether the patient has a low-risk chest pain condition that is not related to ACS. For low-risk chest pain diseases related to the respiratory system, medical information related to this type of low-risk chest pain disease is analyzed with reference to the information in the second guideline to preliminarily determine whether the patient has a low-risk chest pain disease related to the respiratory system. For low-risk chest pain diseases related to the vascular system, medical information related to this type of low-risk chest pain disease is analyzed with reference to the information in the second guideline to preliminarily determine whether the patient has a low-risk chest pain disease related to the vascular system. For low-risk chest pain diseases related to the digestive system, medical information related to this type of low-risk chest pain disease is analyzed with reference to the information in the second guideline to preliminarily determine whether the patient has a low-risk chest pain disease related to the digestive system. For low-risk chest pain related to thoracic diseases, medical information related to this type of low-risk chest pain is analyzed with reference to the information in the second guideline to preliminarily determine whether the patient has low-risk chest pain related to thoracic diseases. For low-risk chest pain conditions related to other diseases, medical information related to such low-risk chest pain conditions is analyzed in accordance with the information in the second guideline to preliminarily determine whether the patient has low-risk chest pain conditions related to the other diseases.

11. The computer program product according to any one of claims 4-10, characterized in that, The method steps also include: Based on the available medical information, determine the corresponding treatment strategy for the target high-risk chest pain type or the target low-risk chest pain type.

12. An electronic device, characterized in that, Includes a processor and a memory, the memory storing computer-readable instructions, which, when executed by the processor, perform the following method steps: Obtain diverse medical information from patients; Based on the aforementioned multi-dimensional medical information, a chest pain risk level is determined; the chest pain risk level includes a first level and a second level, with the risk level of the first level being greater than that of the second level. If the chest pain risk level is the first level, then for any type of high-risk chest pain disease, the multivariate medical information is analyzed with reference to the first guideline information used to identify the type of high-risk chest pain disease to obtain a preliminary result indicating whether it is the type of high-risk chest pain disease; and, based on the preliminary results corresponding to each type of high-risk chest pain disease, the target high-risk chest pain type is determined. If the chest pain risk level is the second level, then for any preset type of low-risk chest pain disease, the multivariate medical information is analyzed with reference to the second guideline information used to identify the type of low-risk chest pain disease to obtain a preliminary result indicating whether it is the type of low-risk chest pain disease; and, based on the preliminary results corresponding to each type of low-risk chest pain disease, the target low-risk chest pain type is determined.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it performs the following method steps: Obtain diverse medical information from patients; Based on the aforementioned multi-dimensional medical information, a chest pain risk level is determined; the chest pain risk level includes a first level and a second level, with the risk level of the first level being greater than that of the second level. If the chest pain risk level is the first level, then for any type of high-risk chest pain disease, the multivariate medical information is analyzed with reference to the first guideline information used to identify the type of high-risk chest pain disease to obtain a preliminary result indicating whether it is the type of high-risk chest pain disease; and, based on the preliminary results corresponding to each type of high-risk chest pain disease, the target high-risk chest pain type is determined. If the chest pain risk level is the second level, then for any preset type of low-risk chest pain disease, the multivariate medical information is analyzed with reference to the second guideline information used to identify the type of low-risk chest pain disease to obtain a preliminary result indicating whether it is the type of low-risk chest pain disease; and, based on the preliminary results corresponding to each type of low-risk chest pain disease, the target low-risk chest pain type is determined.

Images