A precise diagnosis and treatment method and system for non-high-risk chest pain population

Abstract

This invention relates to the field of intelligent diagnosis and treatment technology, and particularly to a precision diagnosis and treatment method and system for non-high-risk chest pain populations. The method includes: acquiring known clinical information, known coronary artery imaging information, and known long-term clinical events of non-high-risk chest pain populations to construct a dataset; training an XGBoost model using the dataset to obtain a risk prediction scoring model; acquiring clinical information of the non-high-risk chest pain patient to be tested, inputting it into the risk prediction scoring model to obtain a risk prediction score; determining the group to which the non-high-risk chest pain patient belongs based on the risk prediction score; and determining subsequent diagnosis and treatment strategies based on the group to which the non-high-risk chest pain patient belongs and the patient's clinical information. This invention can more accurately predict the risk of non-high-risk chest pain patients, and for low-risk non-high-risk chest pain patients, it can reduce unnecessary invasive examinations and achieve effective resource allocation.

Description

Technical Field

[0001] This invention relates to the field of intelligent diagnosis and treatment technology, and in particular to a precision diagnosis and treatment method and system for non-high-risk chest pain populations. Background Technology

[0002] Coronary atherosclerotic heart disease (CHD) is a heart condition caused by atherosclerotic lesions in the coronary arteries, leading to narrowing or blockage of the blood vessels and resulting in myocardial ischemia, hypoxia, or necrosis. With China's socio-economic development, accelerated population aging and urbanization, and significant changes in lifestyle, the number of CHD cases has increased rapidly, and the disease burden continues to worsen. CHD patients often present with chest pain or discomfort, but the spectrum of diseases associated with chest pain is very broad, encompassing cardiovascular, respiratory, digestive, musculoskeletal, and even nervous systems, posing a significant challenge to accurate diagnosis and treatment. Over 80% of chest pain patients, after initial differential diagnosis, are excluded from high-risk chest pain-related diseases and classified as having non-high-risk chest pain (NHRCP). Research on this patient population is limited, and a comprehensive survey of their overall clinical characteristics is lacking. Clinical practice often relies on the individual experience of attending physicians to develop subsequent treatment strategies, and a standardized treatment process with sufficient evidence has not yet been established.

[0003] Although computed tomographic coronary angiography (CCTA) is a non-invasive diagnostic technique, it requires sophisticated equipment and involves intravenous administration of contrast agents, resulting in a certain dose of ionizing radiation. Furthermore, studies have indicated that overuse of CCTA increases the need for subsequent medications and invasive coronary angiography (ICA). Therefore, efficiently developing individualized treatment plans for the large number of NHRCP patients—accurately assessing their true disease status and implementing appropriate examinations and interventions while avoiding unnecessary complications and financial burdens from overtreatment—has become a major focus of attention.

[0004] Current guidelines recommend using risk prediction scores to assess the probability of ischemic events in patients with chest pain and to develop individualized follow-up treatment protocols based on the probability. However, traditional scores are designed for the entire chest pain population. Using these traditional scores for NHRCP patients may overestimate the true disease risk and fail to make accurate predictions for NHRCP patients, leading to unnecessary invasive examinations and causing unnecessary complications and financial burdens for patients.

[0005] Therefore, there is an urgent need for a precise diagnosis and treatment method and system for non-high-risk chest pain populations, which can more accurately predict the risk of non-high-risk chest pain patients. For low-risk non-high-risk chest pain patients, unnecessary invasive examinations can be reduced, and resources can be allocated effectively. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention provides a precise diagnosis and treatment method and system for non-high-risk chest pain patients, which can more accurately predict the risk of non-high-risk chest pain patients. For low-risk non-high-risk chest pain patients, it can reduce unnecessary invasive examinations and achieve effective resource allocation.

[0007] This invention provides a precise diagnosis and treatment method for non-high-risk chest pain populations, comprising the following steps: S1. Obtain known clinical information, known coronary imaging information, and known long-term clinical events in non-high-risk chest pain populations; S2. Construct a dataset by using known clinical information as independent variables and known coronary imaging information and known long-term clinical events as outcome variables; S3. Construct the XGBoost model and train it using the dataset to obtain the risk prediction scoring model. S4. Obtain the clinical information of the non-high-risk chest pain patients to be tested, input it into the risk prediction scoring model, and obtain the risk prediction score; S5. Determine the group to which the non-high-risk chest pain patient to be tested belongs based on the risk prediction score; S6. Determine subsequent treatment strategies based on the group to which the non-high-risk chest pain patients belong and their clinical information.

[0008] Furthermore, in S1, known clinical information includes myeloperoxidase, lipoprotein-associated phospholipase A2, and high-sensitivity cardiac troponin.

[0009] Furthermore, in S1, obtaining known coronary artery imaging information includes: Coronary artery images are obtained from non-high-risk individuals with chest pain via coronary CT angiography. Coronary artery images are processed to obtain coronary artery imaging information, which includes anatomical information based on the degree of luminal stenosis, histological information based on plaque characteristics, and functional information based on fractional flow reserve.

[0010] Furthermore, in S5, the groups to which the non-high-risk chest pain patients to be tested belong include the observation group and the examination group.

[0011] Furthermore, in S5, the group to which the non-high-risk chest pain patient to be tested belongs, based on the risk prediction score, includes: If the risk prediction score is less than the preset score threshold, the non-high-risk chest pain patients to be tested belong to the observation group. If the risk prediction score is greater than or equal to the preset score threshold, the non-high-risk chest pain patient to be tested belongs to the examination group.

[0012] Furthermore, in S6, the subsequent treatment strategies are determined based on the patient's group and clinical information, including: If the non-high-risk chest pain patients to be tested belong to the observation group, the subsequent diagnosis and treatment strategy shall be determined based on the clinical information of the non-high-risk chest pain patients to be tested. If the non-high-risk chest pain patient to be tested belongs to the examination group, then coronary CT angiography needs to be performed on the non-high-risk chest pain patient to obtain the coronary artery imaging results, and the subsequent diagnosis and treatment strategy should be determined based on the coronary artery imaging results and clinical information of the non-high-risk chest pain patient to be tested.

[0013] This invention also provides a precision diagnosis and treatment system for non-high-risk chest pain populations, used to implement the aforementioned precision diagnosis and treatment method for non-high-risk chest pain populations. The system includes the following modules: The data acquisition module is used to acquire known clinical information, known coronary artery imaging information, and known long-term clinical events in non-high-risk chest pain populations; The dataset construction module, connected to the data acquisition module, is used to construct a dataset by using known clinical information as independent variables and known coronary artery imaging information and known long-term clinical events as outcome variables. The model building module, connected to the dataset building module, is used to build the XGBoost model and train the XGBoost model using the dataset to obtain the risk prediction scoring model. The scoring module, connected to the model building module, is used to obtain clinical information of non-high-risk chest pain patients to be tested, input it into the risk prediction scoring model, and obtain the risk prediction score. The grouping module, connected to the scoring module, is used to determine the group to which a non-high-risk chest pain patient belongs based on the risk prediction score. The treatment strategy formulation module, connected to the grouping module, is used to determine subsequent treatment strategies based on the group to which the non-high-risk chest pain patients belong and their clinical information.

[0014] The embodiments of the present invention have the following technical effects: This invention combines clinical information, coronary imaging data, and long-term clinical event data from non-high-risk chest pain patients with an XGBoost model for comprehensive analysis. This allows for more accurate prediction of disease risk in these patients. Based on their risk scores, patients are divided into observation and examination groups, enabling personalized treatment plans for different risk levels. For low-risk patients, unnecessary invasive examinations can be reduced; while for intermediate- and high-risk patients, further examinations and treatments can be scheduled promptly, achieving efficient resource allocation. This approach, by introducing advanced machine learning technology and combining multi-dimensional patient information, achieves precise diagnosis and treatment for non-high-risk chest pain patients, improving diagnostic accuracy, optimizing the use of medical resources, and enhancing the patient experience. Attached Figure Description

[0015] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1 This is a flowchart of a precision diagnosis and treatment method for non-high-risk chest pain populations provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a precision diagnosis and treatment system for non-high-risk chest pain populations provided in an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0018] This invention provides a precise diagnosis and treatment method for non-high-risk chest pain populations. Figure 1 This is a flowchart of a precision diagnosis and treatment method for non-high-risk chest pain populations provided by an embodiment of the present invention. See also... Figure 1 Specifically, it includes: S1. Obtain known clinical information, known coronary imaging information, and known long-term clinical events from non-high-risk chest pain populations.

[0019] In some embodiments, known clinical information of non-high-risk chest pain individuals is obtained through clinical history taking, physical examination, point-of-care testing (POCT), and general examinations. This known clinical information includes, but is not limited to, clinical history taking, physical examination, PCOT laboratory indicators, routine examination results such as ECG, and clinical follow-up results. Furthermore, known clinical information also includes myeloperoxidase (MPO), lipoprotein-associated phospholipase A2 (Lp-PLA2), and high-sensitivity cardiac troponin (hs-cTn). Among them, MPO is an enzyme found in leukocytes, and its elevated levels may be related to the inflammatory process, which is an important pathological mechanism of cardiovascular disease; Lp-PLA2 is an enzyme mainly produced by macrophages and participates in the process of atherosclerotic plaque formation. High levels of Lp-PLA2 are considered to be associated with an increased risk of cardiovascular events; hs-cTn is a very sensitive marker of myocardial injury, which can detect even very small myocardial injuries. Elevated hs-cTn levels are usually an indication of acute coronary syndromes (such as myocardial infarction). With the continuous improvement of test accuracy, hs-cTn has been shown not only to serve as a qualitative variable in the diagnosis of myocardial infarction, but its linear changes can also reflect the degree of myocardial damage and coronary artery lesions, and it can also serve as an independent predictor of the long-term prognosis of NHRCP patients; therefore, the above three indicators are added to the input features of the prediction model.

[0020] In some embodiments, obtaining known coronary artery imaging information includes: Coronary artery images are obtained from non-high-risk individuals with chest pain using coronary CT angiography.

[0021] For example, all patients first underwent Siemens dual-source CT (Somatom Definition Flash) scanning. A non-contrast scan was performed first to determine the extent of the contrast scan: at a tube voltage of 120 kV, a collimation of 24 mm × 1.2 mm, a pitch of 1.2 mm, and a slice thickness of 1.5 mm was used to complete a continuous scan from the aortic root to the apex within one respiratory motion. Subsequently, a CCTA scan was performed: iodine contrast agent and normal saline were injected via the antecubital vein using a high-pressure injector at a flow rate of approximately 5 ml / s. The delayed trigger scan time was calculated using the test bolus technique. A region of interest was selected at the aortic root level to monitor CT values; the time to peak CT value plus 5 seconds was used as the delayed trigger scan time. Scanning parameters: collimation 64 mm × 0.6 mm, slice thickness 0.75 mm, gantry rotation time 0.33 s, tube voltage 100 kV (BMI < 30 kg / m²). 2 ) or 120 kV (BMI>30 kg / m 2 (Pitch 0.2mm). The full-dose exposure range for scanning is 30% to 80% RR interval.

[0022] Coronary artery images are processed to obtain coronary artery imaging information, which includes anatomical information based on the degree of luminal stenosis, histological information based on plaque characteristics, and functional information based on fractional flow reserve.

[0023] For example, the Voxelcloud Autoplaque software, jointly developed by Suzhou Voxel Information Technology Co., Ltd. and Cedars-Sinai Medical Center in Los Angeles, USA, was used to semi-automatically analyze the degree of coronary artery stenosis and plaque characteristics. After importing the CCTA standard image file into the software, the start and end points of the target vessel segment were first manually selected, and then the blood pool signal reference area was selected. Next, the software automatically generated the coronary artery centerline and lumen region segmentation (which could be manually corrected), and performed vessel surface reconstruction and short-axis and long-axis reconstruction. Based on this, the software automatically calculated parameters such as the volume of calcified, high-density non-calcified and low-density non-calcified plaques, the length and degree of stenosis of the lesion, the vascular remodeling index, and quantitative geometric descriptions of the proximal, distal, and stenotic regions of the vessel. The entire coronary tree was segmented, and all segments with a diameter greater than 2 mm were classified according to the following criteria: no stenosis, 1%-24% stenosis, 25%-49% stenosis, 50%-69% stenosis, 70%-99% stenosis, and complete occlusion. High-risk plaque characteristics such as low-density plaques (CT value <30 HU), positive remodeling (remodeling index ≥1.1), napkin sign, and punctate calcifications (density >130 HU, diameter <3 mm) were measured. The virtual FFR (Fractional Flow Reserve) value of the entire coronary tree, i.e., CTFFR (Coronary CT Fractional Flow Reserve AI Quantitative Analysis), was calculated using Siemens' software specifically designed for calculating CTFFR. The specific steps of cFFR (Contrast-FFR) are as follows: After importing the standard CCTA image into cFFR, the software will automatically draw the lumen outline and vessel centerline of the entire coronary artery tree. After manually modifying and adjusting the lumen boundary and vessel centerline and marking the target lesion, cFFR will automatically generate a three-dimensional model of the entire coronary artery tree and visualize the calculated entire coronary artery tree and the virtual FFR of the target lesion.

[0024] S2. Construct a dataset by using known clinical information as independent variables and known coronary imaging information and known long-term clinical events as outcome variables.

[0025] S3. Construct the XGBoost model and train it using the dataset to obtain the risk prediction scoring model.

[0026] In some embodiments, if a patient’s coronary artery lesion has one of the following characteristics: anatomical stenosis exceeding 25%, CTFFR < 0.8, or high-risk plaque features, the lesion is the predictive endpoint of this part of the study and is defined as a positive lesion. Patients with at least one positive lesion are assigned to the case group, and the remaining patients are assigned to the control group.

[0027] In some embodiments, the clinical characteristics and classification (case group and control group) of each patient are compiled and included in the analysis (this can be achieved using the Pandas package). The dataset is randomly divided into training and validation sets to ensure that the proportion of case and control groups is roughly the same in both sets. The training set is randomly divided into 10 subsets, and the model is repeatedly fitted and its parameters are continuously adjusted through cross-validation to optimize model performance (this can be achieved using the XGBoost package). The best-performing XGBoost model in the validation set is used as the final risk prediction scoring model, and the features in the risk prediction scoring model are ranked by importance (this can be achieved using the Shap package).

[0028] S4. Obtain the clinical information of the non-high-risk chest pain patients to be tested, input it into the risk prediction scoring model, and obtain the risk prediction score.

[0029] S5. Determine the group to which the non-high-risk chest pain patient to be tested belongs based on the risk prediction score.

[0030] In some embodiments, the groups to which the non-high-risk chest pain patients to be tested belong include an observation group and an examination group. If the risk prediction score is less than a preset score threshold, the non-high-risk chest pain patients to be tested belong to the observation group; if the risk prediction score is greater than or equal to the preset score threshold, the non-high-risk chest pain patients to be tested belong to the examination group.

[0031] S6. Determine subsequent treatment strategies based on the group to which the non-high-risk chest pain patients belong and their clinical information.

[0032] In some embodiments, if the group to be tested for non-high-risk chest pain belongs to the observation group, the subsequent diagnosis and treatment strategy is determined based on the clinical information of the patients to be tested for non-high-risk chest pain. If the non-high-risk chest pain patient to be tested belongs to the examination group, then coronary CT angiography needs to be performed on the non-high-risk chest pain patient to obtain the coronary artery imaging results, and the subsequent diagnosis and treatment strategy should be determined based on the coronary artery imaging results and clinical information of the non-high-risk chest pain patient to be tested.

[0033] Based on the imaging information provided by CCTA and combined with the clinical information of the non-high-risk chest pain patients to be tested, subsequent OMT (Optimal Medical Therapy), CTFFR, and ICA (Invasive Coronary Angiography) / FFR are selected, and the need for revascularization is determined based on the results of ICA / FFR.

[0034] A Philips FD20 single-channel X-ray tube cardiovascular camera and a standard digital imaging system were used to perform CAG (Coronary Angiography) on the patient using standard techniques: the skin at the puncture site was disinfected with 0.5% povidone-iodine, draped, and local anesthesia was administered with 2% lidocaine at the planned puncture site. The radial or femoral artery was punctured, and an arterial sheath was inserted. Unfractionated heparin was injected through the sheath, and a guidewire catheter was then inserted. The standard Judkins method was used for CAG examination, employing multiple imaging positions for the left main coronary artery, left anterior descending artery, circumflex artery, and right coronary artery. At least two positions were selected for each lesion. If necessary, 0.2 mg of nitroglycerin was administered intravascularly into the target vessel. The proximal and distal reference vessel diameters of the lesion segment, the lesion location, and the degree of stenosis were estimated (the stenosis rate equals 1 - minimum lumen diameter / average diameter of the reference segment). The results were then analyzed according to CAD-RADS. TM The Coronary Artery Disease-Reporting and Data System (CAIDS) divides the entire coronary tree into segments. Segments with a diameter greater than 2 mm are classified according to the following criteria: no stenosis, 1%-49% stenosis, 50%-90% stenosis, and more than 90% stenosis.

[0035] Invasive FFR measurement is performed on lesions with diameter stenosis of 50%-90%. A non-side-hole guiding catheter and pressure guidewire are used to measure the FFR of the target vessel lesion. After anticoagulation, the guidewire is passed distal to the target vessel segment, and nitroglycerin is administered intracoronary. Once the baseline pressure stabilizes, adenosine is infused intravenously at a rate of 140 mg / kg / min. Pressure (Pd) is recorded once the target vessel segment reaches maximum congestion. The calculation formula is: FFR = Pd / Pa, where Pa is the mean aortic pressure at the coronary ostium automatically measured by the fluid pressure sensor on the guiding catheter. Revascularization is performed on lesions with diameter stenosis of 50%-90% and an FFR less than 0.8, as well as lesions with stenosis exceeding 90%.

[0036] This invention combines clinical information, coronary imaging data, and long-term clinical event data from non-high-risk chest pain patients with an XGBoost model for comprehensive analysis. This allows for more accurate prediction of disease risk in these patients. Based on their risk scores, patients are divided into observation and examination groups, enabling personalized treatment plans for different risk levels. For low-risk patients, unnecessary invasive examinations can be reduced; while for intermediate- and high-risk patients, further examinations and treatments can be scheduled promptly, achieving efficient resource allocation. This approach, by introducing advanced machine learning technology and combining multi-dimensional patient information, achieves precise diagnosis and treatment for non-high-risk chest pain patients, improving diagnostic accuracy, optimizing the use of medical resources, and enhancing the patient experience.

[0037] Furthermore, because the XGBoost model can provide an assessment of feature importance, doctors can understand which factors have the greatest impact on risk prediction, which helps them make more scientific and reasonable decisions.

[0038] This invention provides a precision diagnosis and treatment system for non-high-risk chest pain populations. Figure 2 This is a schematic diagram of a precision diagnosis and treatment system for non-high-risk chest pain populations provided in an embodiment of the present invention. (See attached diagram.) Figure 2 This system is used to implement the aforementioned precision diagnosis and treatment method for non-high-risk chest pain populations. The system includes the following modules: The data acquisition module is used to acquire known clinical information, known coronary artery imaging information, and known long-term clinical events in non-high-risk chest pain populations; The dataset construction module, connected to the data acquisition module, is used to construct a dataset by using known clinical information as independent variables and known coronary artery imaging information and known long-term clinical events as outcome variables. The model building module, connected to the dataset building module, is used to build the XGBoost model and train the XGBoost model using the dataset to obtain the risk prediction scoring model. The scoring module, connected to the model building module, is used to obtain clinical information of non-high-risk chest pain patients to be tested, input it into the risk prediction scoring model, and obtain the risk prediction score. The grouping module, connected to the scoring module, is used to determine the group to which a non-high-risk chest pain patient belongs based on the risk prediction score. The treatment strategy formulation module, connected to the grouping module, is used to determine subsequent treatment strategies based on the group to which the non-high-risk chest pain patients belong and their clinical information.

[0039] It should be noted that the terminology used in this invention is for describing specific embodiments only and is not intended to limit the scope of this application. As shown in this specification, unless the context clearly indicates otherwise, words such as "a," "an," "an," and / or "the" do not specifically refer to the singular and may include the plural. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element.

[0040] It should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Unless otherwise expressly specified and limited, the terms "installed," "connected," "linked," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components. For those skilled in the art, the specific meaning of the above terms in the present invention can be understood according to the specific circumstances.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A precision diagnosis and treatment method for non-high-risk chest pain populations, characterized in that, Includes the following steps: S1. Obtain known clinical information, known coronary imaging information, and known long-term clinical events in non-high-risk chest pain populations; S2. Construct a dataset by using the known clinical information as the independent variable, and the known coronary artery imaging information and the known long-term clinical events as outcome variables; S3. Construct an XGBoost model and train it using the dataset to obtain a risk prediction scoring model. S4. Obtain the clinical information of the non-high-risk chest pain patient to be tested, input it into the risk prediction scoring model, and obtain the risk prediction score; S5. Determine the group to which the non-high-risk chest pain patient to be tested belongs based on the risk prediction score; S6. Determine the subsequent diagnosis and treatment strategy based on the group to which the non-high-risk chest pain patients to be tested belong and the clinical information of the non-high-risk chest pain patients to be tested.

2. The precision diagnosis and treatment method for non-high-risk chest pain populations according to claim 1, characterized in that, In S1, the known clinical information includes: myeloperoxidase, lipoprotein-associated phospholipase A2, and high-sensitivity cardiac troponin.

3. The precision diagnosis and treatment method for non-high-risk chest pain populations according to claim 1, characterized in that, In step S1, obtaining the known coronary artery imaging information includes: Coronary artery images are obtained from non-high-risk individuals with chest pain via coronary CT angiography. The coronary artery images are processed to obtain coronary artery imaging information; wherein, the coronary artery imaging information includes anatomical information based on the degree of luminal stenosis, histological information based on plaque characteristics, and functional information based on fractional flow reserve.

4. The precision diagnosis and treatment method for non-high-risk chest pain populations according to claim 1, characterized in that, In S5, the groups to which the non-high-risk chest pain patients to be tested belong include the observation group and the examination group.

5. A precise diagnosis and treatment method for non-high-risk chest pain populations according to claim 4, characterized in that, In step S5, determining the group to which the non-high-risk chest pain patient belongs based on the risk prediction score includes: If the risk prediction score is less than the preset score threshold, the non-high-risk chest pain patient to be tested belongs to the observation group. If the risk prediction score is greater than or equal to the preset score threshold, then the non-high-risk chest pain patient to be tested belongs to the examination group.

6. A precise diagnosis and treatment method for non-high-risk chest pain populations according to claim 5, characterized in that, In step S6, determining the subsequent treatment strategy based on the group to which the non-high-risk chest pain patient belongs and the patient's clinical information includes: If the non-high-risk chest pain patient to be tested belongs to the observation group, the subsequent diagnosis and treatment strategy shall be determined based on the clinical information of the non-high-risk chest pain patient to be tested. If the non-high-risk chest pain patient to be tested belongs to the examination group, then coronary CT angiography needs to be performed on the non-high-risk chest pain patient to obtain the coronary artery imaging results of the non-high-risk chest pain patient to be tested, and the subsequent diagnosis and treatment strategy is determined based on the coronary artery imaging results and clinical information of the non-high-risk chest pain patient to be tested.

7. A precision diagnosis and treatment system for non-high-risk chest pain populations, used to implement the precision diagnosis and treatment method for non-high-risk chest pain populations as described in any one of claims 1-6, characterized in that, The system includes the following modules: The data acquisition module is used to acquire known clinical information, known coronary artery imaging information, and known long-term clinical events in non-high-risk chest pain populations; A dataset construction module, connected to the data acquisition module, is used to construct a dataset by using the known clinical information as independent variables and the known coronary artery imaging information and the known long-term clinical events as outcome variables. The model building module, connected to the dataset building module, is used to build an XGBoost model and train the XGBoost model using the dataset to obtain a risk prediction scoring model. The scoring module, connected to the model building module, is used to obtain clinical information of non-high-risk chest pain patients to be tested, input it into the risk prediction scoring model, and obtain a risk prediction score. A grouping module, connected to the scoring module, is used to determine the group to which the non-high-risk chest pain patient to be tested belongs based on the risk prediction score. The treatment strategy formulation module, connected to the grouping module, is used to determine the subsequent treatment strategy based on the group to which the non-high-risk chest pain patient to be tested belongs and the clinical information of the non-high-risk chest pain patient to be tested.

Images