Atrial fibrillation occurrence risk assessment method, system, equipment and medium

Abstract

The invention relates to the technical field of medical data processing, and discloses an atrial fibrillation occurrence risk assessment method, system and device and a medium, and the method comprises the steps: obtaining a global atrial fibrillation occurrence risk index of a to-be-tested person through a global atrial fibrillation occurrence risk index assessment model in combination with a paper electrocardiogram image and clinical data of the to-be-tested person; obtaining a local atrial fibrillation occurrence risk index of the to-be-tested person by using the electrocardiogram P-wave data of the to-be-tested person, the P-wave feature data and a preset atrial fibrillation risk-free electrocardiogram P-wave standard template, and obtaining a final atrial fibrillation occurrence risk index of the to-be-tested person by combining a risk factor matrix of the to-be-tested person. The method can assist in efficiently and accurately evaluating the risk index of the atrial fibrillation of the to-be-detected person, improves the comfort of the to-be-detected person during detection, is beneficial for a patient to timely find the possibility of the atrial fibrillation and timely seeing a doctor, and provides effective data support for medical staff to formulate a proper medical scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a method, system, device and medium for assessing the risk of atrial fibrillation occurrence. Background Art

[0002] With the aging of the population, the incidence of heart diseases has been continuously increasing in recent years, seriously threatening people's health. Atrial fibrillation, as one of the most common heart diseases, is usually abbreviated as AF. Stroke and deterioration of cardiac function caused by AF are important reasons for disability and death of patients. AF has extremely strong concealment in the initial stage of onset, and the potential hidden dangers of aggravating the condition are more serious, which will affect the timeliness of patients' medical treatment and the decision-making of treatment plans.

[0003] In traditional AF detection methods, the most commonly used is dynamic electrocardiogram screening, which collects electrocardiograms through a dynamic electrocardiograph and then is judged by a doctor. However, dynamic electrocardiogram screening requires patients to wear electrocardiogram monitoring equipment for a long time, which takes a long time and is prone to missed detection situations such as "no onset during detection and no detection during onset". At the same time, long-term use of electrode patches may cause skin discomfort or even allergic reactions in patients, seriously affecting the willingness of patients to use.

[0004] Therefore, there is an urgent need for a method, system, device and medium for assessing the risk of atrial fibrillation occurrence to assist in efficiently assessing the risk index of patients' atrial fibrillation occurrence, which is beneficial for patients to seek medical treatment in time and at the same time provides effective data support for medical staff to formulate medical treatment plans. Summary of the Invention

[0005] The present invention provides a method, system, device and medium for assessing the risk of atrial fibrillation occurrence to solve the defects of the existing AF detection methods, such as low detection efficiency, poor accuracy, and low patient comfort, resulting in difficulty in timely detecting patients and affecting the treatment process.

[0006] A method for assessing the risk of atrial fibrillation occurrence provided by the present invention includes:

[0007] Obtain the paper electrocardiogram image and clinical data of the person to be tested;

[0008] According to the paper electrocardiogram image of the person to be tested, obtain the global atrial fibrillation occurrence risk index of the person to be tested through the global atrial fibrillation occurrence risk index assessment model;

[0009] According to the paper electrocardiogram image of the person to be tested, obtain the electrocardiogram P-wave data and P-wave characteristic data of the person to be tested;

[0010] According to the electrocardiogram P-wave data, P-wave characteristic data of the person to be tested and the preset electrocardiogram P-wave standard template without atrial fibrillation risk, obtain the local atrial fibrillation occurrence risk index of the person to be tested;

[0011] Based on the clinical data of the subject to be tested, a risk factor matrix of the subject to be tested is obtained;

[0012] Based on the risk factor matrix, the global atrial fibrillation occurrence risk index, and the local atrial fibrillation occurrence risk index of the subject to be tested, the final atrial fibrillation occurrence risk index of the subject to be tested is obtained.

[0013] According to a method for assessing the risk of atrial fibrillation provided by the present invention, the clinical data includes any one of the following or any combination thereof: gender, age, height, weight, diastolic blood pressure, systolic blood pressure.

[0014] According to a method for assessing the risk of atrial fibrillation provided by the present invention, the obtaining of the paper electrocardiogram image and clinical data of the subject to be tested includes:

[0015] Performing background removal processing and binarization processing on the paper electrocardiogram image of the subject to be tested to obtain the binarized electrocardiogram of the subject to be tested;

[0016] Performing lead superposition, filtering, and resampling on the binarized electrocardiogram of the subject to be tested to obtain an enhanced electrocardiogram waveform of the binarized electrocardiogram of the subject to be tested.

[0017] According to a method for assessing the risk of atrial fibrillation provided by the present invention, the performing of background removal processing and binarization processing on the paper electrocardiogram image of the subject to be tested to obtain the binarized electrocardiogram of the subject to be tested includes:

[0018] Converting the paper electrocardiogram image of the subject to be tested into a grayscale image;

[0019] Performing pixel value statistics, duplicate pixel value removal, and binarization on the grayscale image to obtain a reverse binarized electrocardiogram with a white background and a black electrocardiogram;

[0020] Subtracting each pixel value in the reverse binarized electrocardiogram by a preset value to obtain the binarized electrocardiogram of the subject to be tested.

[0021] According to a method for assessing the risk of atrial fibrillation provided by the present invention, the performing of lead superposition, filtering, and resampling on the binarized electrocardiogram of the subject to be tested to obtain the enhanced electrocardiogram waveform of the binarized electrocardiogram of the subject to be tested includes:

[0022] Performing vertical pixel summation on the binarized electrocardiogram of the subject to be tested to obtain a lead superposition electrocardiogram waveform;

[0023] Performing filtering and resampling on the lead superposition electrocardiogram waveform to obtain the enhanced electrocardiogram waveform of the binarized electrocardiogram of the subject to be tested.

[0024] According to a method for assessing the risk of atrial fibrillation provided by the present invention, a global atrial fibrillation risk index assessment model is trained based on the training data of the target population, wherein the target population includes an atrial fibrillation patient group and a healthy population, and the training data includes the paper electrocardiogram image sample data of the target population and the corresponding global atrial fibrillation risk index label data.

[0025] According to a method for assessing the risk of atrial fibrillation provided by the present invention, obtaining the electrocardiogram P-wave data and P-wave characteristic data of the person to be tested based on the paper electrocardiogram image of the person to be tested includes:

[0026] Based on the enhanced electrocardiogram waveform of the binary electrocardiogram of the person to be tested, obtaining each P wave of each heartbeat in the electrocardiogram signal as the electrocardiogram P-wave data of the person to be tested, and obtaining the P-wave characteristics in the electrocardiogram signal as the P-wave characteristic data, wherein the P-wave characteristics include any one of the following or any combination thereof: P-wave width, P-wave height, P-wave amplitude change rate, number of P-wave peaks, R / P amplitude ratio.

[0027] According to a method for assessing the risk of atrial fibrillation provided by the present invention, obtaining each P wave of each heartbeat in the electrocardiogram signal as the electrocardiogram P-wave data of the person to be tested, and obtaining the P-wave characteristics in the electrocardiogram signal as the P-wave characteristic data based on the enhanced electrocardiogram waveform of the binary electrocardiogram of the person to be tested includes:

[0028] Based on the enhanced electrocardiogram waveform of the binary electrocardiogram of the person to be tested, obtaining all the R-wave positions in the enhanced electrocardiogram waveform, and obtaining a heartbeat R-wave position list with a length of N and an R-wave amplitude list with a length of N, where N is the number of R waves;

[0029] Traversing the heartbeat R-wave position list to obtain a position list of 0.24 seconds before the QRS wave with a length of N;

[0030] Traversing the position list of 0.24 s before the QRS wave to obtain a P-wave region matrix with a dimension of M×N, where M is the length of the P-wave region;

[0031] Traversing the P-wave region matrix to obtain a P-wave peak list with a length of N, a P-wave start position list with a length of N, a P-wave end position list with a length of N, and a P-wave peak position list with a length of N;

[0032] Based on the P-wave peak position list, obtaining a P-wave height characteristic matrix with a dimension of 1×N;

[0033] Based on the P-wave start position list and the P-wave end position list, obtaining a P-wave width characteristic matrix with a dimension of 1×N;

[0034] According to the P-wave region matrix, the P-wave starting position list, and the P-wave ending position list, a P-wave amplitude change rate feature matrix with a dimension of 1×N is obtained;

[0035] According to the P-wave peak list, a P-wave peak number feature matrix with a dimension of 1×N is obtained;

[0036] According to the R-wave amplitude list and the P-wave peak list, an R / P amplitude ratio feature matrix with a dimension of 1×N is obtained;

[0037] Integrate the P-wave height feature matrix, the P-wave width feature matrix, the P-wave amplitude change rate feature matrix, the P-wave peak number feature matrix, and the R / P amplitude ratio feature matrix to obtain a heartbeat P-wave feature matrix with a dimension of 5×N as the P-wave feature data.

[0038] According to a method for assessing the risk of atrial fibrillation provided by the present invention, a preset P-wave standard template for electrocardiograms without the risk of atrial fibrillation is constructed based on the enhanced electrocardiogram waveforms of the paper electrocardiogram images of healthy people.

[0039] According to a method for assessing the risk of atrial fibrillation provided by the present invention, obtaining the local atrial fibrillation occurrence risk index of a subject according to the electrocardiogram P-wave data, the P-wave feature data, and the preset P-wave standard template for electrocardiograms without the risk of atrial fibrillation includes:

[0040] According to the electrocardiogram P-wave data of the subject and the preset P-wave standard template for electrocardiograms without the risk of atrial fibrillation, a dynamic heartbeat atrial fibrillation occurrence weight matrix of the subject is obtained;

[0041] According to the dynamic heartbeat atrial fibrillation occurrence weight matrix and the P-wave feature data of the subject, the local atrial fibrillation occurrence risk index of the subject is obtained.

[0042] According to a method for assessing the risk of atrial fibrillation provided by the present invention, obtaining the dynamic heartbeat atrial fibrillation occurrence weight matrix of the subject according to the electrocardiogram P-wave data of the subject and the preset P-wave standard template for electrocardiograms without the risk of atrial fibrillation includes:

[0043] According to the electrocardiogram P-wave data of the subject and the preset P-wave standard template for electrocardiograms without the risk of atrial fibrillation, the P-wave standard template amplitude sequence P hb 、P-wave standard template width sequence P lb 、P-wave standard template width first derivative sequence P db 、P-wave standard template peak number P pb 、P-wave standard template R / P amplitude ratio P rb , and the P-wave amplitude sequence P of the subject hd 、P-wave width sequence P ld 、P-wave width first derivative sequence P dd 、P-wave peak number Ppd 1. The P wave R / P amplitude ratio P rd ;

[0044] Obtain and use the amplitude sequence P of the P wave standard template hb and the P wave amplitude sequence P of the subject to be tested hd as the first weight factor of the dynamic cardiac fibrillation occurrence weight matrix, obtain and use the width sequence P of the P wave standard template lb and the P wave width sequence P of the subject to be tested ld as the second weight factor of the dynamic cardiac fibrillation occurrence weight matrix, obtain and use the first derivative sequence P of the width of the P wave standard template db and the first derivative sequence P of the P wave width of the subject to be tested dd as the third weight factor of the dynamic cardiac fibrillation occurrence weight matrix, obtain and use the peak number P of the P wave standard template pb and the P wave peak number P of the subject to be tested pd as the fourth weight factor of the dynamic cardiac fibrillation occurrence weight matrix, obtain and use the R / P amplitude ratio of the P wave standard template and P rb and the P wave R / P amplitude ratio P of the subject to be tested rd as the fifth weight factor of the dynamic cardiac fibrillation occurrence weight matrix;

[0045] Integrate the first weight factor, the second weight factor, the third weight factor, the fourth weight factor, and the fifth weight factor to obtain the dynamic cardiac fibrillation occurrence weight matrix of the subject to be tested.

[0046] According to a method for assessing the risk of atrial fibrillation provided by the present invention, obtaining the local atrial fibrillation occurrence risk index of the subject to be tested based on the dynamic cardiac fibrillation occurrence weight matrix and the P wave characteristic data of the subject to be tested includes:

[0047] Multiply the dynamic cardiac fibrillation occurrence weight matrix of the subject to be tested by the cardiac P wave characteristic matrix to obtain the cardiac fibrillation risk index matrix of the subject to be tested;

[0048] Traverse the cardiac fibrillation risk index matrix of the subject to be tested, and obtain the local atrial fibrillation occurrence risk index of the subject to be tested through the first expression, where the first expression is:

[0049]

[0050] In the first expression, R f represents the local atrial fibrillation occurrence risk index of the subject to be tested, R i represents the i-th cardiac fibrillation risk index in the cardiac fibrillation risk index matrix, and N represents the number of risk factors in the cardiac fibrillation risk index matrix.

[0051] A method for assessing the risk of atrial fibrillation according to the present invention, obtaining the final atrial fibrillation occurrence risk index of the subject according to the risk factor matrix, global atrial fibrillation occurrence risk index and local atrial fibrillation occurrence risk index of the subject, including:

[0052] According to the risk factor matrix, global atrial fibrillation occurrence risk index and local atrial fibrillation occurrence risk index of the subject, the final atrial fibrillation occurrence risk index of the subject is obtained through a second expression, where the second expression is:

[0053]

[0054] In the second expression, R r represents the final atrial fibrillation occurrence risk index of the subject, R m represents the global atrial fibrillation occurrence risk index of the subject, R f represents the local atrial fibrillation occurrence risk index of the subject, A j represents the j-th risk factor in the risk factor matrix A, and T represents the number of risk factors in the risk factor matrix A.

[0055] The present invention also provides an atrial fibrillation occurrence risk auxiliary assessment system, including:

[0056] A data receiving module, configured to: receive the paper electrocardiogram image and clinical data of the subject;

[0057] A global atrial fibrillation occurrence risk index assessment module, configured to: obtain the global atrial fibrillation occurrence risk index of the subject according to the paper electrocardiogram image of the subject through a global atrial fibrillation occurrence risk index assessment model;

[0058] A first data processing module, configured to: obtain the electrocardiogram P-wave data and P-wave characteristic data of the subject according to the paper electrocardiogram image of the subject;

[0059] A local atrial fibrillation occurrence risk index assessment module, configured to: obtain the local atrial fibrillation occurrence risk index of the subject according to the electrocardiogram P-wave data, P-wave characteristic data of the subject and a preset electrocardiogram P-wave standard template without atrial fibrillation risk;

[0060] A second data processing module, configured to: obtain the risk factor matrix of the subject according to the clinical data of the subject;

[0061] A final atrial fibrillation occurrence risk index assessment module, configured to: obtain the final atrial fibrillation occurrence risk index of the subject according to the risk factor matrix, global atrial fibrillation occurrence risk index and local atrial fibrillation occurrence risk index of the subject;

[0062] A data output module, configured to: send the final atrial fibrillation occurrence risk index of the subject to at least one terminal.

[0063] It should be noted that a terminal refers to an input / output device connected to a computer system. According to different functions, terminals can be divided into various types: smart terminals or intelligent terminals, dumb terminals, interactive terminals or online terminals. Specifically, a terminal can be various mobile communication devices, such as mobile phones, tablets, etc. The purpose of this article is to provide users with the functions of inputting data and obtaining data output.

[0064] The present invention also provides an electronic device, including a processor and a memory storing a computer program. When the processor executes the computer program, the above-mentioned any one of the atrial fibrillation occurrence risk assessment methods is implemented.

[0065] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned any one of the atrial fibrillation occurrence risk assessment methods is implemented.

[0066] The present invention also provides a computer program product. The computer program product includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the above-mentioned any one of the atrial fibrillation occurrence risk assessment methods.

[0067] An atrial fibrillation occurrence risk assessment method, system, device and medium provided by the present invention combine the paper electrocardiogram image and clinical data of a subject to obtain the global atrial fibrillation occurrence risk index of the subject by using the global atrial fibrillation occurrence risk index assessment model, and use the electrocardiogram P-wave data, P-wave feature data of the subject and a preset electrocardiogram P-wave standard template without atrial fibrillation risk to obtain the local atrial fibrillation occurrence risk index of the subject, and then combine the risk factor matrix of the subject to obtain the final atrial fibrillation occurrence risk index of the subject. It can assist in efficiently and accurately evaluating the risk index of a subject's occurrence of atrial fibrillation, improve the comfort of the subject during detection, and is conducive to the patient's timely discovery of the possibility of their occurrence of atrial fibrillation and timely medical treatment. At the same time, it provides effective data support for medical staff to formulate appropriate medical treatment plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0069] Figure 1 It is one of the flow diagrams of an atrial fibrillation occurrence risk assessment method provided by the present invention.

[0070] Figure 2 It is the second flowchart diagram of a method for assessing the risk of atrial fibrillation provided by the present invention.

[0071] Figure 3 It is the structural schematic diagram of a system for assessing the risk of atrial fibrillation provided by the present invention.

[0072] Figure 4 It is the structural schematic diagram of an electronic device provided by the present invention. Specific embodiments

[0073] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention, and they should not be construed as limiting the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts belong to the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for the purpose of description and cannot be construed as indicating or implying relative importance.

[0074] Figure 1-2 It is the flowchart diagram of a method for assessing the risk of atrial fibrillation provided by the present invention. The execution subject of the method for assessing the risk of atrial fibrillation provided by the present invention can be any terminal device or network device with an execution program built in, such as an atrial fibrillation risk assessment device, etc.

[0075] See Figure 1 , a method for assessing the risk of atrial fibrillation provided by the present invention may include:

[0076] S110. Obtain the paper electrocardiogram image and clinical data of the person to be tested.

[0077] Specifically, the paper electrocardiogram image and clinical data of the person to be tested can be obtained by medical staff through pre-testing and face-to-face consultations with patients in advance, or the user can take a photo of their own paper electrocardiogram to obtain the paper electrocardiogram image and measure the clinical data by themselves. In this embodiment, the clinical data includes: gender, age, height, weight, diastolic blood pressure, systolic blood pressure.

[0078] In one embodiment, after obtaining the paper electrocardiogram image of the person to be tested, S110 can preprocess the paper electrocardiogram image to make the quality of the electrocardiogram used later higher, such as background removal processing, binarization processing, lead superposition, filtering, resampling, etc. That is, S110 may include:

[0079] Convert the paper electrocardiogram image of the person to be tested into a grayscale image;

[0080] Perform pixel value statistics on the grayscale image, remove duplicate pixel values, and perform binarization (in this embodiment, the image is binarized using 0.95 times the median as the threshold), obtaining a reverse binarized electrocardiogram with a white background and a black electrocardiogram;

[0081] Subtract each pixel value in the reverse binarized electrocardiogram using a preset value (the preset value in this embodiment is 255), obtaining the binarized electrocardiogram of the subject.

[0082] S110 may further include:

[0083] Perform vertical pixel summation on the binarized electrocardiogram of the subject to obtain a lead superimposed electrocardiogram waveform;

[0084] Filter the lead superimposed electrocardiogram waveform using a band-pass filter of [0.67 - 40] to obtain the filtered lead superimposed electrocardiogram waveform of the subject;

[0085] Resample the filtered lead superimposed electrocardiogram waveform of the subject according to a preset sampling rate, resampling the filtered lead superimposed electrocardiogram waveform to the preset sampling rate, obtaining the enhanced electrocardiogram waveform of the binarized electrocardiogram of the subject.

[0086] S120. According to the paper electrocardiogram image of the subject, obtain the global atrial fibrillation occurrence risk index of the subject through the global atrial fibrillation occurrence risk index assessment model.

[0087] Among them, the global atrial fibrillation occurrence risk index assessment model can be pre-trained and verified based on the training data of the target population. Among them, the target population includes the atrial fibrillation occurrence patient group and the healthy population. The training data includes the paper electrocardiogram image sample data of the target population and the corresponding global atrial fibrillation occurrence risk index label data. The global atrial fibrillation occurrence risk index can be pre-specified manually. For example, the global atrial fibrillation occurrence risk index of the atrial fibrillation occurrence patient group is 1, and the global atrial fibrillation occurrence risk index of the healthy population is 0, and so on.

[0088] After training the global atrial fibrillation occurrence risk index assessment model, input the paper electrocardiogram image of the subject into the global atrial fibrillation occurrence risk index assessment model, and the global atrial fibrillation occurrence risk index R predicted by the global atrial fibrillation occurrence risk index assessment model of the subject can be obtained. m 。

[0089] S130. According to the paper electrocardiogram image of the subject, obtain the electrocardiogram P wave data and P wave feature data of the subject.

[0090] Specifically, S130 can obtain each P wave of the electrocardiogram signal from the enhanced electrocardiogram waveform of the binary electrocardiogram of the person to be tested as the electrocardiogram P wave data of the person to be tested, and obtain the P wave characteristics in the electrocardiogram signal as the P wave characteristic data. In this embodiment, the P wave characteristics include: P wave width, P wave height, P wave amplitude change rate, number of P wave peaks, and R / P amplitude ratio.

[0091] In one embodiment, S130 can obtain the cardiac beat P wave feature matrix as the P wave characteristic data through the following method:

[0092] According to the enhanced electrocardiogram waveform of the binary electrocardiogram of the person to be tested, use the wave peak detection algorithm to obtain the positions of all R waves in the enhanced electrocardiogram waveform, and obtain a cardiac beat R wave position list with a length of N and an R wave amplitude list with a length of N, where N is the number of R waves;

[0093] Traverse the cardiac beat R wave position list to obtain a position list of 0.24 seconds before the QRS wave with a length of N;

[0094] Traverse the position list of 0.24 s before the QRS wave, and take 0.2 seconds on each side of each position to obtain a P wave region matrix with a dimension of M×N, where M is the length of the P wave region;

[0095] Traverse the P wave region matrix to obtain a P wave peak list with a length of N, a P wave start position list with a length of N, a P wave end position list with a length of N, and a P wave peak position list with a length of N;

[0096] According to the P wave peak position list, obtain a P wave height feature matrix with a dimension of 1×N;

[0097] According to the P wave start position list and the P wave end position list, obtain a P wave width feature matrix with a dimension of 1×N;

[0098] According to the P wave region matrix, the P wave start position list and the P wave end position list, obtain a P wave amplitude change rate feature matrix with a dimension of 1×N;

[0099] According to the P wave peak list, obtain a P wave peak number feature matrix with a dimension of 1×N;

[0100] According to the R wave amplitude list and the P wave peak list, obtain an R / P amplitude ratio feature matrix with a dimension of 1×N;

[0101] Integrate the P wave height feature matrix, the P wave width feature matrix, the P wave amplitude change rate feature matrix, the P wave peak number feature matrix and the R / P amplitude ratio feature matrix to obtain a cardiac beat P wave feature matrix with a dimension of 5×N as the P wave characteristic data.

[0102] S140. Obtain the local atrial fibrillation occurrence risk index of the person to be tested based on the electrocardiogram P-wave data, P-wave characteristic data of the person to be tested, and a preset electrocardiogram P-wave standard template without atrial fibrillation risk.

[0103] Specifically, the preset electrocardiogram P-wave standard template without atrial fibrillation risk can be pre-constructed based on the enhanced electrocardiogram waveforms of the paper electrocardiogram images of healthy people. The healthy people can be those with sinus rhythm and no atrial fibrillation attacks in several years.

[0104] In one embodiment, S140 can first obtain the dynamic heartbeat atrial fibrillation occurrence weight matrix of the person to be tested according to the electrocardiogram P-wave data of the person to be tested and the preset electrocardiogram P-wave standard template without atrial fibrillation risk; then obtain the local atrial fibrillation occurrence risk index of the person to be tested according to the dynamic heartbeat atrial fibrillation occurrence weight matrix and P-wave characteristic data of the person to be tested.

[0105] Specifically, the dynamic heartbeat atrial fibrillation occurrence weight matrix of the person to be tested can be obtained in the following way:

[0106] According to the electrocardiogram P-wave data of the person to be tested and the preset electrocardiogram P-wave standard template without atrial fibrillation risk, obtain the P-wave standard template amplitude sequence P of dimension 1×L h and the P-wave amplitude sequence P of the person to be tested hb , the P-wave standard template width sequence P of dimension 1×L hd and the P-wave width sequence P of the person to be tested l , the P-wave standard template width first derivative sequence P of dimension 1×(L lb -1) and the P-wave width first derivative sequence P of the person to be tested ld , the P-wave standard template peak number P of dimension 1×1 l and the P-wave peak number P of the person to be tested db , the P-wave standard template R / P amplitude ratio and P of dimension 1×1 dd and the P-wave R / P amplitude ratio P of the person to be tested pb ; pd ; rb ; rd ;

[0107] Obtain and use the correlation between the P-wave standard template amplitude sequence P hb and the P-wave amplitude sequence P of the person to be tested hd as the first weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, obtain and use the correlation between the P-wave standard template width sequence P lb and the P-wave width sequence P of the person to be tested ld as the second weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, obtain and use the correlation between the P-wave standard template width first derivative sequence P db and the P-wave width first derivative sequence P of the person to be tested ddAs the third weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, obtain and use the number of peaks P of the P-wave standard template pb and the number of P-wave peaks P of the subject to be measured pd The ratio is used as the fourth weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, and obtain and use the R / P amplitude ratio of the P-wave standard template and P rb and the R / P amplitude ratio P of the P-wave of the subject to be measured rd The ratio is used as the fifth weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix;

[0108] Integrate the first weight factor, the second weight factor, the third weight factor, the fourth weight factor, and the fifth weight factor to obtain the dynamic heartbeat atrial fibrillation occurrence weight matrix of the subject to be measured.

[0109] After obtaining the dynamic heartbeat atrial fibrillation occurrence weight matrix of the subject to be measured, the dynamic heartbeat atrial fibrillation occurrence weight matrix of the subject to be measured and the heartbeat P-wave feature matrix can be multiplied to obtain the heartbeat atrial fibrillation risk index matrix of the subject to be measured with a dimension of 1×N; then traverse the heartbeat atrial fibrillation risk index matrix of the subject to be measured, and through the first expression, obtain the local atrial fibrillation occurrence risk index of the subject to be measured, where the first expression is:

[0110]

[0111] In the first expression, R f represents the local atrial fibrillation occurrence risk index of the subject to be measured, and R i represents the i-th heartbeat atrial fibrillation risk index in the heartbeat atrial fibrillation risk index matrix, and N represents the number of risk factors in the heartbeat atrial fibrillation risk index matrix.

[0112] S150. According to the clinical data of the subject to be measured, obtain the risk factor matrix of the subject to be measured.

[0113] S160. According to the risk factor matrix, the global atrial fibrillation occurrence risk index, and the local atrial fibrillation occurrence risk index of the subject to be measured, obtain the final atrial fibrillation occurrence risk index of the subject to be measured.

[0114] In one embodiment, S160 can obtain the final atrial fibrillation occurrence risk index of the subject to be measured according to the risk factor matrix, the global atrial fibrillation occurrence risk index, and the local atrial fibrillation occurrence risk index of the subject to be measured through the second expression, where the second expression is:

[0115]

[0116] In the second expression, R r represents the final atrial fibrillation occurrence risk index of the subject to be measured, and R m represents the global atrial fibrillation occurrence risk index of the subject to be measured, and R fIndicates the local atrial fibrillation occurrence risk index of the subject to be tested, A j Indicates the j-th risk factor in the risk factor matrix A, and T represents the number of risk factors in the risk factor matrix A.

[0117] A positive example and a negative example are provided below to better illustrate a method for assessing the risk of atrial fibrillation occurrence provided by the present invention.

[0118] Positive embodiment:

[0119] Subject to be tested: male, 65 years old, height 185 cm, weight 100 kg, diastolic blood pressure 95 mmHg, systolic blood pressure 150 mmHg in clinical data.

[0120] Mean and standard deviation of the population, gender (0, 1), age (50, 15), height (165, 10), weight (70, 15), diastolic blood pressure (80, 10), systolic blood pressure (120, 20).

[0121] The reference information matrix is:

[0122] [1 65 165 85 95 150].

[0123] The risk factor matrix (normalized using the mean and standard deviation of the population) is:

[0124] A = [1 1 2 2 1.5 1.5].

[0125] The global atrial fibrillation occurrence risk index Rm is 0.99.

[0126] The standard P-wave template characteristics (5 heartbeats) are:

[0127] P lb = [80, 80, 80, 80, 80] ms

[0128] P hb = [0.2, 0.2, 0.2, 0.2, 0.2] mV

[0129] P db = [0.2, 0.2, 0.2, 0.2, 0.2]

[0130] P pb = [1, 1, 1, 1, 1]

[0131] P rb = [0.8, 0.8, 0.8, 0.8, 0.8].

[0132] The P-wave characteristics of the subject to be tested (5 heartbeats) are:

[0133] P ld=[120, 125, 130, 135, 140] ms

[0134] P hd =[0.1, 0.09, 0.11, 0.12, 0.13] mV

[0135] P dd =[0.9, 0.5, 0.8, 0.8, 0.7]

[0136] P pd =[3, 2, 4, 3, 5]

[0137] P rd =[1.2, 1.3, 1.1, 1.4, 1.0].

[0138] The dynamic atrial fibrillation occurrence weight matrix W can be obtained as follows:

[0139] W = [0, 0, 0.2, 0.294, 0.667].

[0140] The P-wave feature matrix is as follows:

[0141]

[0142] Using matrix multiplication, the atrial fibrillation risk index matrix (R i ) can be obtained:

[0143] Ri = [1.8624, 1.5551, 1.0697, 1.9758, 2.277].

[0144] The local atrial fibrillation occurrence risk index Rf can be calculated to be approximately 0.85.

[0145] According to the calculation formula of the final atrial fibrillation occurrence risk index, the final atrial fibrillation occurrence risk index R r is approximately 0.665.

[0146] Negative example:

[0147] Subject: Female, 20 years old, height 150 cm, weight 40 kg, diastolic blood pressure 60 mmHg, systolic blood pressure 90 mmHg in clinical data

[0148] The mean and standard deviation of the population, gender (0, 1), age (50, 15), height (165, 10), weight (70, 15), diastolic blood pressure (80, 10), systolic blood pressure (120, 20).

[0149] The reference information matrix is as follows:

[0150] [0 30 170 60 80 100].

[0151] The risk factor matrix (multiplied by -1 after normalizing with the mean and standard deviation of the user population) is:

[0152] A = [0 -2 -1.5 -2 -2 -1.5].

[0153] The global atrial fibrillation occurrence risk index Rm is 0.8.

[0154] The standard P-wave template characteristics (5 heartbeats) are:

[0155] P lb = [80, 80, 80, 80, 80] ms

[0156] P hb = [0.2, 0.2, 0.2, 0.2, 0.2] mV

[0157] P db = [0.2, 0.2, 0.2, 0.2, 0.2]

[0158] P pb = [1, 1, 1, 1, 1]

[0159] P rb = [0.8, 0.8, 0.8, 0.8, 0.8].

[0160] The P-wave characteristics of the subject to be measured (5 heartbeats) are:

[0161] P ld = [80, 75, 85, 90, 70] ms

[0162] P hd = [0.2, 0.21, 0.19, 0.18, 0.22] mV

[0163] P dd = [0.2, 0.3, 0.2, 0.3, 0.1]

[0164] P pd = [1, 1, 1, 1, 1]

[0165] P rd = [0.8, 0.75, 0.85, 0.9, 0.76].

[0166] The dynamic heartbeat atrial fibrillation occurrence weight matrix W can be obtained as:

[0167] W = [0.5, 0.5, 0.5, 0.5, 0.5].

[0168] The P-wave characteristic matrix is:

[0169]

[0170] Using matrix multiplication, the atrial fibrillation risk index matrix (Ri) can be obtained as follows:

[0171] Ri = [0.9, 0.875, 0.895, 0.935, 0.83].

[0172] The local atrial fibrillation occurrence risk index Rf can be calculated to be approximately 0.71.

[0173] According to the final atrial fibrillation occurrence risk index calculation formula, the final atrial fibrillation occurrence risk index Rr is approximately 0.356.

[0174] An atrial fibrillation occurrence risk assessment method provided by the present invention combines the paper electrocardiogram image and clinical data of the subject to obtain the global atrial fibrillation occurrence risk index of the subject using the global atrial fibrillation occurrence risk index assessment model, and obtains the local atrial fibrillation occurrence risk index of the subject using the electrocardiogram P-wave data, P-wave feature data of the subject, and a preset electrocardiogram P-wave standard template without atrial fibrillation risk, and then combines the risk factor matrix of the subject to obtain the final atrial fibrillation occurrence risk index of the subject. It can assist in efficiently and accurately assessing the risk index of the subject's occurrence of atrial fibrillation, improve the comfort of the subject during detection, and is conducive to the patient's timely discovery of the possibility of their own occurrence of atrial fibrillation and timely medical treatment. At the same time, it provides effective data support for medical staff to formulate appropriate medical treatment plans.

[0175] It should be noted that all steps of the atrial fibrillation occurrence risk assessment method provided by the present invention can be implemented by a computer device.

[0176] The following describes the atrial fibrillation occurrence risk assessment system provided by the present invention. The atrial fibrillation occurrence risk assessment system described below can be mutually corresponding and referenced with the atrial fibrillation occurrence risk assessment method described above.

[0177] See Figure 3 , an atrial fibrillation occurrence risk auxiliary assessment system provided by the present invention may include:

[0178] A data receiving module, configured to: receive the paper electrocardiogram image and clinical data of the subject;

[0179] A global atrial fibrillation occurrence risk index assessment module, configured to: obtain the global atrial fibrillation occurrence risk index of the subject through the global atrial fibrillation occurrence risk index assessment model according to the paper electrocardiogram image of the subject;

[0180] A first data processing module, configured to: obtain the electrocardiogram P-wave data and P-wave feature data of the subject according to the paper electrocardiogram image of the subject;

[0181] The local atrial fibrillation occurrence risk index evaluation module is used to: obtain the local atrial fibrillation occurrence risk index of the person to be tested according to the electrocardiogram P-wave data, P-wave characteristic data of the person to be tested, and a preset electrocardiogram P-wave standard template without atrial fibrillation risk;

[0182] The second data processing module is used to: obtain the risk factor matrix of the person to be tested according to the clinical data of the person to be tested;

[0183] The final atrial fibrillation occurrence risk index evaluation module is used to: obtain the final atrial fibrillation occurrence risk index of the person to be tested according to the risk factor matrix, global atrial fibrillation occurrence risk index, and local atrial fibrillation occurrence risk index of the person to be tested;

[0184] The data output module is used to: send the final atrial fibrillation occurrence risk index of the person to be tested to at least one terminal.

[0185] According to an atrial fibrillation occurrence risk auxiliary evaluation system provided by the present invention, the data receiving module may include:

[0186] The binarization sub-module is used to: perform background removal processing and binarization processing on the paper electrocardiogram image of the person to be tested to obtain the binarized electrocardiogram of the person to be tested;

[0187] The lead superposition sub-module is used to: perform lead superposition, filtering, and resampling on the binarized electrocardiogram of the person to be tested to obtain the enhanced electrocardiogram waveform of the binarized electrocardiogram of the person to be tested.

[0188] According to an atrial fibrillation occurrence risk auxiliary evaluation system provided by the present invention, the first data processing module may include:

[0189] The electrocardiogram P-wave data and P-wave characteristic data obtaining sub-module is used to: obtain the P-wave of each heartbeat in the electrocardiogram signal as the electrocardiogram P-wave data of the person to be tested according to the enhanced electrocardiogram waveform of the binarized electrocardiogram of the person to be tested, and obtain the P-wave characteristics in the electrocardiogram signal as the P-wave characteristic data, where the P-wave characteristics include any one or any combination of the following: P-wave width, P-wave height, P-wave amplitude change rate, P-wave peak number, R / P amplitude ratio.

[0190] According to an atrial fibrillation occurrence risk auxiliary evaluation system provided by the present invention, the local atrial fibrillation occurrence risk index evaluation module may include:

[0191] The dynamic heartbeat atrial fibrillation occurrence weight matrix obtaining sub-module is used to: obtain the dynamic heartbeat atrial fibrillation occurrence weight matrix of the person to be tested according to the electrocardiogram P-wave data of the person to be tested and a preset electrocardiogram P-wave standard template without atrial fibrillation risk;

[0192] A local atrial fibrillation occurrence risk index assessment sub-module, configured to: obtain the local atrial fibrillation occurrence risk index of the person to be tested according to the dynamic heartbeat atrial fibrillation occurrence weight matrix and P-wave characteristic data of the person to be tested.

[0193] According to an auxiliary assessment system for atrial fibrillation occurrence risk provided by the present invention, the sub-module for obtaining the dynamic heartbeat atrial fibrillation occurrence weight matrix may include:

[0194] A data processing sub-module, configured to: obtain the amplitude sequence P of the P-wave standard template, the width sequence P of the P-wave standard template, the first derivative sequence P of the width of the P-wave standard template, the number of peaks P of the P-wave standard template, and the R / P amplitude ratio P of the P-wave standard template according to the electrocardiogram P-wave data of the person to be tested and the preset electrocardiogram P-wave standard template without atrial fibrillation risk, as well as the amplitude sequence P of the P-wave of the person to be tested, the width sequence P of the P-wave, the first derivative sequence P of the width of the P-wave, the number of peaks P of the P-wave, and the R / P amplitude ratio P of the P-wave; hb the width sequence P of the P-wave standard template lb the first derivative sequence P of the width of the P-wave standard template db the number of peaks P of the P-wave standard template pb the R / P amplitude ratio P of the P-wave standard template rb , and the amplitude sequence P of the P-wave of the person to be tested hd the width sequence P of the P-wave ld the first derivative sequence P of the width of the P-wave dd the number of peaks P of the P-wave pd the R / P amplitude ratio P of the P-wave rd ;

[0195] A calculation sub-module, configured to: obtain and use the correlation between the amplitude sequence P of the P-wave standard template and the amplitude sequence P of the P-wave of the person to be tested as the first weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, obtain and use the correlation between the width sequence P of the P-wave standard template and the width sequence P of the P-wave of the person to be tested as the second weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, obtain and use the correlation between the first derivative sequence P of the width of the P-wave standard template and the first derivative sequence P of the width of the P-wave of the person to be tested as the third weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, obtain and use the ratio of the number of peaks P of the P-wave standard template and the number of peaks P of the P-wave of the person to be tested as the fourth weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, and obtain and use the ratio of the R / P amplitude ratio of the P-wave standard template and the R / P amplitude ratio of the P-wave of the person to be tested as the fifth weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix; hb and the amplitude sequence P of the P-wave of the person to be tested hd as the first weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, obtain and use the correlation between the width sequence P of the P-wave standard template lb and the width sequence P of the P-wave of the person to be tested ld as the second weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, obtain and use the correlation between the first derivative sequence P of the width of the P-wave standard template db and the first derivative sequence P of the width of the P-wave of the person to be tested dd as the third weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, obtain and use the ratio of the number of peaks P of the P-wave standard template pb and the number of peaks P of the P-wave of the person to be tested pd as the fourth weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix, and obtain and use the ratio of the R / P amplitude ratio of the P-wave standard template and the R / P amplitude ratio of the P-wave of the person to be tested rb and the R / P amplitude ratio P of the P-wave of the person to be tested rd as the fifth weight factor of the dynamic heartbeat atrial fibrillation occurrence weight matrix;

[0196] An integration sub-module, configured to: integrate the first weight factor, the second weight factor, the third weight factor, the fourth weight factor, and the fifth weight factor to obtain the dynamic heartbeat atrial fibrillation occurrence weight matrix of the person to be tested.

[0197] An auxiliary assessment system for atrial fibrillation occurrence risk provided by the present invention, the local atrial fibrillation occurrence risk index assessment sub-module may include:

[0198] A cardiac beat atrial fibrillation risk index matrix obtaining sub-module, configured to: multiply the dynamic cardiac beat atrial fibrillation occurrence weight matrix and the cardiac beat P-wave feature matrix of the person to be tested to obtain the cardiac beat atrial fibrillation risk index matrix of the person to be tested;

[0199] A local atrial fibrillation occurrence risk index calculation sub-module, configured to: traverse the cardiac beat atrial fibrillation risk index matrix of the person to be tested, and obtain the local atrial fibrillation occurrence risk index of the person to be tested through a first expression, where the first expression is:

[0200]

[0201] In the first expression, R f represents the local atrial fibrillation occurrence risk index of the person to be tested, R i represents, and N represents.

[0202] An auxiliary assessment system for atrial fibrillation occurrence risk provided by the present invention, the final atrial fibrillation occurrence risk index assessment module may include:

[0203] A final atrial fibrillation occurrence risk index calculation sub-module, configured to: obtain the final atrial fibrillation occurrence risk index of the person to be tested through a second expression according to the risk factor matrix, the global atrial fibrillation occurrence risk index, and the local atrial fibrillation occurrence risk index of the person to be tested, where the second expression is:

[0204]

[0205] In the second expression, R r represents the final atrial fibrillation occurrence risk index of the person to be tested, R m represents the global atrial fibrillation occurrence risk index of the person to be tested, R f represents the local atrial fibrillation occurrence risk index of the person to be tested, A j represents the j-th risk factor in the risk factor matrix A, and T represents the number of risk factors in the risk factor matrix A.

[0206] Figure 4 Illustrates a schematic physical structure diagram of an electronic device, as Figure 4 shown. The electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840. Among them, the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 can call the logical instructions in the memory 830 to execute the following steps:

[0207] Receive the paper electrocardiogram image and clinical data of the subject to be tested;

[0208] According to the paper electrocardiogram image of the subject to be tested, obtain the global atrial fibrillation occurrence risk index of the subject to be tested through the global atrial fibrillation occurrence risk index assessment model;

[0209] According to the paper electrocardiogram image of the subject to be tested, obtain the electrocardiogram P-wave data and P-wave characteristic data of the subject to be tested;

[0210] According to the electrocardiogram P-wave data, P-wave characteristic data of the subject to be tested and the preset electrocardiogram P-wave standard template without atrial fibrillation risk, obtain the local atrial fibrillation occurrence risk index of the subject to be tested;

[0211] According to the clinical data of the subject to be tested, obtain the risk factor matrix of the subject to be tested;

[0212] According to the risk factor matrix, global atrial fibrillation occurrence risk index and local atrial fibrillation occurrence risk index of the subject to be tested, obtain the final atrial fibrillation occurrence risk index of the subject to be tested;

[0213] Send the final atrial fibrillation occurrence risk index of the subject to be tested to at least one terminal.

[0214] In addition, when the logical instructions in the above-mentioned memory 830 are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0215] On the other hand, the present invention also provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the following steps:

[0216] Receive the paper electrocardiogram image and clinical data of the subject to be tested;

[0217] Based on the paper electrocardiogram image of the person to be tested, obtain the global atrial fibrillation occurrence risk index of the person to be tested through the global atrial fibrillation occurrence risk index evaluation model;

[0218] Based on the paper electrocardiogram image of the person to be tested, obtain the electrocardiogram P-wave data and P-wave characteristic data of the person to be tested;

[0219] Based on the electrocardiogram P-wave data, P-wave characteristic data of the person to be tested and the preset electrocardiogram P-wave standard template without atrial fibrillation risk, obtain the local atrial fibrillation occurrence risk index of the person to be tested;

[0220] Based on the clinical data of the person to be tested, obtain the risk factor matrix of the person to be tested;

[0221] Based on the risk factor matrix, global atrial fibrillation occurrence risk index and local atrial fibrillation occurrence risk index of the person to be tested, obtain the final atrial fibrillation occurrence risk index of the person to be tested;

[0222] Send the final atrial fibrillation occurrence risk index of the person to be tested to at least one terminal.

[0223] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0224] Receive the paper electrocardiogram image and clinical data of the person to be tested;

[0225] Based on the paper electrocardiogram image of the person to be tested, obtain the global atrial fibrillation occurrence risk index of the person to be tested through the global atrial fibrillation occurrence risk index evaluation model;

[0226] Based on the paper electrocardiogram image of the person to be tested, obtain the electrocardiogram P-wave data and P-wave characteristic data of the person to be tested;

[0227] Based on the electrocardiogram P-wave data, P-wave characteristic data of the person to be tested and the preset electrocardiogram P-wave standard template without atrial fibrillation risk, obtain the local atrial fibrillation occurrence risk index of the person to be tested;

[0228] Based on the clinical data of the person to be tested, obtain the risk factor matrix of the person to be tested;

[0229] Based on the risk factor matrix, global atrial fibrillation occurrence risk index and local atrial fibrillation occurrence risk index of the person to be tested, obtain the final atrial fibrillation occurrence risk index of the person to be tested;

[0230] Send the final atrial fibrillation occurrence risk index of the person to be tested to at least one terminal.

[0231] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0232] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0233] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for assessing the risk of atrial fibrillation, characterized in that: include: Obtain paper electrocardiogram images and clinical data of the subject; According to the paper electrocardiogram image of the subject, the global atrial fibrillation risk index of the subject is obtained by using the global atrial fibrillation risk index assessment model; Obtaining electrocardiogram P wave data and P wave characteristic data of the subject according to the paper electrocardiogram image of the subject; According to the P wave data and P wave characteristic data of the subject's electrocardiogram and the preset P wave standard template of the electrocardiogram without atrial fibrillation risk, the risk index of local atrial fibrillation of the subject is obtained; According to the clinical data of the subject, a risk factor matrix of the subject is obtained; According to the risk factor matrix of the subject, the global atrial fibrillation risk index and the local atrial fibrillation risk index, the final atrial fibrillation risk index of the subject is obtained.

2. The method for assessing the risk of atrial fibrillation according to claim 1, characterized in that: The global atrial fibrillation risk index assessment model is trained based on the training data of the target group, wherein the target group includes a patient group with atrial fibrillation and a healthy population, and the training data includes paper electrocardiogram image sample data of the target group and corresponding global atrial fibrillation risk index label data; and / or, The method of obtaining the paper electrocardiogram image and clinical data of the subject to be tested includes: Performing background removal and binarization processing on the paper electrocardiogram image of the subject to be tested to obtain a binarized electrocardiogram of the subject to be tested; Lead superposition, filtering and resampling are performed on the binary electrocardiogram of the subject to be tested to obtain an enhanced electrocardiogram waveform of the binary electrocardiogram of the subject to be tested.

3. The method for assessing the risk of atrial fibrillation according to claim 2, characterized in that: The method of obtaining the electrocardiogram P wave data and P wave characteristic data of the subject according to the paper electrocardiogram image of the subject includes: According to the enhanced ECG waveform of the binary ECG of the subject, the P wave of each heartbeat in the ECG signal is obtained as the ECG P wave data of the subject, and the P wave characteristics in the ECG signal are obtained as the P wave characteristic data, wherein the P wave characteristics include any one of the following items or any combination thereof: P wave width, P wave height, P wave amplitude change rate, number of P wave peaks, R / P amplitude ratio.

4. The method for assessing the risk of atrial fibrillation according to claim 3, characterized in that: The method of obtaining the risk index of local atrial fibrillation of the subject according to the subject's electrocardiogram P wave data, P wave characteristic data and a preset electrocardiogram P wave standard template without atrial fibrillation risk includes: According to the P wave data of the electrocardiogram of the subject and the preset standard template of the P wave of the electrocardiogram without the risk of atrial fibrillation, a dynamic heart beat atrial fibrillation occurrence weight matrix of the subject is obtained; According to the dynamic heartbeat atrial fibrillation occurrence weight matrix and P wave characteristic data of the subject, the local atrial fibrillation occurrence risk index of the subject is obtained.

5. The method for assessing the risk of atrial fibrillation according to claim 4, characterized in that: The method of obtaining a dynamic heartbeat atrial fibrillation occurrence weight matrix of the subject to be tested based on the subject's electrocardiogram P wave data and a preset electrocardiogram P wave standard template without atrial fibrillation risk includes: According to the P wave data of the subject's electrocardiogram and the preset P wave standard template of the electrocardiogram without atrial fibrillation risk, the P wave standard template amplitude sequence P is obtained. hb , P wave standard template width sequence P lb , P wave standard template width first order derivative sequence P db , P wave standard template peak number P pb , P wave standard template R / P amplitude ratio P rb , and the P wave amplitude sequence P of the subject hd , P wave width sequence P ld , P wave width first-order derivative sequence P dd , P wave peak number P pd , P wave R / P amplitude ratio P rd ; The P wave standard template amplitude sequence P hb and the P wave amplitude sequence P of the subject hd The correlation is used as the first weight factor of the dynamic heart beat atrial fibrillation weight matrix and is obtained by using the P wave standard template width sequence P lb and the P wave width sequence P of the subject ld The correlation is used as the second weight factor of the dynamic heart beat atrial fibrillation weight matrix, and the first-order derivative sequence P of the P wave standard template width is obtained. db and the first-order derivative sequence P of the P wave width of the subject dd The correlation is used as the third weight factor of the dynamic heart beat atrial fibrillation occurrence weight matrix and is obtained by using the P wave standard template peak number P pb and the number of P wave peaks of the subject pd The ratio of the P wave standard template R / P amplitude ratio and P rb The P wave R / P amplitude ratio P rd The ratio of is used as the fifth weight factor of the dynamic heart beat atrial fibrillation occurrence weight matrix; The first weight factor, the second weight factor, the third weight factor, the fourth weight factor and the fifth weight factor are integrated to obtain a dynamic heart beat atrial fibrillation occurrence weight matrix of the subject.

6. The method for assessing the risk of atrial fibrillation according to claim 5, characterized in that: The method of obtaining the local atrial fibrillation risk index of the subject according to the subject's dynamic heartbeat atrial fibrillation occurrence weight matrix and P wave characteristic data includes: The dynamic atrial fibrillation occurrence weight matrix of the subject to be tested and the cardiac P wave characteristic matrix are multiplied to obtain the atrial fibrillation risk index matrix of the subject to be tested; Traverse the heart beat atrial fibrillation risk index matrix of the subject to be tested, and obtain the local atrial fibrillation risk index of the subject to be tested through the first expression, wherein the first expression is: In the first expression, R f It indicates the risk index of local atrial fibrillation in the subject, R i represents the ith atrial fibrillation risk index in the atrial fibrillation risk index matrix, and N represents the number of risk factors in the atrial fibrillation risk index matrix.

7. The method for assessing the risk of atrial fibrillation according to claim 6, characterized in that: The method of obtaining the final atrial fibrillation risk index of the subject according to the risk factor matrix of the subject, the global atrial fibrillation risk index and the local atrial fibrillation risk index comprises: According to the risk factor matrix of the subject, the global atrial fibrillation risk index and the local atrial fibrillation risk index, the final atrial fibrillation risk index of the subject is obtained through the second expression, wherein the second expression is: In the second expression, R r It represents the final risk index of atrial fibrillation of the tested person, R m R represents the global risk index of atrial fibrillation in the subject. f A represents the risk index of local atrial fibrillation in the subject. j represents the j-th risk factor in the risk factor matrix A, and T represents the number of risk factors in the risk factor matrix A.

8. A system for assessing the risk of atrial fibrillation, characterized in that: include: A data receiving module is used to: receive paper electrocardiogram images and clinical data of the subject to be tested; A global atrial fibrillation risk index assessment module is used to: obtain the global atrial fibrillation risk index of the subject to be tested through a global atrial fibrillation risk index assessment model based on the paper electrocardiogram image of the subject to be tested; The first data processing module is used to obtain the electrocardiogram P wave data and P wave characteristic data of the subject according to the paper electrocardiogram image of the subject; The local atrial fibrillation occurrence risk index assessment module is used to obtain the local atrial fibrillation occurrence risk index of the subject to be tested based on the subject's electrocardiogram P wave data, P wave characteristic data and a preset electrocardiogram P wave standard template without atrial fibrillation risk; The second data processing module is used to obtain a risk factor matrix of the subject according to the clinical data of the subject; The final atrial fibrillation risk index assessment module is used to obtain the final atrial fibrillation risk index of the subject according to the risk factor matrix of the subject, the global atrial fibrillation risk index and the local atrial fibrillation risk index; The data output module is used to send the final atrial fibrillation risk index of the subject to be tested to at least one terminal.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for assessing the risk of atrial fibrillation as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for assessing the risk of atrial fibrillation according to any one of claims 1 to 7 is implemented.

Images