Full-automatic auxiliary analysis system for multi-lead electrocardiogram abnormity

Abstract

The invention relates to the technical field of data processing, in particular to a multi-lead electrocardiogram abnormity full-automatic auxiliary analysis system, which comprises a data acquisition module, a data processing module and a data processing module, the signal curve fluctuation analysis module is used for obtaining the fluctuation difference degree between signal curves corresponding to each lead and other leads according to the difference between data local fluctuations in the voltage sequences of each lead and other leads; the signal curve anomaly analysis module is used for obtaining normal factors of corresponding signal curve segments in a plurality of subsequent periods according to the time range of each signal curve segment in each lead and the correlation between each signal curve segment and all previous signal curve segments; and the early warning module is used for carrying out early warning on the subsequent multi-lead electrocardiogram through the fluctuation difference degree and the normal factor. According to the method, the interference of muscle vibration is reduced, and the accuracy of automatic early warning of the multi-lead electrocardiogram is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a fully automatic auxiliary analysis system for multi-lead electrocardiogram abnormalities. Background Art

[0002] A lead electrocardiogram is a clinical examination method for recording the electrical activity of the heart. It can provide more detailed and comprehensive electrocardiogram information to help patients evaluate their heart health status. It is mainly used for the analysis of heart abnormalities, determining the patient's response to drug treatment, and revealing the trends and changes in heart function. Therefore, it is of great significance to analyze the multi-lead electrocardiogram to judge heart abnormalities.

[0003] During the process of collecting multi-lead electrocardiograms, due to the interference of muscle tremors, the collected multi-lead electrocardiograms are interfered by noise. Therefore, when automatically warning the heart through multi-lead electrocardiograms, the accuracy of automatic warning of the heart will be reduced. Summary of the Invention

[0004] The present invention provides a fully automatic auxiliary analysis system for multi-lead electrocardiogram abnormalities to solve the existing problems.

[0005] The fully automatic auxiliary analysis system for multi-lead electrocardiogram abnormalities of the present invention adopts the following technical solutions: An embodiment of the present invention provides a fully automatic auxiliary analysis system for multi-lead electrocardiogram abnormalities, and the system includes the following modules: A data acquisition module for acquiring multi-lead electrocardiograms of a patient; A signal curve fluctuation analysis module for obtaining the voltage sequence of each lead through the multi-lead electrocardiogram, and obtaining the degree of fluctuation difference between the corresponding signal curves of each lead and other leads by the difference between the fluctuations of each data in the voltage sequences of each lead and other leads within a local range; A signal curve abnormality analysis module for selecting R-wave peak points from the extreme points in the corresponding signal curves of each lead, and dividing the corresponding signal curves of each lead into several signal curve segments by the R-wave peak points; obtaining the normal factor of each signal curve segment in each lead through the time range of the signal curve segment and the correlation between each signal curve segment and all previous signal curve segments; predicting the normal factors of the corresponding signal curve segments in subsequent multiple cycles through the normal factors of all signal curve segments in each lead; An early warning module for warning the subsequent multi-lead electrocardiograms through the degree of fluctuation difference between the corresponding signal curves of each lead and other leads and the normal factors of the corresponding signal curve segments in subsequent multiple cycles.

[0006] Further, the obtaining the voltage sequence of each lead through the multi-lead electrocardiogram includes: Taking seconds as the time interval, continuously sample the signal curves corresponding to each lead in the electrocardiogram, obtain the voltages at all moments, and form a sequence in chronological order, denoted as the voltage sequence of each lead; wherein, is a preset first parameter.

[0007] Furthermore, obtaining the degree of fluctuation difference between the signal curves corresponding to each lead and other leads through the difference between the fluctuations of each data in the voltage sequences of each lead and other leads within a local range includes: Taking the voltage data at each moment in the voltage sequence of each lead as the center, determining the local range at each moment according to the preset range, and the data corresponding to the local range is denoted as the local voltage data at each moment; Denoting the mean value of the differences between the voltage data at each moment in the voltage sequence of each lead and all local voltage data within the corresponding local range as the local fluctuation factor of the voltage data at each moment in the voltage sequence of each lead; Denoting a sequence formed by the local fluctuation factors of the voltage data at all moments of each lead as the local fluctuation sequence of each lead; Denoting the mean value of the differences between all the data at the same positions in the local fluctuation sequences of each lead and any other lead as the first difference factor between each lead and any other lead, and denoting the mean value of the first difference factors between each lead and all other leads as the degree of fluctuation difference between the signal curves corresponding to each lead and other leads.

[0008] Furthermore, selecting the R-wave peak points from the extreme points in the signal curves corresponding to each lead includes: Obtaining all the maximum points in the signal curves corresponding to each lead in the electrocardiogram. Starting from the first maximum point, select the maximum point with the largest value corresponding to the vertical axis among three adjacent maximum points and denote it as the R-wave peak point. Then starting from the fourth maximum point, select the maximum point with the largest value corresponding to the vertical axis among three adjacent maximum points and denote it as the R-wave peak point, and so on to obtain all the R-wave peak points.

[0009] Furthermore, obtaining the normal factor of each signal curve segment in each lead through the time range of the signal curve segment and the correlation between each signal curve segment and all the previous signal curve segments includes: Obtaining the degree of abnormality of each signal curve segment according to the difference between the time interval between the two ends in each signal curve segment in each lead and the normal time interval; According to the correlation between each signal curve segment and all previous signal curve segments, the degree of correlation of the trend distribution between each signal curve segment and all previous signal curve segments in each lead is obtained; Based on the degree of abnormality and the degree of correlation of the trend distribution, the normal factor of each signal curve segment in each lead is obtained; Among them, there is a negative correlation between the degree of abnormality and the normal factor, and a positive correlation between the degree of correlation of the trend distribution and the normal factor.

[0010] Further, the obtaining of the degree of abnormality of each signal curve segment according to the difference between the time interval between both ends of each signal curve segment in each lead and the normal time interval includes: By Calculating the heartbeat corresponding to each signal curve segment, recording the time interval corresponding to the heartbeat within the normal heartbeat range as the normal time interval, and recording the time interval corresponding to the heartbeat not within the normal heartbeat range as the abnormal time interval; Obtaining the normal time interval range through the normal heartbeat range, and recording the difference between each abnormal time interval and the median value within the normal time interval range as the degree of abnormality of the signal curve segment corresponding to each abnormal time interval; among them, recording the degree of abnormality of the signal curve segment corresponding to each normal time interval as 0; Among them, represents the time interval corresponding to each signal curve segment.

[0011] Further, the obtaining of the degree of correlation of the trend distribution between each signal curve segment and all previous signal curve segments in each lead according to the correlation between each signal curve segment and all previous signal curve segments includes: Recording the result after normalizing the correlation coefficient between each signal curve segment and any previous signal curve segment in each lead as the first correlation coefficient between each signal curve segment and any previous signal curve segment; Recording the result of negative correlation mapping and normalization of the number of signal curve segments difference between each signal curve segment and any previous signal curve segment in each lead as the weight between each signal curve segment and any previous signal curve segment; Through the weight, performing weighted averaging on the first correlation coefficient between each signal curve segment and all previous signal curve segments to obtain the degree of correlation of the trend distribution between each signal curve segment and all previous signal curve segments in each lead.

[0012] Further, the predicting of the normal factor of the corresponding signal curve segments in subsequent multiple cycles through the normal factors of all signal curve segments in each lead includes: Sort the normal factors of all signal curve segments in each lead in chronological order to form a sequence, denoted as the normal factor sequence of each lead, and use the ARIMA model to predict the normal factors of the corresponding signal curve segments in subsequent multiple cycles.

[0013] Further, the subsequent multi-lead electrocardiogram is pre-warned by the degree of fluctuation difference between the corresponding signal curves of each lead and other leads and the normal factors of the corresponding signal curve segments in subsequent multiple cycles, including: According to the degree of fluctuation difference between the corresponding signal curves of each lead and other leads and the normal factors of the corresponding signal curve segments of each lead in each subsequent cycle, obtain the first abnormal degree of the corresponding signal curve segments of each lead in each subsequent cycle; Denote the mean value of the first abnormal degrees of the corresponding signal curve segments of all leads in each subsequent cycle as the abnormal factor of the corresponding signal curve segments in each subsequent cycle; The abnormal factor of the corresponding signal curve segment in each subsequent cycle is greater than the preset threshold Then give a warning; When the abnormal factor of the corresponding signal curve segment in each subsequent cycle is less than or equal to the preset threshold Then it is a normal situation, that is, no warning is required.

[0014] Further, the obtaining of the first abnormal degree of the corresponding signal curve segment of each lead in each subsequent cycle according to the degree of fluctuation difference between the corresponding signal curves of each lead and other leads and the normal factors of the corresponding signal curve segments of each lead in each subsequent cycle includes: Perform a negative correlation normalization mapping on the degree of fluctuation difference between the corresponding signal curves of each lead and other leads, and denote the result as the first coefficient of each lead; Normalize the reciprocal of the normal factor of the corresponding signal curve segment of each lead in each subsequent cycle, and denote the result as the second abnormal degree of the corresponding signal curve segment of each lead in each subsequent cycle; Adjust the second abnormal degree by the first coefficient to obtain the first abnormal degree of the corresponding signal curve segment of each lead in each subsequent cycle.

[0015] The beneficial effects of the technical solution of the present invention are as follows: By the difference between the fluctuations of each data in the voltage sequences of each lead and other leads within a local range, the degree of fluctuation difference between the corresponding signal curves of each lead and other leads is obtained, improving the accuracy of the analysis of muscle interference with the signal curves of individual leads in multi-lead electrocardiograms; By the time range of each signal curve segment in each lead and the correlation between each signal curve segment and all previous signal curve segments, the normal factor of each signal curve segment in each lead is obtained, improving the accuracy of the analysis of the periodic changes of the signal curves in multi-lead electrocardiograms; Predict the normal factors of the corresponding signal curve segments in subsequent multiple cycles through the normal factors of all signal curve segments in each lead; Automatically warn the subsequent multi-lead electrocardiogram through the degree of fluctuation difference between the corresponding signal curves of each lead and other leads and the normal factors of the corresponding signal curve segments in subsequent multiple cycles, that is, the influence of muscle tremors on the interference of normal factors is reduced by the degree of fluctuation difference, improving the accuracy of the automatic warning of multi-lead electrocardiograms. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a module flowchart of a fully automatic auxiliary analysis system for multi-lead electrocardiogram abnormalities of the present invention; Figure 2 It is a schematic diagram of the composition of an electrocardiogram. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manner, structure, characteristics and effects of a fully automatic auxiliary analysis system for multi-lead electrocardiogram abnormalities proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present invention.

[0020] The following specifically describes the specific solution of a fully automatic auxiliary analysis system for multi-lead electrocardiogram abnormalities provided by the present invention in combination with the drawings.

[0021] Please refer to Figure 1 , which shows the module flowchart of a multi-lead electrocardiogram abnormality full-automatic auxiliary analysis system provided by an embodiment of the present invention. The system includes the following modules: Module 101: Data acquisition module, which is used to acquire the multi-lead electrocardiogram of a patient.

[0022] It should be noted that in order to analyze the real-time condition of the heart and complete the early warning of the heart, the multi-lead electrocardiogram is collected for analysis.

[0023] Specifically, the multi-lead electrocardiogram of the patient within one week before the current moment is collected. Thus, the multi-lead electrocardiogram of the patient is obtained. Among them, in this embodiment, the multi-lead electrocardiogram is analyzed with twelve leads as an example. Among them, the acquisition duration of the multi-lead electrocardiogram is not specifically limited in this embodiment, and the implementer can determine it according to the specific situation.

[0024] Thus, the multi-lead electrocardiogram of the patient is obtained.

[0025] Module 102: Signal curve fluctuation analysis module, which is used to obtain the voltage sequence of each lead through the multi-lead electrocardiogram, and obtain the fluctuation difference degree between the corresponding signal curves of each lead and other leads through the difference between the fluctuations of each data in the voltage sequences of each lead and other leads within a local range.

[0026] It should be noted that when analyzing the early warning of the heart through the electrocardiogram, the abnormalities of the heart include: myocardial ischemia, myocardial infarction, myocardial injury, atrial and ventricular fibrillation, tachycardia and bradycardia, and atrioventricular and ventricular premature beats, etc. Therefore, the above situations are roughly classified for analysis. Tachycardia and bradycardia are the acceleration and deceleration of the heartbeat. Myocardial ischemia, myocardial infarction, and myocardial injury correspond to the positive and negative of different waves in the electrocardiogram. Atrioventricular and ventricular premature beats may damage the integrity of the periodic QRS wave, etc. Therefore, the analysis is carried out through roughly several situations. And there are roughly several types of waves in the electrocardiogram, namely P wave, QRS wave and T wave. Through a P wave, QRS wave and T wave, a cycle of the heartbeat can be determined, that is, a complete process of the beating of myocardial cells in the heart. Under normal circumstances, there is first a P wave, followed by a QRS wave, and finally a T wave in sequence. The composition of the electrocardiogram within one cycle is as Figure 2 shown.

[0027] It should be further noted that since the multi-lead electrocardiogram is obtained through the voltage changes of myocardial cells in different directions in the heart, when the heart is abnormal, changes will occur in all signal curves in the multi-lead electrocardiogram. Only the directions of the curve changes are different, that is, the positions of the voltages of myocardial cells at the same moment in all signal curves of all multi-lead electrocardiograms change, so that when abnormal, the fluctuations of some curves are upward and some are downward. Therefore, under normal circumstances, all signal curves in the multi-lead electrocardiogram either change or do not change at the same moment. Therefore, the degree of heart abnormality can be further analyzed and obtained through the changes of different signal curves at the same moment. In the multi-lead electrocardiogram, the multi-leads are respectively composed of limb leads and chest leads. Therefore, when the muscles of the body have local tremors, it usually shows that only individual signal curves change, rather than all signal curves changing. Therefore, the degree of fluctuation difference between the corresponding signal curves of each lead and other leads is obtained through the difference between the fluctuations of each data in the voltage sequences of each lead and other leads within a local range.

[0028] Preferably, a first parameter is preset , where in this embodiment, is taken as an example for description, and this embodiment does not make specific limitations, where can be determined according to the specific implementation situation. Taking seconds as the time interval, continuous sampling is performed on the corresponding signal curves of each lead in the electrocardiogram to obtain the voltages at all moments, and a group of sequences is formed in chronological order, denoted as the voltage sequence of each lead.

[0029] Furthermore, as an embodiment, the specific calculation method for the degree of fluctuation difference between the corresponding signal curves of each lead and other leads is as follows: Taking the voltage data at each moment in the voltage sequence of each lead as the center, a local range is determined according to the preset range , and the data corresponding to the local range is denoted as the local voltage data at each moment; The mean value of the differences between the voltage data at each moment in the voltage sequence of each lead and all local voltage data within the corresponding local range is denoted as the local fluctuation factor of the voltage data at each moment in the voltage sequence of each lead; A group of sequences composed of the local fluctuation factors of the voltage data at all moments of each lead is denoted as the local fluctuation sequence of each lead; The mean of the differences between the data at all the same positions in the local fluctuation sequences of each lead and any other lead is denoted as the first difference factor between each lead and any other lead. The mean of the first difference factors between each lead and all other leads is denoted as the degree of fluctuation difference between the corresponding signal curves of each lead and other leads.

[0030] In an embodiment of the present invention, it is specifically expressed by the formula: In the formula, represents the voltage data at the th moment in the voltage sequence of each lead, represents the th local voltage data within the local range at the th moment in the voltage sequence of each lead, is the absolute value symbol, represents the number of all local voltage data within the local range at each moment, represents the local fluctuation factor of the voltage data at the th moment in the voltage sequence of each lead, represents the difference between the th data in the local fluctuation sequence of each lead and the th data in the local fluctuation sequence of the th lead, represents the number of all data in the local fluctuation sequence, represents the number of all leads, represents the degree of fluctuation difference between the corresponding signal curves of each lead and the th lead. Among them, the local fluctuation sequence of each lead is a sequence formed by arranging the local fluctuation factors of the voltage data of each lead at all moments in chronological order.

[0031] Among them, the greater the difference between the data in the local fluctuation sequences of each lead and all other leads, the more different the data fluctuations of the corresponding signal curves of this lead and all other leads at the same moment, that is, the greater the possibility that this lead is affected by muscle tremors and causes abnormal fluctuations in the signal curve; conversely, the more similar the data fluctuations of the corresponding signal curves of this lead and all other leads at the same moment, that is, the smaller the possibility that this lead is affected by muscle tremors and causes abnormal fluctuations in the signal curve.

[0032] Among them, is a preset second parameter. In this embodiment, it is described by taking as an example, and this embodiment does not make specific limitations. Among them, can be determined according to the specific implementation situation.

[0033] Thus, the degree of fluctuation difference between the signal curves corresponding to each lead and those of other leads is obtained.

[0034] Module 103: Signal curve anomaly analysis module, which is used to select the R-wave peak points from the extreme points in the signal curves corresponding to each lead, and divide the signal curves corresponding to each lead into several signal curve segments through the R-wave peak points; obtain the normal factors of each signal curve segment in each lead through the time range of the signal curve segments and the correlation between each signal curve segment and all previous signal curve segments; predict the normal factors of the signal curve segments corresponding to subsequent multiple cycles through the normal factors of all signal curve segments in each lead.

[0035] It should be noted that since the fluctuation changes of each signal curve in the electrocardiogram are periodic changes, that is, the P wave, QRS wave, and T wave change periodically, when there is no abnormality in the heart, the fluctuation changes of each signal curve always show periodic changes. Therefore, the signal curve segments corresponding to all cycles can be obtained through the wave peaks, and whether there is an abnormality in the electrocardiogram can be analyzed through the differences between the signal curve segments. Therefore, the R-wave peak points can be selected from the extreme points in the signal curves corresponding to each lead, and the signal curves corresponding to each lead are divided into several signal curve segments through the R-wave peak points.

[0036] Preferably, all the maximum points in the signal curves corresponding to each lead in the electrocardiogram are obtained. Starting from the first maximum point, the maximum point with the largest value corresponding to the vertical axis among three adjacent maximum points is recorded as the R-wave peak point. Then, starting from the fourth maximum point, the maximum point with the largest value corresponding to the vertical axis among three adjacent maximum points is recorded as the R-wave peak point, and so on to obtain all the R-wave peak points. Among them, when there are less than three maximum points at the end, no R-wave peak point selection is performed. The signal curves corresponding to each lead are divided into several signal curve segments through the R-wave peak points. Thus, several signal curve segments on the signal curves corresponding to each lead are obtained.

[0037] Furthermore, it should be noted that since the heart rate changes little per minute when the heart is normal, that is, in the electrocardiogram, the intervals between all adjacent R-wave peak points are the same. When the heart is abnormal, the heart rate will change significantly. Therefore, the abnormal situation can be analyzed through the changes in the heart rate in adjacent cycles. Also, under normal circumstances, the distributions of all adjacent signal curve segments in the signal curves of each lead are similar. Therefore, the normal factors of each signal curve segment in each lead are obtained through the time range of each signal curve segment and the correlation between each signal curve segment and all previous signal curve segments.

[0038] Preferably, as an embodiment, the specific calculation method of the normal factor for each signal curve segment in each lead is as follows: Obtain the abnormality degree of each signal curve segment according to the difference between the time interval between both ends in each signal curve segment in each lead and the normal time interval; Obtain the correlation degree of the trend distribution between each signal curve segment in each lead and all previous signal curve segments according to the correlation between each signal curve segment and all previous signal curve segments; Obtain the normal factor of each signal curve segment in each lead through the abnormality degree and the correlation degree of the trend distribution; Wherein, the abnormality degree and the normal factor have a negative correlation, and the correlation degree of the trend distribution and the normal factor have a positive correlation.

[0039] In an embodiment of the present invention, it is specifically expressed by the formula: In the formula, represents the correlation degree of the trend distribution between the th signal curve segment in each lead and all previous signal curve segments, represents the exponential function with the natural constant as the base, represents the th signal curve segment's abnormality degree, represents the normal factor of the th signal curve segment in each lead.

[0040] Wherein, when the correlation degree of the trend distribution is larger and the abnormality degree is smaller, it indicates that the normal factor of this signal curve segment is larger; otherwise, it indicates that the normal factor of this signal curve segment is smaller.

[0041] Among them, the process of obtaining the abnormality degree of each signal curve segment in each lead is as follows: Preferably, obtain the time interval between both ends in each signal curve segment corresponding to each lead on the signal curve; through calculate whether the heartbeat corresponding to each signal curve segment is within the normal heartbeat range. If the heartbeat is within the normal range, record the time interval corresponding to the signal curve segment as the normal time interval. If the heartbeat is not within the normal range, record the time interval corresponding to the signal curve segment as the abnormal time interval. Among them, represents the time interval corresponding to each signal curve segment. Among them, is the formula for calculating the heartbeat, which is a conventionally well-known formula.

[0042] The normal time interval range is obtained through the normal heart rate range, and the difference between each abnormal time interval and the median value within the normal time interval range is recorded as the degree of abnormality of the signal curve segment corresponding to each abnormal time interval. Among them, the degree of abnormality of the signal curve segment corresponding to each normal time interval is recorded as 0; thus, the degree of abnormality of each signal curve segment in each lead is obtained. Among them, the obtained normal time interval range is the normal time interval range corresponding to each signal curve segment.

[0043] Among them, the process of obtaining the correlation degree of the trend distribution between each signal curve segment in each lead and all the previous signal curve segments is as follows: Preferably, as an embodiment, the specific calculation method of the correlation degree of the trend distribution between each signal curve segment in each lead and all the previous signal curve segments is as follows: The result of normalizing the correlation coefficient between each signal curve segment in each lead and any one of the previous signal curve segments is recorded as the first correlation coefficient between each signal curve segment and any one of the previous signal curve segments; The result of negatively mapping and normalizing the number of signal curve segments between each signal curve segment in each lead and any one of the previous signal curve segments is recorded as the weight between each signal curve segment and any one of the previous signal curve segments; Through the weight, the first correlation coefficients between each signal curve segment and all the previous signal curve segments are weighted and averaged to obtain the correlation degree of the trend distribution between each signal curve segment in each lead and all the previous signal curve segments.

[0044] In an embodiment of the present invention, it is specifically expressed by the formula: In the formula, represents the Spearman correlation coefficient between the th signal curve segment in each lead and the th signal curve segment before, is the reciprocal of the number of signal curve segments between the th signal curve segment in each lead and the th signal curve segment before plus 1, that is, represents the weight between two signal curve segments, represents the reciprocal of the number of signal curve segments between the th signal curve segment in each lead and the th signal curve segment before plus 1, represents the number of all the signal curve segments before each signal curve segment, represents the correlation degree of the trend distribution between the th signal curve segment in each lead and all the previous signal curve segments, It represents a linear normalization function. Among them, the Spearman correlation coefficient is a well-known technology and will not be elaborated specifically here.

[0045] Among them, when the correlation degree between each signal curve segment and all previous signal curve segments is greater, it indicates that the fluctuations and distributions of each lead are more normal and more in line with periodic changes; conversely, it is less in line with periodic changes.

[0046] It should be noted that since both abnormal heartbeats and peaks will show trend changes, the normal factors of all signal curve segments in each lead are used to predict the normal factors of the corresponding signal curve segments in multiple subsequent cycles.

[0047] Preferably, the normal factors of all signal curve segments in each lead are sorted in chronological order to form a sequence, denoted as the normal factor sequence of each lead, and the ARIMA model is used to predict the normal factors of the corresponding signal curve segments in multiple subsequent cycles. Among them, the ARIMA model is well-known and will not be elaborated specifically here.

[0048] Module 104: Early warning module, which is used to give early warnings to subsequent multi-lead electrocardiograms based on the fluctuation difference degree between each lead and the corresponding signal curves of other leads, and the normal factors of the corresponding signal curve segments in multiple subsequent cycles.

[0049] It should be noted that when the fluctuation difference degree between each lead and the corresponding signal curves of other leads is greater, it indicates that the possibility of the signal curve of this lead being abnormal due to muscle tremors is greater, that is, the credibility of the detected abnormality is lower; when the fluctuation difference degree between each lead and the corresponding signal curves of other leads is smaller, it indicates that the possibility of the signal curve of this lead being abnormal due to muscle tremors is smaller, that is, the credibility of the detected abnormality is higher; when the influence of muscle tremors is smaller, the analysis of the abnormality or normality of the lead is more credible. Therefore, early warnings are given to subsequent multi-lead electrocardiograms based on the fluctuation difference degree between each lead and the corresponding signal curves of other leads, and the normal factors of the corresponding signal curve segments in multiple subsequent cycles.

[0050] Preferably, as an embodiment, the specific calculation method of the abnormal factor of the corresponding signal curve segment in each subsequent cycle is as follows: Perform a negative correlation normalization mapping on the fluctuation difference degree between each lead and the corresponding signal curves of other leads, and record the result as the first coefficient of each lead; perform normalization on the reciprocal of the normal factor of the corresponding signal curve segment in each subsequent cycle of each lead, and record the result as the second abnormal degree of the corresponding signal curve segment in each subsequent cycle of each lead; Adjust the second abnormal degree through the first coefficient to obtain the first abnormal degree of the corresponding signal curve segment in each subsequent cycle of each lead; The mean value of the first abnormal degree of the corresponding signal curve segments in each subsequent cycle of all leads is denoted as the abnormal factor of the corresponding signal curve segments in each subsequent cycle.

[0051] In one embodiment of the present invention, it is specifically expressed by the formula: In the formula, represents the degree of fluctuation difference between the corresponding signal curves of the th lead and those of other leads, represents the normal factor of the corresponding signal curve segment of the th lead in the th subsequent cycle, represents the number of all leads, represents the abnormal factor of the corresponding signal curve segment in the th subsequent cycle, represents the exponential function with the natural constant as the base, represents the linear normalization function.

[0052] Among them, the greater the degree of fluctuation difference, the lower the reliability of the abnormal and normal situations in the signal curve; conversely, the higher the reliability. When the normal factor of the corresponding signal curve segment of each lead in each subsequent cycle, then the abnormal factor of the corresponding signal curve segment of this cycle.

[0053] Preset a threshold , where in this embodiment, it is described by taking as an example. This embodiment does not make specific limitations, and can be determined according to the specific implementation situation.

[0054] When the abnormal factor of the corresponding signal curve segment in each subsequent cycle is greater than the preset threshold , warning needs to be given; when the abnormal factor of the corresponding signal curve segment in each subsequent cycle is less than or equal to the preset threshold , warning does not need to be given.

[0055] It should be noted that the model used in this embodiment is only used to represent the negative correlation relationship and restrict the result of the model output to be within the interval. In specific implementation, it can be replaced with other models with the same purpose. This embodiment only takes the model as an example for description and does not make specific limitations on it. Among them, refers to the input of this model.

[0056] So far, this embodiment is completed.

[0057] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A fully automatic auxiliary analysis system for multi-lead electrocardiogram abnormalities, characterized in that, The system includes the following modules: A data acquisition module for acquiring multi-lead electrocardiograms of patients; A signal curve fluctuation analysis module for obtaining the voltage sequence of each lead from the multi-lead electrocardiogram, and obtaining the degree of fluctuation difference between the corresponding signal curves of each lead and other leads through the difference between the fluctuations of each data in the local range of the voltage sequences of each lead and other leads; A signal curve abnormality analysis module for selecting R-wave peak points from the extreme points in the corresponding signal curves of each lead, and dividing the corresponding signal curves of each lead into several signal curve segments through the R-wave peak points; obtaining the normal factor of each signal curve segment in each lead through the time range of the signal curve segment and the correlation between each signal curve segment and all previous signal curve segments; predicting the normal factors of the corresponding signal curve segments in multiple subsequent cycles through the normal factors of all signal curve segments in each lead; An early warning module for warning the subsequent multi-lead electrocardiogram through the degree of fluctuation difference between the corresponding signal curves of each lead and other leads and the normal factors of the corresponding signal curve segments in multiple subsequent cycles.

2. The multi-lead electrocardiogram abnormality full-automatic auxiliary analysis system according to claim 1, wherein The obtaining of the voltage sequence of each lead from the multi-lead electrocardiogram includes: Taking seconds as the time interval, continuously sample the signal curves corresponding to each lead in the electrocardiogram, obtain the voltages at all moments, and form a set of sequences in chronological order, denoted as the voltage sequence of each lead; Among them, is a preset first parameter.

3. The multi-lead electrocardiogram abnormality full-automatic auxiliary analysis system according to claim 1, characterized in that, The obtaining of the degree of fluctuation difference between the corresponding signal curves of each lead and other leads through the difference between the fluctuations of each data in the local range of the voltage sequences of each lead and other leads includes: Centering on the voltage data at each moment in the voltage sequence of each lead, determining the local range at each moment according to the preset range, and the data corresponding to the local range is recorded as the local voltage data at each moment; Recording the mean value of the differences between the voltage data at each moment in the voltage sequence of each lead and all local voltage data within the corresponding local range as the local fluctuation factor of the voltage data at each moment in the voltage sequence of each lead; Recording a set of sequences composed of the local fluctuation factors of the voltage data at all moments of each lead as the local fluctuation sequence of each lead; Recording the mean value of the differences between the data at all the same positions in the local fluctuation sequences of each lead and any other lead as the first difference factor between each lead and any other lead, and recording the mean value of the first difference factors between each lead and all other leads as the degree of fluctuation difference between the corresponding signal curves of each lead and other leads.

4. The multi-lead electrocardiogram abnormality full-automatic auxiliary analysis system according to claim 1, characterized in that The selection of the R-wave peak points from the extreme points in the corresponding signal curves of each lead includes: Obtaining all the maximum points in the corresponding signal curves of each lead in the electrocardiogram, starting from the first maximum point, selecting the maximum point with the largest value corresponding to the vertical axis among three adjacent maximum points as the R-wave peak point, and then starting from the fourth maximum point, selecting the maximum point with the largest value corresponding to the vertical axis among three adjacent maximum points as the R-wave peak point, and so on to obtain all the R-wave peak points.

5. The multi-lead electrocardiogram abnormality full-automatic auxiliary analysis system according to claim 1, characterized in that The obtaining of the normal factor of each signal curve segment in each lead through the time range of the signal curve segment and the correlation between each signal curve segment and all previous signal curve segments includes: Obtain the abnormality degree of each signal curve segment according to the difference between the time interval between both ends in each signal curve segment of each lead and the normal time interval; Obtain the degree of correlation between the trend distribution of each signal curve segment in each lead and all previous signal curve segments according to the correlation between each signal curve segment and all previous signal curve segments; Obtain the normal factor of each signal curve segment in each lead through the abnormality degree and the degree of correlation between the trend distribution; Among them, there is a negative correlation between the abnormality degree and the normal factor, and a positive correlation between the degree of correlation between the trend distribution and the normal factor.

6. The multi-lead electrocardiogram abnormality full-automatic auxiliary analysis system according to claim 5, wherein The obtaining of the abnormality degree of each signal curve segment according to the difference between the time interval between both ends in each signal curve segment of each lead and the normal time interval includes: By calculating the heartbeat corresponding to each signal curve segment, recording the time interval corresponding to the heartbeat within the normal heartbeat range as the normal time interval, and recording the time interval corresponding to the heartbeat not within the normal heartbeat range as the abnormal time interval; Obtain the normal time interval range through the normal heartbeat range, and record the difference between each abnormal time interval and the median value within the normal time interval range as the abnormality degree of the signal curve segment corresponding to each abnormal time interval; among them, record the abnormality degree of the signal curve segment corresponding to each normal time interval as 0; Among them, represents the time interval corresponding to each signal curve segment.

7. The fully automatic auxiliary analysis system for multi-lead electrocardiogram abnormalities according to claim 5, characterized in that, The obtaining of the degree of correlation between the trend distribution of each signal curve segment in each lead and all previous signal curve segments according to the correlation between each signal curve segment and all previous signal curve segments includes: Record the result after normalizing the correlation coefficient between each signal curve segment in each lead and any previous signal curve segment as the first correlation coefficient between each signal curve segment and any previous signal curve segment; Record the result of negative correlation mapping and normalization of the number of signal curve segments differed between each signal curve segment in each lead and any previous signal curve segment as the weight between each signal curve segment and any previous signal curve segment; Through the weight, perform weighted averaging on the first correlation coefficient between each signal curve segment and all previous signal curve segments to obtain the degree of correlation between the trend distribution of each signal curve segment in each lead and all previous signal curve segments.

8. The multi-lead electrocardiogram abnormality full-automatic auxiliary analysis system according to claim 1, wherein The prediction of the normal factors of the corresponding signal curve segments in subsequent multiple cycles through the normal factors of all signal curve segments in each lead includes: Sort the normal factors of all signal curve segments in each lead in chronological order to form a group of sequences, denoted as the normal factor sequence of each lead, and predict the normal factors of the corresponding signal curve segments in subsequent multiple cycles through the ARIMA model.

9. The multi-lead electrocardiogram abnormality full-automatic auxiliary analysis system according to claim 1, characterized in that The early warning of subsequent multi-lead electrocardiograms through the degree of fluctuation difference between the corresponding signal curves of each lead and other leads and the normal factors of the corresponding signal curve segments in subsequent multiple cycles includes: Obtain the first abnormality degree of the corresponding signal curve segment in each subsequent cycle of each lead according to the degree of fluctuation difference between the corresponding signal curves of each lead and other leads and the normal factors of the corresponding signal curve segments in each subsequent cycle of each lead; record the mean value of the first abnormality degrees of the corresponding signal curve segments in each subsequent cycle of all leads as the abnormality factor of the corresponding signal curve segments in each subsequent cycle; If the abnormal factor of the signal curve segment corresponding to each subsequent period is greater than the preset threshold a warning is issued; when the abnormal factor of the signal curve segment corresponding to each subsequent period is less than or equal to the preset threshold it is a normal situation, that is, no warning needs to be issued.

10. The multi-lead electrocardiogram abnormality full-automatic auxiliary analysis system according to claim 9, wherein Obtaining the first degree of abnormality of the corresponding signal curve segment of each subsequent cycle of each lead according to the degree of fluctuation difference between the corresponding signal curves of each lead and other leads and the normal factor of the corresponding signal curve segment of each subsequent cycle of each lead, including: Performing a negative correlation normalization mapping on the degree of fluctuation difference between the corresponding signal curves of each lead and other leads, and recording the result as the first coefficient of each lead; normalizing the reciprocal of the normal factor of the corresponding signal curve segment of each subsequent cycle of each lead, and recording the result as the second degree of abnormality of the corresponding signal curve segment of each subsequent cycle of each lead; Adjusting the second degree of abnormality by the first coefficient to obtain the first degree of abnormality of the corresponding signal curve segment of each subsequent cycle of each lead.

Images