CN116616790B

CN116616790B - Cardiac risk assessment method, apparatus, computer device and storage medium

Info

Publication number: CN116616790B
Application number: CN202310907009.XA
Authority: CN
Inventors: 左能; 黄庆玺; 李小钦; 龙文瑶; 方红; 刘文玉
Original assignee: Biosorp Biotechnology Co ltd
Current assignee: Biosorp Biotechnology Co ltd
Priority date: 2023-07-24
Filing date: 2023-07-24
Publication date: 2023-11-17
Anticipated expiration: 2043-07-24
Also published as: CN116616790A

Abstract

The application relates to a heart risk assessment method, a heart risk assessment device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring electrocardiographic data corresponding to target electrocardiographic detection matched with clinical indications; the clinical indication is used for indicating whether the load movement electrocardiographic detection can be performed; the target electrocardiographic detection at least comprises resting electrocardiographic detection; analyzing high-frequency components of a QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics; determining a heart risk assessment grade and a heart risk type according to the reference characteristics; the heart risk assessment grade is used as a reference index for shunting the testee; the cardiac risk type serves as a reference index for assessing the risk type that may be present in the subject's heart. By adopting the method, the accuracy of heart health condition identification can be improved in a noninvasive manner.

Description

Cardiac risk assessment method, apparatus, computer device and storage medium

Technical Field

The present application relates to the field of electrocardiographic data processing technology, and in particular, to a cardiac risk assessment method, apparatus, computer device, and storage medium.

Background

At present, cardiac activity related information is usually analyzed based on ST-T segment data representing a cardiac repolarization stage in an Electrocardiogram (ECG), so that risk assessment of the heart is achieved, but many cardiac potential problems are not abnormal in the ST-T segment data, so that there is a problem of low accuracy in cardiac risk assessment, and if cardiac risk needs to be assessed more accurately, so that cardiac health is identified more effectively, the cardiac activity related information needs to be achieved based on invasive modes such as coronary angiography and myocardial biopsy, and the invasive assessment modes have a more or less influence on the physical health of a tested person.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a cardiac risk assessment method, apparatus, computer device, and storage medium that can improve accuracy of cardiac health status identification in a non-invasive manner.

A method of cardiac risk assessment, the method comprising:

acquiring electrocardiographic data corresponding to target electrocardiographic detection matched with clinical indications; the clinical indication is used for indicating whether the load movement electrocardiographic detection can be performed; the target electrocardiographic detection at least comprises resting electrocardiographic detection;

analyzing high-frequency components of a QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics;

Determining a heart risk assessment grade and a heart risk type according to the reference characteristics; the heart risk assessment grade is used as a reference index for shunting the testee; the cardiac risk type serves as a reference index for assessing the risk type that may be present in the subject's heart.

In one embodiment, if the target electrocardiographic detection comprises only resting electrocardiographic detection, the electrocardiographic data comprises an age of the subject and a resting electrocardiographic signal, and the reference feature comprises a first resting reference feature; analyzing the high-frequency component of the QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics, wherein the method comprises the following steps:

analyzing the high-frequency component of the QRS complex in the resting electrocardiosignal to obtain a high-frequency QRS envelope curve;

determining a first resting reference feature from the high frequency QRS envelope curve and the age; the first resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, and a second target number of leads; the first target number of leads refers to the number of resting leads with a corresponding high frequency morphology index greater than or equal to a first index threshold; the second target number of leads refers to the number of resting leads having a corresponding root mean square voltage less than or equal to the first voltage threshold.

In one embodiment, the reference features further comprise a second resting reference feature; analyzing the high-frequency component of the QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics, and further comprising:

determining a second resting reference feature from the high frequency QRS envelope curve and the age; the second resting reference feature comprises the resting positive number of leads, the resting critical number of leads, and the first target number of leads;

the determining the heart risk assessment level and the heart risk type according to the reference features comprises the following steps:

determining a first risk assessment level according to the first rest reference feature;

determining a second risk assessment level according to the second resting reference feature;

and determining a heart risk assessment level and a heart risk type according to the first risk assessment level and the second risk assessment level.

In one embodiment, the first resting reference feature further comprises a target frequency morphology index and a target root mean square voltage; the second stationary reference feature further comprises the target high frequency morphology index; the target high-frequency morphology index is the maximum value of the high-frequency morphology indexes corresponding to the rest leads; the target rms voltage is the minimum of the rms voltages corresponding to the respective rest leads.

In one embodiment, if the target electrocardiographic detection further includes load motion electrocardiographic detection, the electrocardiographic data includes an age, a resting electrocardiographic signal, and a motion electrocardiographic signal of the subject, and the reference features include a first resting reference feature and a first motion reference feature; analyzing the high-frequency component of the QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics, wherein the method comprises the following steps:

determining a first resting reference feature from the high frequency QRS envelope curve and the age; the first resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, and a second target number of leads; the first target number of leads refers to the number of resting leads with a corresponding high frequency morphology index greater than or equal to a first index threshold; the second target number of leads refers to the number of resting leads having a corresponding root mean square voltage less than or equal to the first voltage threshold;

analyzing the high-frequency component of the QRS complex in the motion electrocardiosignal to obtain a high-frequency QRS waveform curve;

Determining a maximum heart rate of the subject from the exercise electrocardiosignal;

determining a first exercise reference feature from the high frequency QRS waveform profile, the age and the maximum heart rate; the first motion reference feature comprises a motion positive number of leads, a motion critical number of leads, a third target number of leads, a fourth target number of leads, and a fifth target number of leads; the third target number of leads refers to the number of moving leads having a corresponding first amplitude decrease relative value greater than or equal to a first relative value threshold; the fourth target lead number refers to the number of motion leads with descending and ascending repeated fluctuation trend of the corresponding high-frequency QRS waveform curve in a first time period; the fifth target number of leads refers to a number of moving leads having a corresponding second amplitude reduction relative value greater than or equal to a second relative value threshold.

In one embodiment, the reference features further comprise a second stationary reference feature and a second motion reference feature; analyzing the high-frequency component of the QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics, and further comprising:

Determining a second exercise reference feature from the high frequency QRS waveform profile, the age and the maximum heart rate; the second motion reference feature includes the number of motion positive leads and the number of motion critical leads;

determining a second risk assessment level from the second resting reference feature and the second movement reference feature;

determining a third risk assessment level according to the first motion reference feature;

and determining a heart risk assessment level and a heart risk type according to the first risk assessment level, the second risk assessment level and the third risk assessment level.

In one embodiment, the first resting reference feature further comprises a target frequency morphology index and a target root mean square voltage; the second stationary reference feature further comprises the target high frequency morphology index; the target high-frequency morphology index is the maximum value of the high-frequency morphology indexes corresponding to the rest leads; the target root mean square voltage is the minimum value of root mean square voltages corresponding to the rest leads; the first motion reference feature further comprises a first amplitude reduction relative value and a second amplitude reduction relative value corresponding to each motion lead; the second motion reference feature further includes a second amplitude reduction relative value for each motion lead.

In one embodiment, the method further comprises:

determining corresponding risk assessment features according to the cardiac risk type according to the electrocardiographic data;

and determining the attention level of the corresponding heart risk type according to the risk assessment features.

A cardiac risk assessment device, the device comprising:

the acquisition module is used for acquiring electrocardiographic data corresponding to target electrocardiographic detection matched with clinical indications; the clinical indication is used for indicating whether the load movement electrocardiographic detection can be performed; the target electrocardiographic detection at least comprises resting electrocardiographic detection;

the characteristic determining module is used for analyzing the high-frequency component of the QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics;

the risk assessment module is used for determining a heart risk assessment grade and a heart risk type according to the reference characteristics; the heart risk assessment grade is used as a reference index for shunting the testee; the cardiac risk type serves as a reference index for assessing the risk type that may be present in the subject's heart.

A computer device comprising a memory storing a computer program and a processor implementing steps in various method embodiments when the computer program is executed.

A computer readable storage medium having stored thereon a computer program which when executed by a processor performs steps in various method embodiments.

According to the cardiac risk assessment method, the cardiac risk assessment device, the computer equipment and the storage medium, by acquiring the electrocardiographic data corresponding to the target electrocardiographic detection matched with the clinical indication, analyzing the high-frequency component of the QRS complex in the corresponding electrocardiographic data according to the target electrocardiographic detection to obtain the corresponding reference characteristic, and evaluating and analyzing the reference characteristic, the cardiac risk assessment grade for representing the risk of the heart of the testee and the cardiac risk type for representing the possible risk type of the heart are obtained efficiently and accurately, so that the risk of the heart of the testee and the risk type can be estimated efficiently and accurately in a noninvasive manner for reference by doctors, the doctors can conveniently and efficiently identify the heart health condition of the testee in combination with the clinical indication, and further diagnosis and/or detection reference suggestions are given, and the diagnosis and diversion of the testee are realized. In addition, the electrocardiographic data for evaluating the heart risk of the testee are acquired in the target electrocardiographic detection process matched with the clinical indication of the testee, so that the electrocardiographic data capable of accurately evaluating the heart risk of the testee can be acquired as comprehensively as possible under the condition of ensuring the safety detection of the testee, the accuracy of the heart risk evaluation is further improved, and the accuracy of the heart health condition identification is further improved.

Drawings

FIG. 1 is a flow chart of a method for cardiac risk assessment according to one embodiment;

fig. 2 is a schematic representation of a high frequency QRS waveform profile in one embodiment;

fig. 3 is a schematic representation of a high frequency QRS envelope curve in one embodiment;

FIG. 4 is a flowchart of a method for cardiac risk assessment according to another embodiment;

FIG. 5 is a block diagram of a heart risk assessment device according to one embodiment;

fig. 6 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The cardiac risk assessment method provided by the application can be applied to a terminal, a server and an interactive system comprising the terminal and the server, and is realized through interaction between the terminal and the server, and is not particularly limited. The terminal may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, electrocardiographic monitoring devices and portable wearable devices, and the server may be implemented by a separate server or a server cluster formed by a plurality of servers.

In one embodiment, as shown in fig. 1, a cardiac risk assessment method is provided, and the method is applied to a server for illustration, and specifically includes the following steps:

s102, acquiring electrocardiographic data corresponding to target electrocardiographic detection matched with clinical indications; clinical indications are used to indicate whether load exercise electrocardiographic detection can be performed; the target electrocardiographic detection comprises at least resting electrocardiographic detection.

The clinical indication is used for indicating the electrocardiographic detection suitable for the corresponding testee, and particularly is used for indicating whether the corresponding testee can carry out load exercise electrocardiographic detection or not, and particularly comprises clinical data such as whether the blood sugar is low, the acute attack period of the hypotension and the myocardial infarction is low, whether vital signs are stable or not and the like. If the vital signs are stable and the acute attack phases of hypoglycemia, hypotension and myocardial infarction are eliminated, the corresponding testees can carry out load movement electrocardiographic detection, the target electrocardiographic detection matched with the clinical indication comprises resting electrocardiographic detection and load movement electrocardiographic detection, otherwise, the corresponding testees cannot carry out load movement electrocardiographic detection, and the target electrocardiographic detection matched with the clinical indication comprises resting electrocardiographic detection. The subject is in a resting state during resting electrocardiographic detection. The subject is in motion during the load motion electrocardiographic detection to increase the subject's cardiac load through motion. The target electrocardiographic detection refers to the type of electrocardiographic detection that the subject is adapted to. It will be appreciated that the specific details of the clinical indications described above are by way of example only and are not intended to be limiting.

Specifically, electrocardiographic data of the subject is obtained, the electrocardiographic data is electrocardiographic data collected in a target electrocardiographic detection process, and the target electrocardiographic detection is matched with clinical indications of the subject, namely, the target electrocardiographic detection is determined by the clinical indications of the subject.

In one embodiment, if the target electrocardiographic detection comprises a resting electrocardiographic detection, the acquired electrocardiographic data comprises the age of the subject and a resting electrocardiographic signal acquired during the resting electrocardiographic detection. If the target electrocardiograph detection comprises resting electrocardiograph detection and load movement electrocardiograph detection, the acquired electrocardiograph data comprises the age of the testee, resting electrocardiograph signals acquired in the resting electrocardiograph detection process and movement electrocardiograph signals acquired in the load movement electrocardiograph detection process.

S104, analyzing the high-frequency components of the QRS complex in the electrocardiographic data according to the target electrocardiograph detection to obtain corresponding reference characteristics.

Specifically, the electrocardiographic data includes a plurality of QRS complexes reflecting changes in left and right ventricular depolarization potentials and time, each QRS complex including a high frequency component and a low frequency component. And each target electrocardiograph detection corresponds to a corresponding reference feature, and the high-frequency component of the QRS complex in electrocardiograph data corresponding to each target electrocardiograph detection is analyzed respectively to determine the reference feature corresponding to the target electrocardiograph detection.

In one embodiment, if the target electrocardiographic detection comprises a resting electrocardiographic detection, the high frequency component of the QRS complex in the resting electrocardiographic signal is analyzed to obtain the corresponding reference feature. If the target electrocardio detection comprises resting electrocardio detection and load movement electrocardio detection, analyzing the high-frequency component of the QRS complex in the resting electrocardio signal to obtain corresponding reference characteristics, and analyzing the high-frequency component of the QRS complex in the movement electrocardio signal to obtain corresponding reference characteristics. The reference feature determined based on the resting electrocardiographic signal may be understood as a resting reference feature, and the resting reference feature may include at least a first resting reference feature, may further include a second resting reference feature, and the reference feature determined based on the moving electrocardiographic signal may be understood as a moving reference feature, and the moving reference feature may include at least a first moving reference feature, and may further include a second moving reference feature.

S106, determining a heart risk assessment grade and a heart risk type according to the reference characteristics; the heart risk assessment grade is used as a reference index for shunting the testee; the cardiac risk type serves as a reference index for assessing the risk type that may be present in the heart of the subject.

The cardiac risk assessment level is used for representing the risk of the heart becoming a problem, for example, the higher the cardiac risk assessment level is, the greater the risk of the heart becoming a problem is represented, so that a doctor can conduct diagnosis and shunt on a tested person by combining clinical symptoms of the tested person. The cardiac risk type is used to characterize a type of risk that a subject's heart may be at, i.e., a type that characterizes a cardiac problem that the subject may be at, specifically including at least one of myocardial injury risk, sudden cardiac death risk, coronary stenosis risk, and others, the myocardial injury risk characterizing the likelihood of myocardial injury, sudden cardiac death risk characterizing the likelihood of sudden cardiac death, coronary stenosis risk characterizing the likelihood of coronary stenosis, and other characterizing the likelihood of not having any of myocardial injury, sudden cardiac death, and coronary stenosis risk. It will be appreciated that the physician may also shunt the subject in combination with cardiac risk assessment level, cardiac risk type and clinical symptoms.

Specifically, the obtained reference features are evaluated and analyzed to obtain corresponding cardiac risk evaluation scores, and corresponding cardiac risk evaluation grades and cardiac risk types are determined according to the cardiac risk evaluation scores so as to be referred by doctors, so that the doctors can accurately know the risk of the heart of the testee and the risk types possibly existing, and the heart health condition of the testee can be accurately identified. If the target electrocardiograph detection comprises resting electrocardiograph detection, determining a heart risk assessment score according to the resting reference index, and if the target electrocardiograph detection comprises resting electrocardiograph detection and load movement electrocardiograph detection, determining the heart risk assessment score according to the resting reference index and the load movement reference index, and further determining the heart risk assessment grade and the heart risk type of the testee.

In one embodiment, the obtained reference features are input into corresponding preset risk assessment functions or pre-trained risk assessment models according to target electrocardiographic detection, and corresponding cardiac risk assessment scores are obtained. It will be appreciated that the reference features are input into a pre-trained risk assessment model, which may also directly output the corresponding cardiac risk assessment level, and may also synchronously output the corresponding cardiac risk type, as determined in particular by the training dataset (comprising input features and corresponding output features) used to train the risk assessment model.

In one embodiment, the cardiac risk assessment score is compared to each of the preset score intervals to determine a corresponding cardiac risk assessment level and, in turn, a cardiac risk type. Taking six levels, i.e., first to sixth levels, which are sequentially increased, as an example, a corresponding preset score interval is preset for each cardiac risk assessment level, wherein the intervals are respectively [0,10], [11,30], [31,50], [51,60], [61,70], [71,100], and if the cardiac risk assessment score is [0,10], the cardiac risk assessment level is determined as the first level, and the cardiac risk type is determined as the other cardiac risk.

In one embodiment, if the output cardiac risk assessment level and cardiac risk type are for reference by a lead doctor, diverting the subject includes suggesting that the subject visit the hospitalization department, suggesting that the subject visit the clinic, and suggesting that the subject return home (without having to visit). It will be appreciated that if the subject is advised to go to an outpatient or hospitalization department, the subject may also be shunted to the corresponding department or doctor based on the type of cardiac risk. The doctor for guiding diagnosis, such as a doctor in a physical examination institution or a physical examination department, and a doctor for guiding diagnosis and diversion of a subject to be treated in a cardiovascular disease department, which is set in a hospital, are not particularly limited herein. For example, taking a cardiac risk assessment level including six levels as an example, if the cardiac risk assessment level output for the subject is a first level, the lead doctor may recommend that the subject return home, if the cardiac risk assessment level is a second level or a third level, the subject be advised to go to an outpatient visit, otherwise, the subject be advised to go to a hospitalization department visit. It is worth mentioning that the guiding doctor also needs to conduct guiding and shunting on the tested person in combination with the clinical symptoms of the tested person.

In one embodiment, if the output cardiac risk assessment level and cardiac risk type are for reference by an outpatient service, the diversion of the subject includes advising the subject to hospitalize, advising the subject to review periodically, and advising the subject to review if discomfort symptoms are present. For example, taking a cardiac risk assessment level including six levels as an example, if the cardiac risk assessment level output for the subject is a first level, the outpatient may recommend that the subject be re-diagnosed if discomfort symptoms occur, if the cardiac risk assessment level is a second or third level, the subject may be advised to review regularly, otherwise, hospitalization of the subject is advised. It is worth noting that the outpatient physician needs to provide further advice on diagnosis and/or detection references in combination with the clinical symptoms of the subject.

According to the cardiac risk assessment method, the cardiac risk assessment grade for representing the risk of the heart of the testee and the cardiac risk type for representing the possible risk type of the heart are obtained efficiently and accurately by acquiring the electrocardiographic data corresponding to the target electrocardiographic detection matched with the clinical indication, analyzing the high-frequency component of the QRS complex in the corresponding electrocardiographic data according to the target electrocardiographic detection to obtain the corresponding reference characteristic, evaluating and analyzing the reference characteristic, so that the doctor can efficiently and accurately identify the heart health condition of the testee by combining the clinical symptoms, and give further diagnosis and/or detection reference suggestions to realize diagnosis and diversion of the testee. In addition, the electrocardiographic data for evaluating the heart risk of the testee are acquired in the target electrocardiographic detection process matched with the clinical indication of the testee, so that the electrocardiographic data capable of accurately evaluating the heart risk of the testee can be acquired as comprehensively as possible under the condition of ensuring the safety detection of the testee, the accuracy of the heart risk evaluation is further improved, and the accuracy of the heart health condition identification is further improved.

In one embodiment, if the target electrocardiographic detection comprises only resting electrocardiographic detection, the electrocardiographic data comprises an age of the subject and a resting electrocardiographic signal, and the reference feature comprises a first resting reference feature; s104 includes: analyzing the high-frequency component of the QRS complex in the resting electrocardiosignal to obtain a high-frequency QRS envelope curve; determining a first resting reference feature according to the high frequency QRS envelope curve and age; the first resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, and a second target number of leads; the first target number of leads refers to the number of resting leads for which the corresponding high frequency morphology index is greater than or equal to the first index threshold; the second target number of leads refers to the number of resting leads having a corresponding root mean square voltage less than or equal to the first voltage threshold.

The number of resting positive leads refers to the number of resting leads with positive indication of corresponding lead positive indexes, and can be used for evaluating myocardial ischemia risk in a resting state, and the resting leads are in positive correlation. The resting critical lead number refers to the number of resting leads indicated as critical by the corresponding lead positive index, can be used for evaluating the critical risk of myocardial ischemia in a resting state, and can more accurately identify the myocardial ischemia by combining the reference characteristic. The lead positive index indicates positive, and is used for representing that the high-frequency morphological index of the corresponding resting lead is larger than or equal to a second index threshold value and the age of the testee is larger than or equal to a preset age, or is used for representing that the high-frequency morphological index of the corresponding resting lead is larger than or equal to a third index threshold value and the age of the testee is smaller than the preset age. The lead positive index is indicated as critical, and is used for representing that the high-frequency morphological index of the corresponding resting lead is larger than the second index threshold value and smaller than the third index threshold value, and the age of the testee is smaller than the preset age. The first, second and third index thresholds may be specifically customized, for example, the first index threshold is 20%, the second index threshold is 8%, and the third index threshold is 15%. The first voltage threshold may be specifically customized according to practical situations, for example, 4uV (micro volt). The preset age may be custom, such as 50 years old.

Specifically, alignment, averaging and high-frequency filtering are sequentially performed on each QRS complex in the resting electrocardiosignal to obtain high-frequency QRS complex data (high-frequency band data of the QRS complex), or high-frequency filtering, alignment and averaging are sequentially performed on the QRS complex in the resting electrocardiosignal to obtain high-frequency QRS complex data, or the resting electrocardiosignal is analyzed to extract the high-frequency electrocardiosignal therefrom, and then alignment and averaging are sequentially performed on the QRS complex in the high-frequency electrocardiosignal to obtain high-frequency QRS complex data, which is not particularly limited herein. A high-frequency QRS envelope curve can be formed based on the high-frequency QRS complex data, and thus, the high-frequency QRS envelope curve can be obtained by performing the above-described data processing on the resting electrocardiographic signal. Analyzing the high-frequency QRS envelope curve corresponding to each resting lead to obtain the total area of each amplitude reduction area on the high-frequency QRS envelope curve as a first total area, the total area below the high-frequency QRS envelope curve as a second total area, and taking the ratio of the first total area to the second total area as the high-frequency morphological index corresponding to the resting lead. Determining the positive indexes of the corresponding leads according to the age of the testee and the high-frequency morphological indexes corresponding to the leads, screening and counting the leads with the positive indexes indicated as positive by the positive indexes of the corresponding leads to obtain the number of the positive leads of the rest, screening and counting the leads with the positive indexes indicated as critical leads of the corresponding leads to obtain the critical number of the rest, and screening and counting the leads with the morphological indexes greater than or equal to the first index threshold value of the corresponding high-frequency leads to obtain the number of the first target leads. And solving the root mean square of a high-frequency QRS envelope curve (namely high-frequency QRS complex data) corresponding to each rest lead to obtain root mean square voltage of the corresponding rest lead, screening and counting rest leads with the corresponding root mean square voltage smaller than or equal to a first voltage threshold value to obtain the number of second target leads.

In one embodiment, if the reference feature comprises a first resting reference feature, the cardiac risk assessment score comprises a first risk assessment score. Inputting a first rest reference characteristic determined based on the age of a tested person and a rest electrocardiosignal into a first risk assessment function pre-configured for rest electrocardiosignal detection or a first risk assessment model pre-trained to obtain corresponding first risk assessment scores, comparing the first risk assessment scores with each preset score interval to obtain first risk assessment grades, determining a first risk type according to the first risk assessment grades, determining the first risk assessment grades as heart risk assessment grades, and determining the first risk type as heart risk types. For example, if the first risk assessment level is the first level, the first risk type is other, otherwise, the first risk type is myocarditis risk.

In one embodiment, the expression of the first risk assessment function pre-configured for resting electrocardiographic detection is as follows:

wherein,for the first risk assessment score,/>For resting critical number of leads, +.>For the number of resting positive leads,for the first target number of leads, +. >A second target number of leads.

In one embodiment, the first rest reference feature further comprises a target high frequency morphology index and a target root mean square voltage, wherein the target high frequency morphology index is a maximum value in the high frequency morphology indexes corresponding to the rest leads, and the target root mean square voltage is a minimum value of the root mean square voltages corresponding to the rest leads. In this embodiment, the expression of the first risk assessment function preconfigured for resting electrocardiographic detection may also be expressed as follows:

wherein,for an additional score determined based on the target frequency morphology index,/->For additional scores determined based on the target root mean square voltage, the following expressions are based, respectively:

wherein,for the target high frequency morphological index +.>The target rms voltage is given in uV (microvolts).

In the above embodiment, if the clinical indication indicates that the subject cannot perform the load exercise electrocardiographic detection, the first resting reference feature is determined according to the resting electrocardiographic signal collected during the resting electrocardiographic detection and the age of the subject, so as to accurately evaluate the cardiac risk assessment level and the cardiac risk type according to the first resting reference feature.

In one embodiment, the reference features further comprise a second resting reference feature; s104 further includes: determining a second resting reference feature according to the high frequency QRS envelope curve and age; the second resting reference feature comprises a resting positive number of leads, a resting critical number of leads, and a first target number of leads; s106 includes: determining a first risk assessment level according to the first rest reference feature; determining a second risk assessment level based on the second resting reference feature; and determining a heart risk assessment level and a heart risk type according to the first risk assessment level and the second risk assessment level.

Wherein the second stationary reference feature is a subset of the first stationary reference feature, whereby the second stationary reference feature may also be determined simultaneously when the first stationary reference feature is determined. The first resting reference feature is used to assess the likelihood of developing myocarditis and the second resting reference feature is used to assess the likelihood of developing sudden cardiac death.

In one embodiment, if the reference features include a first resting reference feature and a second resting reference feature, the cardiac risk assessment score includes a first risk assessment score and a second risk assessment score. Inputting the first resting reference characteristic into a first risk assessment function pre-configured for resting electrocardiograph detection or a first risk assessment model pre-trained to obtain corresponding first risk assessment scores, and comparing the first risk assessment scores with each preset score interval to obtain a first risk assessment grade. Inputting the second rest reference characteristics into a second risk assessment function or a second risk assessment model which is preconfigured for rest electrocardiographic detection to obtain corresponding second risk assessment scores, and comparing the second risk assessment scores with each preset score interval to obtain a second risk assessment grade. The maximum value (highest level) of the first risk assessment level and the second risk assessment level is determined as the cardiac risk assessment level. The first risk type is determined according to the first risk assessment level, the second risk type is determined according to the second risk assessment level, and the cardiac risk type is determined according to the first risk type and the second risk type.

For example, if the first risk assessment level is a second level and the second risk assessment level is a first level, the cardiac risk assessment level is determined to be the second level, the first risk type is determined to be the risk of myocarditis, the second risk type is determined to be other, and the cardiac risk type is determined to be the risk of myocarditis. If the first risk assessment level is a third level and the second risk assessment level is a second level, determining the cardiac risk assessment level as the third level, determining the first risk type as the myocarditis risk, determining the second risk type as the sudden cardiac death risk, and further determining the cardiac risk type as the myocarditis risk and the sudden cardiac death risk.

In one embodiment, the expression of the second risk assessment function pre-configured for resting electrocardiographic detection is as follows:

wherein,for a second risk assessment score determined based on a second resting reference feature +.>For resting critical number of leads, +.>For resting positive number of leads, +.>For a first target number of leads.

In the above embodiment, if the clinical indication indicates that the subject cannot perform the load exercise electrocardiographic detection, the first resting reference feature and the second resting reference feature are determined according to the resting electrocardiographic signal and the age of the subject, so as to more accurately evaluate the cardiac risk assessment level and the cardiac risk type by combining the first resting reference feature and the second resting reference feature.

In one embodiment, the first resting reference feature further comprises a target frequency morphology index and a target root mean square voltage; the second resting reference feature further comprises a target frequency morphology index; the target frequency morphology index is the maximum value in the high frequency morphology indexes corresponding to the rest leads; the target rms voltage is the minimum of the rms voltages corresponding to the respective rest leads.

In one embodiment, the expression of the second risk assessment function pre-configured for resting electrocardiographic detection may also be expressed as follows:

wherein,for additional scores determined based on the target frequency morphology index, it is derived based on the following expression:

wherein,is the target high-frequency morphological index.

In the above embodiment, based on the first resting reference feature and the second resting reference feature including the additional reference feature, the risk types possibly existing in the heart can be more accurately identified and distinguished, and the risk of the heart having problems can be more accurately estimated, so that the doctor can more accurately identify the heart health condition of the testee in combination with clinical symptoms, thereby giving reference suggestions for further diagnosis, detection and the like, and realizing more accurate diagnosis guiding and diversion.

In one embodiment, if the target electrocardiographic detection further comprises load motion electrocardiographic detection, the electrocardiographic data comprises an age, a resting electrocardiographic signal, and a motion electrocardiographic signal of the subject, and the reference features comprise a first resting reference feature and a first motion reference feature; s104 includes: analyzing the high-frequency component of the QRS complex in the resting electrocardiosignal to obtain a high-frequency QRS envelope curve; determining a first resting reference feature according to the high frequency QRS envelope curve and age; the first resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, and a second target number of leads; the first target number of leads refers to the number of resting leads for which the corresponding high frequency morphology index is greater than or equal to the first index threshold; the second target number of leads refers to the number of resting leads having a corresponding root mean square voltage less than or equal to the first voltage threshold; analyzing the high-frequency component of the QRS complex in the motion electrocardiosignal to obtain a high-frequency QRS waveform curve; determining a maximum heart rate of the subject from the exercise electrocardiosignal; determining a first exercise reference feature according to the high-frequency QRS waveform curve, the age and the maximum heart rate; the first motion reference feature comprises a motion positive number of leads, a motion critical number of leads, a third target number of leads, a fourth target number of leads, and a fifth target number of leads; the third target number of leads refers to the number of moving leads having a corresponding first amplitude decrease relative value greater than or equal to the first relative value threshold; the fourth target lead number refers to the number of motion leads of which the corresponding high-frequency QRS waveform curve has a descending and ascending repeated fluctuation trend in the first time period; the fifth target number of leads refers to the number of moving leads having a corresponding second amplitude reduction relative value greater than or equal to the second relative value threshold.

The motion electrocardiosignals are electrocardiosignals acquired in the process of detecting the load motion electrocardiosignals. The load movement electrocardiograph detection process comprises a plurality of stages, and particularly can sequentially comprise a resting stage, a movement stage, a recovery stage and the like, the movement electrocardiograph signal comprises electrocardiograph signals of all stages, the stage division is not limited to the stage, and the stage division can be particularly carried out according to actual conditions. The maximum heart rate refers to the maximum value of the heart rate of the subject during the whole load exercise electrocardiographic detection. The number of the motion positive leads refers to the number of the motion leads with positive indication of the corresponding lead positive index, and can be used for evaluating myocardial ischemia risk under a load motion state, and the motion positive leads and the motion leads are in positive correlation. The motion critical lead number refers to the number of motion leads with the positive index of the corresponding lead indicated as critical, can be used for evaluating the critical risk of myocardial ischemia in the load motion state, and can be used for more accurately evaluating the myocardial ischemia condition in the load motion state by combining the reference characteristic.

The lead positive indicator indicates positive, is used for representing that the first amplitude decrease relative value of the corresponding motion lead is larger than the third relative value threshold, the amplitude decrease absolute value is larger than the preset absolute value threshold, the age of the testee is smaller than the preset age, and the maximum heart rate of the testee is larger than 80% of the target heart rate, is used for representing that the first amplitude decrease relative value of the corresponding motion lead is larger than the fourth relative value threshold, the amplitude decrease absolute value is larger than the preset absolute value threshold, the age of the testee is smaller than the preset age, and the maximum heart rate of the testee is smaller than or equal to 80% of the target heart rate, is used for representing that the first amplitude decrease relative value of the corresponding motion lead is larger than the fourth relative value threshold, the amplitude decrease absolute value is larger than the preset absolute value threshold, the age of the testee is larger than or equal to the preset age, and the maximum heart rate of the testee is larger than or equal to the target heart rate, or is larger than the fifth relative value, the amplitude decrease absolute value is larger than the preset absolute value, the age of the testee is larger than or equal to the target heart rate, and the maximum heart rate of the testee is larger than or equal to the target heart rate. The first relative value threshold, the second relative value threshold, the third relative value threshold, the fourth relative value threshold, the fifth relative value threshold, the preset absolute value threshold and the preset age are customized according to actual conditions, such as 55%, 40%, 60%, 50%, 40%, 1uV (microvolts) and 50 years old. The target heart rate is determined according to the age of the subject, as target heart rate= (220-subject age) ×85%.

The lead positive indicator is indicated as critical, is used for representing that the first amplitude decrease relative value of the corresponding motion lead is greater than 90% of the third relative value threshold and is less than or equal to the third relative value threshold, the amplitude decrease absolute value is greater than the preset absolute value threshold, the age of the subject is less than the preset age, and the maximum heart rate of the subject is greater than 80% of the target heart rate, or is used for representing that the first amplitude decrease relative value of the corresponding motion lead is greater than 90% of the fourth relative value threshold and is less than or equal to the fourth relative value threshold, the amplitude decrease absolute value is greater than the preset absolute value threshold, the age of the subject is less than the preset age, and the maximum heart rate of the subject is less than or equal to 80% of the target heart rate, or is used for representing that the first amplitude decrease relative value of the corresponding motion lead is greater than 90% of the fourth relative value threshold and is less than or equal to the fourth relative value threshold, the amplitude decrease absolute value is greater than or equal to the preset absolute value threshold, the age of the subject is greater than or equal to the maximum heart rate of the fourth relative value threshold, and the amplitude decrease relative value of the first amplitude decrease relative value of the subject is greater than or equal to the preset age of the fourth relative value is greater than or equal to 80% of the maximum heart rate.

The first time period comprises a pre-exercise time period, an exercise middle and a post-exercise time period, wherein the pre-exercise time period is positioned in a resting stage, the exercise middle comprises a whole exercise stage, the post-exercise time period is positioned in a recovery stage, and the pre-exercise time period, the exercise middle and the post-exercise time period are continuous time periods. The second period of time includes a period of time before the exercise and a period of time during the exercise, or the second period of time includes a period of time during the exercise, where the period of time before the exercise and the period of time during the exercise are continuous periods of time, and the period of time during the exercise can be customized according to practical situations, such as the first 3 minutes during the exercise. The first time period may specifically include a second time period, that is, a subinterval in which the second time period is the first time period. The second amplitude dip relative value is used to characterize the dip or steepness of the high frequency QRS waveform curve over a second period of time, and if the second amplitude dip relative value exceeds the second relative value threshold value, indicating that the dip or steepness is sufficiently large, then the likelihood of coronary stenosis is characterized. The first amplitude-decreasing relative value may be understood as the amplitude-decreasing relative value of the high-frequency QRS waveform curve over a first period of time, and the second amplitude-decreasing relative value may be understood as the amplitude-decreasing relative value of the high-frequency QRS waveform curve over a second period of time.

Specifically, according to the first resting reference feature determining manner disclosed in one or more embodiments of the present application, the corresponding first resting reference feature is determined according to the resting electrocardiographic signal and the age of the subject, which is not described herein. The exercise electrocardiosignal comprises a QRS complex corresponding to each heartbeat of the testee in the whole load exercise electrocardio detection process. Dividing the motion electrocardiosignals into a plurality of electrocardiosignal subsets according to the time sequence and the preset moving step length through a window function, wherein each electrocardiosignal subset comprises a QRS complex corresponding to a plurality of heartbeats. For each electrocardiosignal subset, aligning, averaging and high-frequency filtering are sequentially carried out on QRS complexes corresponding to a plurality of heartbeats included in each electrocardiosignal subset to obtain corresponding high-frequency QRS complex data (high-frequency band data of the QRS complexes), and the high-frequency QRS complex data is subjected to root mean square to obtain corresponding root mean square voltage which is used as root mean square voltage/intensity/amplitude corresponding to the electrocardiosignal subset. And carrying out curve smoothing on root mean square voltage/intensity/amplitude corresponding to each electrocardiosignal subset according to time sequence to obtain a high-frequency QRS waveform curve corresponding to the motion electrocardiosignal, wherein the high-frequency QRS waveform curve can be understood as a high-frequency QRS time-intensity curve. The window length and the preset moving step length of the window function can be customized according to actual requirements, for example, the window length is set to 10 seconds, the preset moving step length is set to 10 seconds or one heartbeat period, and one heartbeat period refers to a time interval between two adjacent heartbeats, which is not particularly limited herein. The time sequence is the sequence of the detection time advanced in the electrocardiograph detection process according to the acquisition time/load motion of the signals. According to the mode of extracting heart rate sequences from electrocardiosignals disclosed in the prior art, extracting heart rate sequences of a tested person from exercise electrocardio data, and screening the maximum value from the heart rate sequences as the maximum heart rate of the tested person.

Further, a point with the largest root mean square voltage is selected from the high-frequency QRS waveform curve in the first time period to serve as a first reference point, a point with the smallest root mean square voltage and later than the first reference point is selected from the high-frequency QRS waveform curve in the first time period to serve as a second reference point, the root mean square voltage of the first reference point and the root mean square voltage of the second reference point are subjected to difference to obtain a first amplitude reduction absolute value, and the ratio of the first amplitude reduction absolute value to the root mean square voltage of the first reference point is determined to be a first amplitude reduction relative value. Screening and counting the motion leads with the corresponding first amplitude reduction relative values greater than or equal to the first relative value threshold value to obtain a third target lead number. And determining the lead positive index of the corresponding high-frequency QRS waveform curve according to the first amplitude reduction relative value, the first amplitude reduction absolute value, the age and the maximum heart rate of the testee, and taking the lead positive index as the lead positive index corresponding to the corresponding motion lead. Screening and counting the number of the motion positive leads obtained by the motion leads with positive indexes indicated as positive by the corresponding leads, and screening and counting the number of the motion critical leads obtained by the motion leads with critical indexes indicated as the positive indexes of the corresponding leads. And analyzing the change trend of the high-frequency QRS waveform curve corresponding to each motion lead in the first time period to screen and count the motion leads of which the corresponding high-frequency QRS waveform curve has the descending and ascending repeated fluctuation trend in the first time period, so as to obtain the fourth target lead number.

And selecting a point with the minimum root mean square voltage from the high-frequency QRS waveform curve in the second time period as a third reference point, selecting a point with the maximum root mean square voltage from the high-frequency QRS waveform curve in the second time period, which is earlier than the third reference point in time, as a fourth reference point, and obtaining a second amplitude drop absolute value in the second time period by means of difference between the root mean square voltage of the fourth reference point and the root mean square voltage of the third reference point, wherein the ratio of the second amplitude drop absolute value to the root mean square voltage of the fourth reference point is used as a second amplitude drop relative value. Screening and counting the motion leads with the corresponding second amplitude reduction relative values greater than or equal to the second relative value threshold value to obtain a fifth target lead number.

In one embodiment, the high-frequency QRS waveform curve shows a decreasing and increasing repetitive fluctuation trend in the first period of time, which means that the total number of times the high-frequency QRS curve shows a decreasing trend in the first period of time is greater than or equal to two times, and the increasing trend and the decreasing trend alternately appear. Such as a high frequency QRS waveform curve that exhibits a "W" or "inverted N" waveform during a first period of time.

In one embodiment, if the reference features include a first resting reference feature and a first motion reference feature, the cardiac risk assessment score includes a first risk assessment score and a third risk assessment score. According to one or more embodiments of the application, a respective first risk assessment level and first risk type is determined from a first rest reference feature. Inputting the first motion reference characteristic into a risk assessment function or a pre-trained risk assessment model which is pre-configured for load motion electrocardiograph detection to obtain corresponding third risk assessment scores, comparing the third risk assessment scores with each preset score interval to obtain third risk assessment grades, and determining a third risk type according to the third risk assessment grades. And determining the highest level of the first risk assessment level and the third risk assessment level as a heart risk assessment level, and determining the heart risk type according to the first risk type and the third risk type. For example, if the first risk assessment level is the first level, the third risk assessment level is the fifth level, the first risk type is other, the third risk type is coronary stenosis risk, the cardiac risk assessment level is determined to be the fifth level, and the cardiac risk type is determined to be coronary stenosis risk.

In one embodiment, the expression of the risk assessment function preconfigured for load motion electrocardiography detection is as follows:

/>

wherein,for a third risk assessment score,/->For the number of exercise critical leads, +.>For the number of motion positive leads,for the third target number of leads, +.>For the fourth target number of leads, +.>A fifth target number of leads.

In one embodiment, the first motion reference feature further comprises a first amplitude decline versus a second amplitude decline versus a corresponding motion lead. In this embodiment, the expression of the risk assessment function preconfigured for the load exercise electrocardiographic detection may also be expressed as follows:

wherein,for an additional fraction determined on the basis of the corresponding first amplitude decrease relative value of the respective motion lead,/->For the additional score determined based on the corresponding second amplitude reduction relative value for each motion lead, the following expressions are based, respectively:

in the above embodiment, if the clinical indication indicates that the subject can perform the load exercise electrocardiographic detection, the first resting reference feature is determined according to the resting electrocardiographic signal collected during the resting electrocardiographic detection and the age of the subject, and the first exercise reference feature is determined according to the exercise electrocardiographic signal collected during the load exercise electrocardiographic detection and the age of the subject, so as to accurately evaluate the cardiac risk assessment level and the cardiac risk type according to the first resting reference feature and the first exercise reference feature.

In one embodiment, the reference features further comprise a second stationary reference feature and a second motion reference feature; s104 further includes: determining a second resting reference feature according to the high frequency QRS envelope curve and age; the second resting reference feature comprises a resting positive number of leads, a resting critical number of leads, and a first target number of leads; determining a second exercise reference feature according to the high-frequency QRS waveform curve, the age and the maximum heart rate; the second motion reference feature comprises a motion positive number of leads and a motion critical number of leads; s106 includes: determining a first risk assessment level according to the first rest reference feature; determining a second risk assessment level according to the second resting reference feature and the second movement reference feature; determining a third risk assessment level according to the first motion reference feature; and determining a heart risk assessment level and a heart risk type according to the first risk assessment level, the second risk assessment level and the third risk assessment level.

Wherein the second stationary reference feature is a subset of the first stationary reference feature, whereby the second stationary reference feature may also be determined simultaneously when the first stationary reference feature is determined. Similarly, the second motion reference feature is a subset of the first motion reference feature, whereby the second motion reference feature may also be determined simultaneously when the first motion reference feature is determined. The first resting reference feature is used to assess the likelihood of developing myocarditis, the second resting reference feature is used in combination with the second movement reference feature to assess the likelihood of developing sudden cardiac death, and the first movement reference feature is used to assess the likelihood of developing coronary stenosis.

In one embodiment, if the reference features include a first resting reference feature, a second resting reference feature, a first motion reference feature, and a second motion reference feature, the cardiac risk assessment score includes a first risk assessment score, a second risk assessment score, and a third risk assessment score. According to one or more embodiments of the present application, a first risk assessment score is determined from a first resting reference feature, thereby determining a first risk assessment level and a first risk type, and a third risk assessment score is determined from a first movement reference feature, thereby determining a third risk assessment level and a third risk type. And inputting a risk assessment function or a risk assessment model configured for the combination of resting electrocardiograph detection and load exercise electrocardiograph detection to obtain a second risk assessment score, comparing the second risk assessment score with each preset score interval to obtain a second risk assessment grade, and determining a second risk type according to the second risk assessment grade. Further, the highest level of the first, second and third risk assessment levels is determined as the cardiac risk assessment level, and the cardiac risk type is determined from the first, second and third risk types.

For example, if the first risk assessment level is the second level, the second risk assessment level is the fourth level, and the third risk assessment level is the third level, then the first risk type is myocarditis risk, the second risk type is sudden cardiac death risk, and the third risk type is coronary stenosis risk, then the cardiac risk assessment level is determined as the fourth level, and the cardiac risk type is determined as myocarditis risk, sudden cardiac death risk, and coronary stenosis risk.

In one embodiment, the expression of the risk assessment function configured for the combination of resting electrocardiographic detection and load movement electrocardiographic detection is as follows:

wherein,for a second risk assessment score determined based on a second resting reference feature in combination with a second movement reference feature +.>For resting critical number of leads, +.>For resting positive number of leads, +.>For the first target number of leads, +.>For the number of exercise critical leads, +.>Is the number of motion positive leads.

In the above embodiment, if the clinical indication indicates that the subject can perform the load exercise electrocardiographic detection, the first resting reference feature and the second resting reference feature are determined according to the resting electrocardiographic signal and the age of the subject, and the first exercise reference feature and the second exercise reference feature are determined according to the exercise electrocardiographic signal and the age of the subject, so that the heart risk assessment level and the heart risk type can be more accurately assessed by combining the first resting reference feature, the second resting reference feature, the first exercise reference feature and the second exercise reference feature.

In one embodiment, the first resting reference feature further comprises a target frequency morphology index and a target root mean square voltage; the second resting reference feature further comprises a target frequency morphology index; the target frequency morphology index is the maximum value in the high frequency morphology indexes corresponding to the rest leads; the target root mean square voltage is the minimum value of the root mean square voltages corresponding to the rest leads; the first motion reference feature further comprises a first amplitude reduction relative value and a second amplitude reduction relative value corresponding to each motion lead; the second motion reference feature further includes a second amplitude reduction relative value for each motion lead.

In one embodiment, the expression of the risk assessment function configured for the combination of resting electrocardiographic detection and load movement electrocardiographic detection may also be expressed as follows:

wherein,for an additional score determined based on the target frequency morphology index,/->For the additional score determined based on the corresponding second amplitude reduction relative value for each motion lead, the following expressions are based, respectively:

wherein,is the target high-frequency morphological index.

In the above embodiment, based on the first resting reference feature, the second resting reference feature, the first movement reference feature and the second movement reference feature including the additional reference feature, the possible risk types of the heart can be more accurately identified and distinguished, and the risk of the heart being problematic can be more accurately estimated, so that the doctor can more accurately identify the heart health condition of the subject in combination with clinical symptoms, thereby giving reference suggestions for further diagnosis, detection, and the like, and realizing more accurate diagnosis guiding and diversion.

In one embodiment, the cardiac risk assessment method further includes: determining corresponding risk assessment features according to the heart risk type according to the electrocardiographic data; and determining the attention level of the corresponding heart risk type according to the risk assessment features.

In particular, the level of attention characterizes the difference in the degree of attention, which can be used to indicate the difference in the magnitude of the likelihood of the subject developing the corresponding cardiac risk type. After determining the heart risk type according to the electrocardio data, determining corresponding risk assessment features according to each heart risk type determined according to the electrocardio data, and determining corresponding attention level according to the risk assessment features corresponding to each heart risk type so as to be referred by a doctor in a diagnosis process, so that the doctor can accurately identify the heart health condition of the testee according to the heart risk type, the attention level and clinical symptoms, and accordingly corresponding diagnosis and treatment reference suggestions are given. It can be appreciated that at least one of the risk assessment level and the risk assessment feature corresponding to the cardiac risk type can also be output, so that the doctor can recognize the cardiac health condition by comprehensively considering the reference indexes. In this embodiment, the output cardiac risk type, the attention level, and the like are referred to by an outpatient or inpatient, so that the doctor can accurately identify the cardiac health condition of the subject in combination with the clinical symptoms, thereby giving corresponding diagnosis and treatment or detection reference advice.

In one embodiment, a risk assessment feature corresponding to each cardiac risk type is input into a risk assessment model pre-trained for the cardiac risk type, a corresponding attention level is output by the risk assessment model, or a risk assessment function pre-configured for the cardiac risk type or a pre-trained risk assessment model is input into the risk assessment feature corresponding to each cardiac risk type, so as to obtain a risk assessment score corresponding to the cardiac risk type, and further determine a corresponding attention level, or each risk assessment feature corresponding to each cardiac risk type is respectively compared with a corresponding preset reference interval to determine a reference level corresponding to each risk assessment feature, and each reference level is synthesized to determine a corresponding attention level. It will be appreciated that if the risk assessment features include only features for quantitative analysis, the corresponding level of attention is indeed based on the risk assessment features in the manner of assessment described above. If the risk assessment features include features for qualitative analysis and features for quantitative analysis, then the respective level of interest may be determined in the manner of the assessment described above based on the features for quantitative analysis, if it is determined that the respective cardiac risk type exists based on the features for qualitative analysis. For the risk assessment model with the attention level as the output feature, the feature for qualitative analysis and the feature for quantitative analysis may be used as the input feature, and the corresponding risk assessment model may be input to obtain the corresponding attention level.

In an embodiment, the cardiac electrical data only comprises resting cardiac electrical signals, and if the cardiac risk type comprises a risk of myocardial damage, the risk assessment feature corresponding to the risk of myocardial damage is determined from the resting cardiac electrical signals, and if the cardiac risk type further comprises a risk of sudden cardiac death, the risk assessment feature corresponding to the risk of sudden cardiac death is also determined from the resting cardiac electrical signals. The risk assessment features corresponding to the myocardial damage risk include a first risk assessment feature for assessing the risk of myocarditis and a second risk assessment feature for assessing the risk of heart failure. The first risk assessment feature comprises a number of resting positive leads for determining an myocarditis type, and if the myocarditis type is acute myocarditis, the first risk assessment feature further comprises a target frequency morphology index, if the myocarditis type is chronic myocarditis, the first risk assessment feature further comprises a target frequency morphology index and an average peak voltage of limb leads, and if the myocarditis type is fulminant myocarditis, the first risk assessment feature further comprises a QRS time limit, a target high frequency morphology index, and a high frequency morphology index corresponding to each resting lead by the average peak voltage of limb leads. Wherein the target high-frequency morphology index is the maximum value in the high-frequency morphology indexes corresponding to each resting lead, the average peak voltage of the limb leads is the average value of the peak voltages of the limb leads, and the resting leads comprise limb leads and chest leads. It will be appreciated that the first risk assessment feature may also include a sixth target number of leads for qualitative analysis of myocarditis condition, the sixth target number of leads being the number of resting leads for which the corresponding number of peaks exceeds a first number threshold, such as 3, and for which the corresponding lead positive indicator indicates positive. The second risk assessment feature comprises a QRS time limit, a high-frequency morphological index of average peak voltage of limb leads corresponding to each resting lead, and can further comprise the number of resting positive leads for quantitatively analyzing heart failure risk, and can further comprise the number of sixth target leads for qualitatively analyzing heart failure condition.

In this embodiment, the risk assessment features corresponding to the sudden cardiac death risk include a high frequency morphology index with QRS time limit corresponding to each resting lead, and further include at least one of a resting positive lead number, an arrhythmia assessment index, a target peak voltage, and a tachycardia assessment index, for quantitatively analyzing the sudden cardiac death risk, and further include a seventh target lead number for qualitatively analyzing the sudden cardiac death risk, and further include a QRS fragmentation wave index for performing more accurate qualitative analysis in combination with the seventh target lead number. Arrhythmia assessment indicators include recurrent and sporadic arrhythmias. The target peak voltage is the minimum value of the peak voltages corresponding to the rest leads. The tachycardia evaluation index is used to indicate whether there is a possibility of ventricular tachycardia. The seventh number of leads is the number of stationary leads having a corresponding number of peaks greater than or equal to the second number threshold. A second number threshold such as 4. Arrhythmia assessment indicators and tachycardia assessment indicators are determined based on low frequency electrocardiograms derived from resting electrocardiosignals. The QRS-fragmentation index is used to indicate whether QRS-fragmentation is present in the low frequency electrocardiogram.

In one embodiment, the cardiac electrical data comprises a resting cardiac electrical signal and a moving cardiac electrical signal, the respective risk assessment features are determined from the moving cardiac electrical signal if the cardiac risk type comprises a coronary stenosis risk, the respective risk assessment features are determined from the resting cardiac electrical signal if the cardiac risk type comprises a myocardial damage risk, and the respective risk assessment features are determined from the resting cardiac electrical signal and the moving cardiac electrical signal if the cardiac risk type comprises a sudden cardiac death risk. The risk assessment feature corresponding to the coronary stenosis risk comprises at least one of a first amplitude decrease relative value and a first amplitude decrease absolute value for quantitatively analyzing the coronary stenosis condition, a number of motion positive leads for quantitatively analyzing the myocardial ischemia condition, and a second amplitude decrease relative value for qualitatively analyzing the coronary stenosis condition. The risk assessment features corresponding to the risk of myocardial damage are the same as those in the above corresponding embodiments, and will not be described here again. The risk assessment features corresponding to the sudden cardiac death risk include a risk assessment feature determined based on the resting electrocardiosignal and a risk assessment feature determined based on the exercise electrocardiosignal, where the risk assessment feature determined based on the resting electrocardiosignal is consistent with the foregoing corresponding embodiment, and not described in detail herein, the risk assessment feature determined based on the exercise electrocardiosignal includes the number of exercise positive leads, and may further include a second amplitude reduction relative value.

In the above embodiment, the corresponding risk assessment feature is determined according to the cardiac risk type of the subject according to the electrocardiographic data, and the attention level corresponding to the cardiac risk type is further determined based on the risk assessment feature, so as to be referred by a doctor, so that the doctor can more accurately identify the cardiac health condition of the subject in combination with clinical symptoms.

In one or more embodiments of the present application, the resting leads used to collect resting electrocardiographic signals during resting electrocardiographic detection and the moving leads used to collect moving electrocardiographic signals during load movement electrocardiographic detection may be the same or different in type, number, and location, and are not specifically limited herein.

In one implementation, as shown in fig. 2, a schematic representation of a high frequency QRS waveform profile is provided. The high-frequency QRS waveform curve is used for representing the change trend of root mean square of high-frequency components of the QRS complex of the tested person along with time in the whole load movement electrocardiograph detection process, namely, the change trend of energy in the whole load movement electrocardiograph detection process. Fig. 2 illustrates a high frequency QRS waveform curve corresponding to limb lead aVF, with time on the abscissa, time of detection corresponding to the load movement electrocardiographic detection process in minutes, root mean square voltage (RMS voltage), which can also be understood as intensity or amplitude in uV (microvolts). Wherein the first amplitude decrease relative value and the first amplitude decrease absolute value used to determine the corresponding lead positive indicator are 55% and 2.9uV, respectively.

In one implementation, as shown in fig. 3, a schematic representation of a high frequency QRS envelope curve is provided. The high-frequency QRS envelope curve represents a shape chart obtained by averaging all high-frequency QRS complexes (high-frequency components of QRS complexes) in the resting electrocardiosignal, and is specifically represented by a single high-frequency QRS complex envelope curve. Fig. 3 illustrates a high frequency QRS envelope curve corresponding to chest lead V5, with time on the abscissa and time duration of the corresponding QRS complex in ms (milliseconds) and voltage on the ordinate in uV (microvolts). Wherein the high frequency morphology index of the corresponding lead is 7.1%.

As shown in fig. 4, in one embodiment, there is provided a cardiac risk assessment method, which specifically includes the steps of:

s402, acquiring electrocardiographic data corresponding to target electrocardiographic detection matched with clinical indications; clinical indications are used to indicate whether load exercise electrocardiographic detection can be performed; the target electrocardiographic detection comprises at least resting electrocardiographic detection.

S404, if the target electrocardiograph detection only comprises the resting electrocardiograph detection, the electrocardiograph data comprise the age of the testee and the resting electrocardiograph signal; and analyzing the high-frequency component of the QRS complex in the resting electrocardiosignal to obtain a high-frequency QRS envelope curve.

S406, determining a first rest reference characteristic and a second rest reference characteristic according to the high-frequency QRS envelope curve and the age; the first resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, a second target number of leads, a target high frequency morphology index, and a target root mean square voltage; the first target number of leads refers to the number of resting leads for which the corresponding high frequency morphology index is greater than or equal to the first index threshold; the second target number of leads refers to the number of resting leads having a corresponding root mean square voltage less than or equal to the first voltage threshold; the target frequency morphology index is the maximum value in the high frequency morphology indexes corresponding to the rest leads; the target root mean square voltage is the minimum value of the root mean square voltages corresponding to the rest leads; the second resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, and a target high frequency morphology index.

S408, determining a first risk assessment level according to the first rest reference characteristic.

S410, determining a second risk assessment level according to the second rest reference characteristic.

S412, determining a heart risk assessment level and a heart risk type according to the first risk assessment level and the second risk assessment level; the heart risk assessment grade is used as a reference index for shunting the testee; the cardiac risk type serves as a reference index for assessing the risk type that may be present in the heart of the subject.

S414, if the target electrocardiograph detection further comprises load movement electrocardiograph detection, the electrocardiograph data comprise age, resting electrocardiograph signals and movement electrocardiograph signals of the testee; and analyzing the high-frequency component of the QRS complex in the resting electrocardiosignal to obtain a high-frequency QRS envelope curve.

S416, determining a first rest reference characteristic and a second rest reference characteristic according to the high-frequency QRS envelope curve and the age; the first resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, a second target number of leads, a target high frequency morphology index, and a target root mean square voltage; the first target number of leads refers to the number of resting leads for which the corresponding high frequency morphology index is greater than or equal to the first index threshold; the second target number of leads refers to the number of resting leads having a corresponding root mean square voltage less than or equal to the first voltage threshold; the target frequency morphology index is the maximum value in the high frequency morphology indexes corresponding to the rest leads; the target root mean square voltage is the minimum value of the root mean square voltages corresponding to the rest leads; the second resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, and a target high frequency morphology index.

S418, analyzing the high-frequency component of the QRS complex in the exercise electrocardiosignal to obtain a high-frequency QRS waveform curve.

S420, determining the maximum heart rate of the testee according to the exercise electrocardiosignal.

S422, determining a first exercise reference feature and a second exercise reference feature according to the high-frequency QRS waveform curve, the age and the maximum heart rate; the first motion reference feature comprises a motion positive lead number, a motion critical lead number, a third target lead number, a fourth target lead number and a fifth target lead number, and a first amplitude reduction relative value and a second amplitude reduction relative value corresponding to each motion lead; the third target number of leads refers to the number of moving leads having a corresponding first amplitude decrease relative value greater than or equal to the first relative value threshold; the fourth target lead number refers to the number of motion leads of which the corresponding high-frequency QRS waveform curve has a descending and ascending repeated fluctuation trend in the first time period; the fifth target number of leads refers to the number of moving leads having a corresponding second amplitude reduction relative value greater than or equal to the second relative value threshold; the second motion reference feature includes a number of motion positive leads and a number of motion critical leads, and a second amplitude reduction relative value for each motion lead.

S424, determining a first risk assessment level according to the first rest reference characteristic.

S426, determining a second risk assessment level according to the second rest reference characteristic and the second motion reference characteristic.

And S428, determining a third risk assessment level according to the first motion reference characteristic.

S430, determining a heart risk assessment level and a heart risk type according to the first risk assessment level, the second risk assessment level and the third risk assessment level.

S432, corresponding risk assessment features are determined according to the cardiac risk types according to the electrocardiographic data.

S434, the attention level of the corresponding heart risk type is determined according to the risk assessment features.

In the above embodiment, if the clinical indication indicates that the subject cannot perform the load exercise electrocardiographic detection, the age of the subject and the resting electrocardiographic signal acquired during the resting electrocardiographic detection process are acquired and analyzed to obtain the first resting reference feature and the second resting reference feature, so as to determine the corresponding cardiac risk assessment level and cardiac risk type. If the clinical indication indicates that the testee can carry out load exercise electrocardio detection, acquiring and analyzing the age of the testee and the rest electrocardio signals acquired in the rest electrocardio detection process to obtain a first rest reference characteristic and a second rest reference characteristic, acquiring and analyzing the age and the exercise electrocardio signals acquired in the load exercise electrocardio detection process to obtain a first exercise reference characteristic and a second exercise reference characteristic, and comprehensively considering each reference characteristic to obtain a corresponding heart risk assessment grade and heart risk type. The heart risk assessment grade of the risk of the heart of the tested person is output, and the heart risk type of the risk type possibly existing in the heart is indicated for a doctor to refer to, so that the doctor can efficiently and accurately identify the heart health condition of the tested person by combining clinical symptoms, and further diagnosis and/or detection reference suggestions are given to realize common screening, diagnosis guiding and diversion of the tested person. And corresponding risk assessment characteristics are determined according to the heart risk types of the testee according to the electrocardiograph data, and then the attention level corresponding to the heart risk types is determined for reference by doctors, so that the doctors can more accurately identify the heart health condition of the testee by combining clinical symptoms, and further diagnosis and treatment reference suggestions are given.

It should be understood that, although the steps in the flowcharts of fig. 1 and 4 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps in fig. 1 and 4 may include a plurality of steps or stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the execution of the steps or stages is not necessarily sequential, but may be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps.

In one embodiment, as shown in fig. 5, there is provided a cardiac risk assessment apparatus 500 comprising: an acquisition module 501, a feature determination module 502, and a risk assessment module 503, wherein:

an acquisition module 501, configured to acquire electrocardiographic data corresponding to target electrocardiographic detection matched with a clinical indication; clinical indications are used to indicate whether load exercise electrocardiographic detection can be performed; the target electrocardiographic detection at least comprises resting electrocardiographic detection;

The feature determining module 502 is configured to analyze a high-frequency component of a QRS complex in electrocardiographic data according to target electrocardiographic detection to obtain a corresponding reference feature;

a risk assessment module 503, configured to determine a cardiac risk assessment level and a cardiac risk type according to the reference features; the heart risk assessment grade is used as a reference index for shunting the testee; the cardiac risk type serves as a reference index for assessing the risk type that may be present in the heart of the subject.

In one embodiment, if the target electrocardiographic detection comprises only resting electrocardiographic detection, the electrocardiographic data comprises an age of the subject and a resting electrocardiographic signal, and the reference feature comprises a first resting reference feature; the feature determining module 502 is further configured to analyze a high frequency component of the QRS complex in the resting electrocardiograph signal to obtain a high frequency QRS envelope curve; determining a first resting reference feature according to the high frequency QRS envelope curve and age; the first resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, and a second target number of leads; the first target number of leads refers to the number of resting leads for which the corresponding high frequency morphology index is greater than or equal to the first index threshold; the second target number of leads refers to the number of resting leads having a corresponding root mean square voltage less than or equal to the first voltage threshold.

In one embodiment, the reference features further comprise a second resting reference feature; the feature determining module 502 is further configured to determine a second rest reference feature according to the high-frequency QRS envelope curve and the age; the second resting reference feature comprises a resting positive number of leads, a resting critical number of leads, and a first target number of leads; the risk assessment module 503 is further configured to determine a first risk assessment level according to the first rest reference feature; determining a second risk assessment level based on the second resting reference feature; and determining a heart risk assessment level and a heart risk type according to the first risk assessment level and the second risk assessment level.

In one embodiment, if the target electrocardiographic detection further comprises load motion electrocardiographic detection, the electrocardiographic data comprises an age, a resting electrocardiographic signal, and a motion electrocardiographic signal of the subject, and the reference features comprise a first resting reference feature and a first motion reference feature; the feature determining module 502 is further configured to analyze a high frequency component of the QRS complex in the resting electrocardiograph signal to obtain a high frequency QRS envelope curve; determining a first resting reference feature according to the high frequency QRS envelope curve and age; the first resting reference feature comprises a resting positive number of leads, a resting critical number of leads, a first target number of leads, and a second target number of leads; the first target number of leads refers to the number of resting leads for which the corresponding high frequency morphology index is greater than or equal to the first index threshold; the second target number of leads refers to the number of resting leads having a corresponding root mean square voltage less than or equal to the first voltage threshold; analyzing the high-frequency component of the QRS complex in the motion electrocardiosignal to obtain a high-frequency QRS waveform curve; determining a maximum heart rate of the subject from the exercise electrocardiosignal; determining a first exercise reference feature according to the high-frequency QRS waveform curve, the age and the maximum heart rate; the first motion reference feature comprises a motion positive number of leads, a motion critical number of leads, a third target number of leads, a fourth target number of leads, and a fifth target number of leads; the third target number of leads refers to the number of moving leads having a corresponding first amplitude decrease relative value greater than or equal to the first relative value threshold; the fourth target lead number refers to the number of motion leads of which the corresponding high-frequency QRS waveform curve has a descending and ascending repeated fluctuation trend in the first time period; the fifth target number of leads refers to the number of moving leads having a corresponding second amplitude reduction relative value greater than or equal to the second relative value threshold.

In one embodiment, the reference features further comprise a second stationary reference feature and a second motion reference feature; the feature determining module 502 is further configured to determine a second rest reference feature according to the high-frequency QRS envelope curve and the age; the second resting reference feature comprises a resting positive number of leads, a resting critical number of leads, and a first target number of leads; determining a second exercise reference feature according to the high-frequency QRS waveform curve, the age and the maximum heart rate; the second motion reference feature comprises a motion positive number of leads and a motion critical number of leads; the risk assessment module 503 is further configured to determine a first risk assessment level according to the first rest reference feature; determining a second risk assessment level according to the second resting reference feature and the second movement reference feature; determining a third risk assessment level according to the first motion reference feature; and determining a heart risk assessment level and a heart risk type according to the first risk assessment level, the second risk assessment level and the third risk assessment level.

In one embodiment, the feature determining module 502 is further configured to determine a corresponding risk assessment feature according to the cardiac risk type according to the electrocardiographic data; the risk assessment module 503 is further configured to determine a focus level of the corresponding cardiac risk type according to the risk assessment feature.

For specific limitations of the cardiac risk assessment device, reference may be made to the above limitations of the cardiac risk assessment method, which are not repeated here. The respective modules in the cardiac risk assessment apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing the electrocardiographic data corresponding to the target electrocardiographic detection matched with the clinical indication. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a cardiac risk assessment method.

It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.

Claims

1. A method of cardiac risk assessment, the method comprising:

Determining a heart risk assessment grade and a heart risk type according to the reference characteristics; the heart risk assessment grade is used as a reference index for shunting the testee; the cardiac risk type is used as a reference index for evaluating the risk type possibly existing in the heart of the subject;

if the target electrocardiograph detection further comprises load movement electrocardiograph detection, the electrocardiograph data comprise the age, the resting electrocardiograph signal and the movement electrocardiograph signal of the testee, and the reference features comprise a first resting reference feature and a first movement reference feature; analyzing the high-frequency component of the QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics, wherein the method comprises the following steps:

2. The method of claim 1, wherein if the target electrocardiographic detection comprises only resting electrocardiographic detection, the electrocardiographic data comprises an age of the subject and a resting electrocardiographic signal, the reference feature comprises a first resting reference feature; analyzing the high-frequency component of the QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics, wherein the method comprises the following steps:

3. The method of claim 2, wherein the reference features further comprise a second resting reference feature; analyzing the high-frequency component of the QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics, and further comprising:

4. The method of claim 3, wherein the first resting reference feature further comprises a target frequency morphology index and a target root mean square voltage; the second stationary reference feature further comprises the target high frequency morphology index; the target high-frequency morphology index is the maximum value of the high-frequency morphology indexes corresponding to the rest leads; the target rms voltage is the minimum of the rms voltages corresponding to the respective rest leads.

5. The method of claim 1, wherein the reference features further comprise a second resting reference feature and a second moving reference feature; analyzing the high-frequency component of the QRS complex in the electrocardiograph data according to the target electrocardiograph detection to obtain corresponding reference characteristics, and further comprising:

6. The method of claim 5, wherein the first resting reference feature further comprises a target frequency morphology index and a target root mean square voltage; the second stationary reference feature further comprises the target high frequency morphology index; the target high-frequency morphology index is the maximum value of the high-frequency morphology indexes corresponding to the rest leads; the target root mean square voltage is the minimum value of root mean square voltages corresponding to the rest leads; the first motion reference feature further comprises a first amplitude reduction relative value and a second amplitude reduction relative value corresponding to each motion lead; the second motion reference feature further includes a second amplitude reduction relative value for each motion lead.

7. The method according to any one of claims 1 to 6, further comprising:

8. A cardiac risk assessment device, the device comprising:

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.