CN109770889B - Electrocardiogram data section selection method and device - Google Patents

Electrocardiogram data section selection method and device Download PDF

Info

Publication number
CN109770889B
CN109770889B CN201711132057.7A CN201711132057A CN109770889B CN 109770889 B CN109770889 B CN 109770889B CN 201711132057 A CN201711132057 A CN 201711132057A CN 109770889 B CN109770889 B CN 109770889B
Authority
CN
China
Prior art keywords
analysis result
analysis
target
electrocardiogram
electrocardiogram data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711132057.7A
Other languages
Chinese (zh)
Other versions
CN109770889A (en
Inventor
张在阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Edan Instruments Inc
Original Assignee
Edan Instruments Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Edan Instruments Inc filed Critical Edan Instruments Inc
Priority to CN201711132057.7A priority Critical patent/CN109770889B/en
Publication of CN109770889A publication Critical patent/CN109770889A/en
Application granted granted Critical
Publication of CN109770889B publication Critical patent/CN109770889B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention provides an electrocardiogram data section selection method and device, wherein the method comprises the following steps: acquiring original electrocardiogram data; carrying out segmentation processing on original electrocardiogram data to obtain N segments of electrocardiogram data, wherein N is a positive integer; analyzing each section of the electrocardiogram data fragments by adopting at least one preset analysis strategy to obtain at least one pre-analysis result of each section of the electrocardiogram data, wherein different preset analysis strategies correspond to different pre-analysis results; comprehensively judging at least one pre-analysis result of each section of the electrocardiogram data fragments to obtain the electrocardiogram data fragments corresponding to the optimal target analysis result; and generating a target electrocardiogram waveform according to the electrocardiogram data segment corresponding to the optimal target analysis result. The method can obtain the target electrocardiographic waveform capable of reflecting the real state of illness of the patient, so that accurate diagnosis results can be obtained based on the target electrocardiographic waveform, and risks of misdiagnosis or missed diagnosis are reduced as far as possible.

Description

Electrocardiogram data section selection method and device
Technical Field
The invention relates to the technical field of electrocardiographic examination, in particular to an electrocardiographic data section selection method and device.
Background
The traditional static electrocardio examination time is 10s, and an electrocardio algorithm or a doctor can give quantitative measurement information and qualitative diagnosis information according to the electrocardio signal characteristics of a patient within 10 s; with the development of networking/informatization, the current electrocardiographic examination workflow gradually turns to be more network-dependent and informatization-intelligentized. Normally, a doctor at a diagnosis end does not perform other examinations, waits for a report to be printed, performs diagnosis, but acquires electrocardiosignals by an operator, transmits the acquired electrocardiosignals to the diagnosis end through a network, and performs diagnosis and prints the report according to uploaded data by the doctor at the diagnosis end; although the examination efficiency is improved, the examination end and the diagnosis end cannot communicate in real time, so that interference exists in the acquired 10s waveform, or the real condition of the patient cannot be displayed, and the requirement of long-time acquisition is met.
The acquisition of the electrocardiosignals which can reach several minutes to dozens of minutes can not only reflect the electrocardio information of patients more comprehensively, but also ensure that waveforms with good signal quality are used for diagnosis and analysis of doctors. For example, some patients have occasional early ventricular signs, which are not always reflected in a normal 10s static examination, but the early signs and reflections of some diseases may be the signs and reflections of some diseases, and early detection and clinical intervention can effectively reduce the risk of late stage morbidity of the patients and even save the lives of the patients in early stage of morbidity. In the current examination process, after long-time electrocardiosignals are collected, a doctor needs to browse all collected signals one by one second, and manually selects an optimal 10s waveform as a diagnosis basis and prints a report. The process undoubtedly increases the workload for doctors invisibly, obviously increases the diagnosis time of a single patient and influences the work efficiency of the doctors. The optimal may include whether the cardiac signal is good, whether an abnormal signal appears, whether an arrhythmia event occurs, whether other abnormalities which need attention exist, and the like. These complex waveform determinations also require a high degree of attention from the doctor, and if there is a visual determination error, misdiagnosis or missed diagnosis may occur, which greatly increases the risk. Therefore, an electrocardiographic data segment selection method and device become a technical problem to be solved urgently.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, a first objective of the present invention is to provide an electrocardiographic data segmentation method, which analyzes each segment of electrocardiographic data by using a plurality of different preset analysis strategies, and comprehensively judges a plurality of pre-analysis results of each segment of electrocardiographic data to select an electrocardiographic data segment corresponding to an optimal target analysis result, so as to obtain a target electrocardiographic waveform capable of reflecting the real disease condition of a patient, thereby ensuring that an accurate diagnosis result is obtained subsequently based on the target electrocardiographic waveform, and reducing the risk of misdiagnosis or missed diagnosis as much as possible.
Therefore, the second purpose of the invention is to provide an electrocardiogram data section selection device.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides a method for selecting electrocardiographic data, including:
acquiring original electrocardiogram data;
carrying out segmentation processing on the original electrocardiogram data to obtain N segments of electrocardiogram data fragments, wherein N is a positive integer;
analyzing each section of the electrocardiogram data fragments by adopting at least one preset analysis strategy to obtain at least one pre-analysis result of each section of the electrocardiogram data, wherein different preset analysis strategies correspond to different pre-analysis results;
comprehensively judging at least one pre-analysis result of each section of the electrocardiogram data segments to obtain the electrocardiogram data segments corresponding to the optimal target analysis result;
and generating a target electrocardiogram waveform according to the electrocardiogram data segment corresponding to the optimal target analysis result.
The method for comprehensively judging at least one pre-analysis result of each segment of the electrocardiographic data segment to obtain the electrocardiographic data segment corresponding to the optimal target analysis result comprises the following steps:
weighting and summing at least one pre-analysis result of each section of the electrocardiogram data segment to obtain a target analysis result of each section of the electrocardiogram data segment;
and selecting a target analysis result with the largest value from the target analysis results of all the sections of the electrocardiogram data segments, and determining the electrocardiogram segment corresponding to the target analysis result with the largest value as the electrocardiogram data segment corresponding to the optimal target analysis result.
According to the method, the at least one preset analysis strategy is respectively waveform signal quality analysis, abnormal electrocardiosignal screening analysis and arrhythmia event analysis;
acquiring an execution sequence corresponding to a preset analysis strategy, wherein the execution sequence comprises synchronous execution or asynchronous execution;
the weighted summation of the at least one pre-analysis result of each section of the electrocardiogram data segment is performed to obtain a target analysis result of each section of the electrocardiogram data segment, and the weighted summation comprises the following steps:
analyzing and processing each section of the electrocardiogram data segment according to waveform signal quality analysis based on the execution sequence to obtain a pre-analysis result corresponding to the waveform signal quality analysis;
analyzing and processing each section of the electrocardiogram data fragments according to abnormal electrocardiogram signal screening analysis based on the execution sequence to obtain a pre-analysis result corresponding to the abnormal electrocardiogram signal screening analysis;
analyzing and processing each section of the electrocardiogram data fragments according to arrhythmia event analysis based on the execution sequence to obtain a pre-analysis result corresponding to the arrhythmia event analysis;
and carrying out weighted summation on the pre-analysis result corresponding to the waveform signal quality analysis, the pre-analysis result corresponding to the abnormal electrocardiosignal screening analysis and the pre-analysis result corresponding to the arrhythmia event analysis so as to obtain a target analysis result corresponding to each section of the electrocardio data segment.
As the method described above, the waveform signal quality analysis includes:
judging lead falling and judging signal noise;
the analyzing and processing of each section of the electrocardiogram data segment according to the waveform signal quality analysis to obtain a pre-analysis result corresponding to the waveform signal quality analysis comprises the following steps:
judging whether the electrocardiogram data segments have lead falling according to the lead falling;
if the judgment result is yes, determining the analysis result corresponding to the lead falling judgment as a pre-analysis result corresponding to the waveform signal quality analysis;
if the judgment result is negative, judging and analyzing each section of the electrocardiogram data segment according to signal noise, and determining an analysis result corresponding to the signal noise judgment as a pre-analysis result corresponding to the waveform signal quality analysis.
According to the method, the target analysis result with the largest numerical value is selected from the target analysis results of the electrocardio data segments; determining the electrocardiogram data segment corresponding to the target analysis result with the maximum value as the electrocardiogram data segment corresponding to the optimal target analysis result, wherein the electrocardiogram data segment comprises:
carrying out N-1 rounds of comparison on target analysis results corresponding to the electrocardio data segments;
aiming at the jth round, comparing a target analysis result corresponding to the comparison result of the jth round-1 with a target analysis result corresponding to the ith section of the electrocardiogram data segment, and selecting the electrocardiogram data segment corresponding to the target analysis result with a larger numerical value as the jth round comparison result, wherein i is a positive integer from 1 to N, j is a positive integer from 1 to N-1, j is i-1, and the 0 th round comparison result is the 1 st section of the electrocardiogram data segment;
and determining the comparison result of the (N-1) th round as the electrocardiogram data segment corresponding to the optimal target analysis result.
After comparing the target analysis result corresponding to the comparison result of the j-1 th round with the target analysis result corresponding to the ith segment of the electrocardiographic data, the method further includes:
when the values of the target analysis result corresponding to the comparison result of the j-1 th round are equivalent to the values of the target analysis result corresponding to the i-th section of the electrocardiogram data segment, comparing the pre-analysis result corresponding to the comparison result of the j-1 th round with the pre-analysis result corresponding to the i-th section of the electrocardiogram data segment;
and selecting the electrocardiogram data segment corresponding to the pre-analysis result with a larger value as the jth round of comparison result.
The method for comparing the pre-analysis result corresponding to the j-1 th round of comparison result with the pre-analysis result corresponding to the ith section of electrocardiogram data segment includes:
determining the priority of a pre-analysis result corresponding to a preset analysis strategy according to the priority of the preset analysis strategy;
comparing the pre-analysis result with higher priority corresponding to the comparison result of the j-1 th round with the pre-analysis result with higher priority corresponding to the section i of the electrocardiogram data segment;
and when the numerical values of the pre-analysis result with higher priority corresponding to the comparison result of the j-1 th round are equivalent to the numerical values of the pre-analysis result with higher priority corresponding to the i-th section of the electrocardiogram data segment, comparing the pre-analysis result with lower priority corresponding to the comparison result of the j-1 th round with the pre-analysis result with lower priority corresponding to the i-th section of the electrocardiogram data segment.
After the generating the target electrocardiographic waveform according to the electrocardiographic data segment corresponding to the optimal target analysis result, the method further includes:
when an arrhythmia event exists in the target electrocardiogram waveform, popping up prompt information, wherein the prompt information is used for prompting a user to detect the arrhythmia event and to prolong and print a rhythm electrocardiogram report;
acquiring a time-delay printing selection of a user;
and when the delayed printing is selected to start the delayed printing, the rhythm electrocardio report is printed at the delayed set time.
After the generating the target electrocardiographic waveform according to the electrocardiographic data segment corresponding to the optimal target analysis result, the method further includes:
acquiring a system printing report corresponding to the target electrocardiogram waveform and printing reports of other electrocardiogram waveforms;
and correcting the target analysis result corresponding to the electrocardiogram data segment according to the comparison result of the system print report corresponding to the target electrocardiogram waveform and the print reports of other electrocardiogram waveforms.
The method for correcting the target analysis result corresponding to the electrocardiographic data segment according to the comparison result between the system print report corresponding to the target electrocardiographic waveform and the print reports of other electrocardiographic waveforms includes:
extracting a first pre-analysis result in a system printing report of the target electrocardiogram waveform, wherein the first pre-analysis result is an analysis result obtained by analyzing and processing the target electrocardiogram fragment by using a preset analysis strategy;
extracting a second pre-analysis result in the printing report of the other electrocardiographic waveforms, wherein the second pre-analysis result is an analysis result obtained by analyzing and processing electrocardiographic segments corresponding to the other electrocardiographic waveforms by using a preset analysis strategy;
comparing the first pre-analysis result with the second pre-analysis result;
and when the first pre-analysis result is smaller than the second pre-analysis result, modifying the weight of a preset analysis strategy so as to modify a target analysis result corresponding to the electrocardiogram data segment.
In order to achieve the above object, a second embodiment of the present invention provides an electrocardiographic data segmentation apparatus, including:
the acquisition module is used for acquiring original electrocardiogram data;
the segmentation module is used for carrying out segmentation processing on the original electrocardiogram data to obtain N segments of electrocardiogram data, wherein N is a positive integer;
the processing module is used for analyzing and processing each section of the electrocardiogram data fragments by adopting at least one preset analysis strategy to obtain at least one analysis result of each section of the electrocardiogram data, and different preset analysis strategies correspond to different analysis results;
the judging module is used for comprehensively judging at least one analysis result of each section of the electrocardiogram data fragments so as to obtain the electrocardiogram data fragments corresponding to the optimal target analysis result;
and the generating module is used for generating a target electrocardiogram waveform according to the electrocardiogram data segment corresponding to the optimal target analysis result.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a method for selecting cardiac electrical data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating an exemplary generation of a target analysis result corresponding to an electrocardiogram data segment according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for selecting cardiac electrical data according to another embodiment of the present invention;
FIG. 4 is a schematic diagram of comparing segments of ECG data to determine a target ECG data segment according to an exemplary embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electrocardiographic data segmentation apparatus according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The following describes an electrocardiographic data segmentation method and device according to an embodiment of the present invention with reference to the drawings.
Fig. 1 is a flowchart of an electrocardiographic data segmentation method according to an embodiment of the present invention. As shown in fig. 1, the method for selecting electrocardiographic data according to this embodiment includes:
and S101, acquiring original electrocardiogram data.
Specifically, the electrocardiograph is started, and the electrocardiograph automatically executes an initialization command; the electrocardiograph receives the acquisition command, acquires and stores original electrocardiographic data according to the set sampling time T; for example, the set sampling time is a multiple of 10 seconds; the sampling time may also be chosen to be some default value.
Step S102, carrying out segmentation processing on the original electrocardiogram data to obtain N segments of electrocardiogram data fragments, wherein N is a positive integer.
Specifically, the implementation manner of step S102 is: and carrying out segmentation processing on the original electrocardiogram data to obtain N segments of electrocardiogram data fragments, and marking the ith segment of electrocardiogram data fragment, wherein i is a positive integer from 1 to N, and N is a positive integer.
Specifically, the system starts a data analysis module, and performs segmentation processing and marking on the acquired original electrocardiographic data. For example, the original electrocardiographic data with the duration of 20 seconds is segmented every 2.5 seconds from the acquisition starting time and sequentially marked, and the segments are respectively a 1 st electrocardiographic data segment, a2 nd electrocardiographic data segment, a3 rd electrocardiographic data segment, a 4 th electrocardiographic data segment, a 5 th electrocardiographic data segment, a 6 th electrocardiographic data segment, a 7 th electrocardiographic data segment and an 8 th electrocardiographic data segment.
Step S103, analyzing each section of the electrocardiogram data fragments by adopting at least one preset analysis strategy to obtain at least one pre-analysis result of each section of the electrocardiogram data, wherein different preset analysis strategies correspond to different pre-analysis results.
Specifically, the preset analysis strategy includes, but is not limited to, waveform signal quality analysis, abnormal cardiac signal screening analysis, and arrhythmia event analysis. For example, the total waveform signal quality result Q of each segment of the electrocardiographic data segment can be obtained by analyzing the waveform signal quality of each segment of the electrocardiographic data segment; for example, abnormal electrocardiosignal screening analysis is performed on each section of electrocardio data segment to obtain an abnormal electrocardiosignal screening result P of each section of electrocardio data segment; for example, arrhythmia event analysis is performed on each segment of electrocardiographic data segment, so that arrhythmia event result a of each segment of electrocardiographic data segment can be obtained.
For example, the waveform signal quality analysis mainly includes lead drop judgment and signal noise judgment, and the priority of the lead drop judgment in the analysis is higher than that of the signal noise judgment; the total waveform signal quality result Q has three gears which are respectively 0, 5 and 10; specifically, the total waveform signal quality result Q is obtained according to the result of the lead drop judgment and the result of the signal noise judgment, when the lead drop judgment result is 0, the total waveform signal quality result Q is 0, and the signal noise judgment is not performed; when the lead falling judgment result is 10 and the signal noise judgment result of the main lead is 0, the quality result Q of the main waveform signal is 0; when the lead falling result is 10 and the signal noise judgment result of the total lead is 5, the quality result Q of the total waveform signal is 5; when the lead drop result is 10 and the signal noise judgment result of the total lead is 10, the total waveform signal quality result Q is 10.
Wherein, the lead falling judgment is to detect whether each lead of each section of the electrocardiographic waveform has an electrocardiographic signal. The electrocardiosignal judgment method comprises the following steps: whether the signal characteristics of the P-QRS-T wave group exist in the electrocardiosignals or not; if judging that one or more leads fall off, directly endowing the gear value of the total waveform signal quality result Q with 0, and not judging signal noise; when there is no lead drop, the judgment result given by the lead drop judgment is 10.
Wherein the signal noise determination includes but is not limited to: baseline drift interference, power frequency interference and myoelectric interference; judging each interference condition of each branch lead of the electrocardiogram fragment, and giving a judgment result; the judgment result is divided into three gears which are respectively 0, 5 and 10; respectively representing strong interference, medium interference and weak interference; when any strong interference exists in the baseline wandering interference, the power frequency interference and the myoelectric interference, the judgment result of the signal noise of the branch lead is 0, and when the baseline wandering interference, the power frequency interference and the myoelectric interference are weak, the judgment result of the signal noise of the branch lead is 10; when any one or more of baseline wandering interference, power frequency interference and myoelectric interference is medium, judging that the result of the branch lead is 5; when more than half of the branch lead signal noise judgment results in all the branch leads are 0, judging the signal noise judgment result of the main lead to be 0; when the signal noise judgment results of all the branch leads are 10, judging the signal noise judgment result of the main lead to be 10; and when one or more than one of all the partial leads and less than half of the partial lead signal noise judgment results are 5, judging the signal noise judgment result of the total lead to be 5.
For example, the abnormal electrocardiosignal screening and analyzing is to analyze the electrocardio waveform in each segment according to preset electrocardio parameter values and give an analysis result; the abnormal electrocardiosignal screening result P has three gears which are respectively 15, 30 and 45;
the preset values of the various electrocardiographic parameters include but are not limited to: characteristic values of the P-QRS-T wave group of the electrocardiographic wave; p-wave amplitude and time limit: amplitude and timing of P-A and P-T, QRS wave groups: amplitude and timing of QRS-A and QRS-T, T waves: T-A and T-T, PR intervals: PR, QT interval: QT.
The characteristic value of each electrocardiographic waveform comprises two threshold values, namely a threshold value 1 and a threshold value 2, wherein the threshold value 2 is greater than the threshold value 1; taking the P-wave time limit PA as an example, carrying out threshold judgment analysis on the PA to obtain three results in total, wherein the three results are marked as 10 when the three results are smaller than the PA threshold value 1; greater than or equal to PA threshold 1 is less than PA threshold 2, labeled 5; greater than or equal to PA threshold 2, marked as 0; meanwhile, threshold judgment and analysis are carried out on parameters such as PA, PT, QRS-A, QRS-T, TA, TT, PR, QT and the like;
when one or more characteristic values are marked as 0 in all the characteristic value judgments, judging that the abnormal electrocardiosignal screening result P is 45; when the results given in all the characteristic value judgments are 10, judging that the abnormal electrocardiosignal screening result P is 15; when the judgment result of one or more characteristic values is 5, but the judgment result of the absence of the characteristic values is 0, the abnormal electrocardiosignal screening result P is judged to be 30.
In a preferred embodiment, when the threshold value of the abnormal waveform is judged, the specific threshold value judgment is carried out according to the age of the current patient; divided into children and adults according to age; wherein the children are 0-16 years old and the adults are over 16 years old; when the current patient is judged to be a child, the threshold values 1 and 2 of all the items are judged according to the child standard; when the current patient is judged to be an adult, the threshold value 1 and the threshold value 2 of each item are judged according to adult standards.
For example, arrhythmia event analysis refers to performing arrhythmia event detection analysis on waveforms in the electrocardiograph data segment, and giving out an analysis result; wherein, the arrhythmia event result A has four gears which are respectively 0, 20, 40 and 60;
table 1 is a list of arrhythmic events. In table 1, there are three levels of arrhythmic events, D1, D2, and D3. It is noted that arrhythmic events include, but are not limited to, the arrhythmic events listed in table 1. The arrhythmia event can be automatically analyzed by an electrocardiograph, and the arrhythmia event is only used as intermediate data of the patent and is used as one of input interfaces for selecting target electrocardiogram data segments.
If any arrhythmia event does not exist in the electrocardiogram data segment, judging that an arrhythmia event result A is 0; when a D1-level arrhythmia event exists in the electrocardiogram data segment, judging that the arrhythmia event result A is 20; when a D2-grade arrhythmia event exists in the electrocardiogram data segment, judging that the arrhythmia event result A is 40; when any one of the following situations appears in the electrocardiogram data segment: there are multiple class D2 arrhythmia events; the presence of one or more class D3 arrhythmia events; both class D2 and D3 arrhythmic events; then the arrhythmic event outcome a is determined to be 60.
TABLE 1
Figure BDA0001469771520000081
And S104, comprehensively judging at least one pre-analysis result of each section of the electrocardiogram data segments to obtain the electrocardiogram data segment corresponding to the optimal target analysis result.
For example, the at least one preset analysis strategy is respectively waveform signal quality analysis, abnormal electrocardiosignal screening analysis and arrhythmia event analysis, and accordingly, each section of the electrocardio data has three pre-analysis results, namely an analysis result corresponding to the waveform signal quality analysis, an analysis result corresponding to the abnormal electrocardiosignal screening analysis and an analysis result corresponding to the arrhythmia event analysis. Specifically, different preset analysis strategies and the number of the preset analysis strategies are selected according to actual conditions.
Fig. 2 is a schematic diagram of an exemplary target analysis result corresponding to the generated electrocardiographic data segment according to the embodiment of the present invention. As shown in fig. 2, the pre-analysis results of the ith segment of electrocardiographic data are respectively: and if the total waveform signal quality result Qi, the abnormal electrocardiosignal screening result Pi and the arrhythmia event result Ai are obtained, the target analysis result Ri of the ith section of the electrocardio data segment is Qi + Pi + Ai.
For example, three preset analysis strategies are adopted to analyze and process each section of electrocardiogram data segment, so that three pre-analysis results are obtained. And performing data fusion on the three pre-analysis results according to a preset algorithm to obtain a target analysis result of each section of the electrocardiogram data segment. As shown in fig. 2, three pre-analysis results are directly analyzed to obtain a target analysis result. Or, according to different weights of the preset analysis strategies, a weighting algorithm is adopted to perform data fusion on the three pre-analysis results to obtain a target analysis result, and then the reference value of the target analysis result is improved.
Preferably, a weighting algorithm is adopted to perform data fusion on at least one pre-analysis result to obtain a target analysis result, so that the reference value of the target analysis result is improved. The weight of each pre-analysis result is related to the weight of the corresponding pre-analysis strategy, and the weight of the pre-analysis strategy is flexibly adjusted according to the actual situation.
And S105, generating a target electrocardiogram waveform according to the electrocardiogram data segment corresponding to the optimal target analysis result.
For example, the 4 th electrocardiographic data segment is screened as the electrocardiographic data segment corresponding to the optimal target analysis result through comparison, the time length of the target electrocardiographic waveform which is actually expected to be output is 10 seconds, at this time, a plurality of electrocardiographic data segments are selected from the electrocardiographic data segments adjacent to the label of the 4 th electrocardiographic data segment, and the electrocardiographic data segments and the 4 th electrocardiographic data segment form the target electrocardiographic waveform with the time length of 10 seconds, for example, the target electrocardiographic waveform with the time length of 10 seconds is obtained by simultaneously selecting the first 1 electrocardiographic data segment and the last 2 electrocardiographic data segments of the 4 th electrocardiographic data segment.
It should be noted that the plurality of electrocardiographic data segments adjacent to the electrocardiographic data segment corresponding to the optimal target analysis result are screened out according to actual cleaning setting. For example, if the index of the electrocardiographic data segment corresponding to the optimal target analysis result is the ith segment, the (i-1) th segment, the (i + 2) th segment and the like are taken as defaults, that is, 1 electrocardiographic data segment is taken forward and a plurality of electrocardiographic data segments are taken backward in sequence to obtain the target electrocardiographic waveform. And if the label of the electrocardiogram data segment corresponding to the optimal target analysis result is the 1 st segment, sequentially taking a plurality of electrocardiogram data segments backwards to make up the target electrocardiogram waveform with the target waveform duration.
It should be noted that the target electrocardiographic waveform screened from the raw electrocardiographic data can be displayed, analyzed and printed. Taking the system as an electrocardiograph as an example, after the system screens out a target electrocardiographic waveform for 10 seconds, marking the initial position of the target electrocardiographic waveform; automatically taking the 10s target electrocardiographic waveform to display on a screen display interface, and calling a built-in automatic analysis algorithm to measure, diagnose and analyze the 10s target electrocardiographic waveform; and after the diagnosis is confirmed, automatically printing an electrocardio analysis report of the target electrocardio waveform.
It should be noted that the electrocardiographic data segments that are not filtered from the original electrocardiographic data can be played back or called by a system such as an electrocardiograph.
As a preferred embodiment, after generating the target electrocardiographic waveform according to the electrocardiographic data segment corresponding to the optimal target analysis result, the method further includes: recording the initial position of the target electrocardiogram waveform in the original electrocardiogram data; and (5) calling back and displaying the target electrocardiographic waveform according to the starting position. Taking the system as an electrocardiograph as an example, after the system screens out a target electrocardiographic waveform of 10 seconds, the system needs to memorize the mark of the initial position in the stored data, and when the data is called out next time, the target electrocardiographic waveform of 10 seconds is still displayed.
As a preferred embodiment, after generating the target electrocardiographic waveform according to the electrocardiographic data segment corresponding to the optimal target analysis result, the method further includes: when an arrhythmia event exists in the target electrocardiogram waveform, popping up prompt information, wherein the prompt information is used for prompting a user to detect the arrhythmia event and to prolong and print a rhythm electrocardiogram report; acquiring a time-delay printing selection of a user; and when the delayed printing is selected to start the delayed printing, the rhythm electrocardio report is printed at the delayed set time.
Taking the system as an electrocardiograph as an example, after the system screens out a target electrocardiographic waveform for 10 seconds, if an arrhythmia event exists in the target electrocardiographic waveform, namely the value of an arrhythmia event result A is not 0, the system supports the function of prolonging the printing of the rhythmic electrocardio, at the moment, the system needs to pop up a prompt box to prompt a user to detect the arrhythmia event and to judge whether to prolong the printing of a set of rhythmic electrocardio, and if the user manually selects yes, the system starts one-time prolonged printing, namely a rhythm electrocardio report with fixed default duration is continuously printed after the set sampling time T; if the user selects no manually, the system abandons the operation of prolonging the printing rhythm electrocardio.
As a preferred embodiment, after generating the target electrocardiographic waveform according to the electrocardiographic data segment corresponding to the optimal target analysis result, the method further includes: acquiring a system printing report corresponding to the target electrocardiogram waveform and printing reports of other electrocardiogram waveforms; and correcting the target analysis result corresponding to the electrocardiogram data segment according to the comparison result of the system print report corresponding to the target electrocardiogram waveform and the print reports of other electrocardiogram waveforms.
Taking the system as an electrocardiograph as an example, after the system screens out a target electrocardiographic waveform for 10 seconds, a user is required to confirm the waveform and print a report, and a feedback mechanism exists in the process; the feedback mechanism is that after the system automatically screens the target electrocardiogram waveform and presents the target electrocardiogram waveform to the user, the user confirms the process, if the user confirms that the target electrocardiogram waveform automatically screened by the printing system is selected, the system returns a null value, at the moment, the system can restart to execute the step of acquiring the original electrocardiogram data, and when the next sampling and screening process is started, the target electrocardiogram waveform is automatically selected according to the judgment mechanism in the current system.
If the user does not print the target electrocardiogram waveform of 10 seconds automatically screened by the system, other electrocardiogram waveforms with the duration of 10 seconds are manually selected for printing; the system starts a one-time feedback mechanism to require the system to automatically judge and compare each first pre-analysis result of the 10-second target electrocardiographic waveform automatically selected by the system with each second pre-analysis result of each electrocardiographic data segment in other electrocardiographic waveforms with the printing time length of 10 seconds selected by the user one by one. The numerical value increase of each feedback is memorized and accumulated, in the continuous feedback modification process, the numerical value increase can be continuously close to the professional judgment standard of the user, in the continuous feedback modification process, the actual clinical requirement of the personalized judgment of the user is completed, and a doctor is helped to more quickly and accurately screen the target electrocardiographic waveform.
In a possible implementation manner, the specific implementation manner of correcting the target analysis result corresponding to the electrocardiographic data segment according to the comparison result between the system print report corresponding to the target electrocardiographic waveform and the print reports of other electrocardiographic waveforms includes:
extracting a first pre-analysis result in a system printing report of the target electrocardiogram waveform, wherein the first pre-analysis result is an analysis result obtained by analyzing and processing the target electrocardiogram fragment by using a preset analysis strategy;
extracting a second pre-analysis result in the printing report of the other electrocardiographic waveforms, wherein the second pre-analysis result is an analysis result obtained by analyzing and processing electrocardiographic segments corresponding to the other electrocardiographic waveforms by using a preset analysis strategy;
comparing the first pre-analysis result with the second pre-analysis result;
and when the first pre-analysis result is smaller than the second pre-analysis result, modifying the weight of a preset analysis strategy so as to modify a target analysis result corresponding to the electrocardiogram data segment.
Taking the example that three pre-analysis results are obtained by analyzing and processing each section of electrocardiogram data fragments by adopting three preset analysis strategies, wherein three first pre-analysis results of a 10-second target electrocardiogram waveform are respectively a total waveform signal quality result Qs, an abnormal electrocardiogram signal screening result Ps and an arrhythmia event result As; meanwhile, the three second pre-analysis results of other 10-second electrocardiographic waveforms are respectively a total waveform signal quality result Qm, an abnormal electrocardiographic signal screening result Pm and an arrhythmia event result Am.
If Qm is greater than Qs and Pm < Ps and Am > As, the system feedback signal is a signal quality result adjustment command, and when the next sampling judgment screening is started, the system needs to increase the weight of a waveform signal quality analysis strategy, namely, the weight of the total waveform signal quality result Q in a generated target analysis result is adjusted, namely, the importance degree of the total waveform signal quality result Q in automatic screening is increased.
If Qm < Qs and Pm > Ps and Am < As, the system feedback signal is an abnormal electrocardiosignal screening result adjusting command, when the next sampling judgment screening is started, the system needs to increase the weight of the abnormal electrocardiosignal screening analysis, namely, the weight of the abnormal electrocardiosignal screening result P in the generated target analysis result is adjusted, namely, the importance degree of the abnormal electrocardiosignal screening result P in automatic screening is increased.
If Qm < Qs and Pm < Ps and Am > As, the system feedback signal is an arrhythmia event result adjustment command, and when the next sampling judgment screening is started, the system needs to increase the weight of arrhythmia event analysis, namely, the weight of arrhythmia event result A in the generated target analysis result is adjusted, namely, the importance degree of arrhythmia event A in automatic screening is increased.
In the method for selecting the electrocardiographic data, the original electrocardiographic data is obtained; carrying out segmentation processing on the original electrocardiogram data to obtain N segments of electrocardiogram data fragments, wherein N is a positive integer; analyzing each section of the electrocardiogram data fragments by adopting at least one preset analysis strategy to obtain at least one pre-analysis result of each section of the electrocardiogram data, wherein different preset analysis strategies correspond to different pre-analysis results; comprehensively judging at least one pre-analysis result of each section of the electrocardiogram data segments to obtain the electrocardiogram data segments corresponding to the optimal target analysis result; and generating a target electrocardiogram waveform according to the electrocardiogram data segment corresponding to the optimal target analysis result. According to the method, various different preset analysis strategies are utilized to analyze each section of the electrocardiogram data segments, and a plurality of pre-analysis results of each section of the electrocardiogram data segments are comprehensively judged to select the electrocardiogram data segment corresponding to the optimal target analysis result, so that a target electrocardiogram waveform capable of reflecting the real state of an illness of a patient is obtained, an accurate diagnosis result is obtained based on the target electrocardiogram waveform subsequently, and the risk of misdiagnosis or missed diagnosis is reduced as much as possible.
Fig. 3 is a flowchart of a method for selecting cardiac electrical data according to another embodiment of the present invention. On the basis of the above embodiment, the step of "comprehensively judging at least one analysis result of each segment of the electrocardiographic data segment to obtain an electrocardiographic data segment corresponding to an optimal target analysis result" is optimized to "perform weighted summation on at least one analysis result of each segment of the electrocardiographic data segment to obtain a target analysis result of each segment of the electrocardiographic data segment; and selecting a target analysis result with the largest value from the target analysis results of all the sections of the electrocardiogram data segments, and determining the electrocardiogram segment corresponding to the target analysis result with the largest value as the electrocardiogram data segment corresponding to the optimal target analysis result. "
As shown in fig. 3, the method for selecting electrocardiographic data according to this embodiment includes:
step S201, obtaining original electrocardiogram data.
Step S202, carrying out segmentation processing on the original electrocardiogram data to obtain N segments of electrocardiogram data fragments, wherein N is a positive integer.
Step S203, analyzing each section of the electrocardiogram data fragments by adopting at least one preset analysis strategy to obtain at least one pre-analysis result of each section of the electrocardiogram data, wherein different preset analysis strategies correspond to different analysis results.
The implementation manners of steps S201, S202, and S203 in this embodiment are the same as the implementation manners of steps S101, S102, and S103 in the above embodiment, and are not described herein again.
Step S204, carrying out weighted summation on at least one analysis result of each section of the electrocardiogram data fragments to obtain a target analysis result of each section of the electrocardiogram data fragments.
Specifically, a weighting algorithm is adopted to perform data fusion on at least one pre-analysis result to obtain a target analysis result, so that the reference value of the target analysis result can be improved. The weight of each pre-analysis result is related to the weight of the corresponding pre-analysis strategy, and the weight of the pre-analysis strategy is flexibly adjusted according to the actual situation.
For example, the pre-analysis results of the ith segment of electrocardiographic data are respectively: and if the total waveform signal quality result Qi, the abnormal electrocardiosignal screening result Pi and the arrhythmia event result Ai are obtained, the target analysis result Ri of the ith section of the electrocardio data segment is alpha Qi + beta Pi + epsilon Ai, wherein alpha is the weight of the total waveform signal quality result, beta is the weight of the abnormal electrocardiosignal screening result and epsilon is the weight of the arrhythmia event result.
The following describes in detail at least one preset analysis strategy as waveform signal quality analysis, abnormal electrocardiosignal screening analysis, and arrhythmia event analysis, respectively.
Specifically, when at least one preset analysis strategy is waveform signal quality analysis, abnormal electrocardiosignal screening analysis, and arrhythmia event analysis, the process of obtaining the target analysis result corresponding to each segment of the electrocardiographic data segment is as follows:
the first step is as follows: and acquiring an execution sequence corresponding to a preset analysis strategy, wherein the execution sequence comprises synchronous execution or asynchronous execution. It should be noted that, the execution sequence including synchronous execution or asynchronous execution may be understood as that the second step, the third step, and the fourth step are executed simultaneously or in a preset sequence, and is not limited herein.
The second step is that: and analyzing and processing each section of the electrocardiogram data segment according to the waveform signal quality analysis based on the execution sequence to obtain a pre-analysis result corresponding to the waveform signal quality analysis.
The third step: and analyzing and processing each section of the electrocardiogram data fragments according to abnormal electrocardiogram signal screening analysis based on the execution sequence to obtain a pre-analysis result corresponding to the abnormal electrocardiogram signal screening analysis.
The fourth step: and analyzing and processing each section of the electrocardiogram data fragments according to arrhythmia event analysis based on the execution sequence to obtain a pre-analysis result corresponding to the arrhythmia event analysis.
The fifth step: and carrying out weighted summation on the pre-analysis result corresponding to the waveform signal quality analysis, the pre-analysis result corresponding to the abnormal electrocardiosignal screening analysis and the pre-analysis result corresponding to the arrhythmia event analysis so as to obtain a target analysis result corresponding to each section of the electrocardio data segment.
Preferably, the waveform signal quality analysis comprises: judging lead falling and judging signal noise;
then, the analyzing and processing each segment of the electrocardiographic data segment according to the waveform signal quality analysis to obtain a pre-analysis result corresponding to the waveform signal quality analysis includes:
judging whether the electrocardiogram data segments have lead falling according to the lead falling;
if the judgment result is yes, determining the analysis result corresponding to the lead falling judgment as a pre-analysis result corresponding to the waveform signal quality analysis;
if the judgment result is negative, judging and analyzing each section of the electrocardiogram data segment according to signal noise, and determining an analysis result corresponding to the signal noise judgment as a pre-analysis result corresponding to the waveform signal quality analysis.
Step S205, selecting a target analysis result with the largest numerical value from the target analysis results of the electrocardiographic data segments, and determining the electrocardiographic segment corresponding to the target analysis result with the largest numerical value as the electrocardiographic data segment corresponding to the optimal target analysis result.
Specifically, after the target analysis result of each segment of the electrocardiographic data is obtained, the optimal target analysis result may be obtained through a numerical comparison method, but the method is not limited thereto.
In a possible implementation manner, the specific implementation manner of step S205 is:
and S1, performing N-1 round comparison on the target analysis results corresponding to the electrocardio data segments.
And S2, determining the comparison result of the (N-1) th round as the electrocardiogram data segment corresponding to the optimal target analysis result.
Fig. 4 is a schematic diagram of comparing segments of electrocardiographic data to determine a target electrocardiographic data segment according to an exemplary embodiment of the present invention. It should be noted that, in this embodiment, taking whether the 1 st segment of electrocardiographic data is better than the 2 nd segment of electrocardiographic data in fig. 4 as an example, whether the 1 st segment of electrocardiographic data is better than the 2 nd segment of electrocardiographic data means whether the value of the target analysis result of the 1 st segment of electrocardiographic data is greater than the value of the target analysis result of the 2 nd segment of electrocardiographic data. When the 1 st section of the electrocardiogram data segment is superior to the 2 nd section of the electrocardiogram data segment, taking the 1 st section of the electrocardiogram data segment as a reference means that the 1 st section of the electrocardiogram data segment is taken as a current comparison result;
when the 1 st section of the electrocardiogram data segment is not superior to the 2 nd section of the electrocardiogram data segment, the 2 nd section of the electrocardiogram data segment is taken as a reference, namely the 2 nd section of the electrocardiogram data segment is taken as a current comparison result.
Specifically, in this embodiment, two-by-two comparison is performed one by one starting from the 1 st electrocardiographic data segment according to the label of the electrocardiographic data segment, and the result of the previous comparison is used as the reference of the next part. When the original electrocardiogram data is divided into N segments of electrocardiogram data fragments, comparison is needed for N-1 times, and the last comparison result, namely the comparison result of the (N-1) th round, is determined as the electrocardiogram data fragment corresponding to the optimal target analysis result.
Taking the example that the original electrocardiographic data is divided into the 1 st electrocardiographic data segment, the 2 nd electrocardiographic data segment, the 3 rd electrocardiographic data segment and the 4 th electrocardiographic data segment, firstly, the 1 st electrocardiographic data segment is taken as the 0 th round of comparison result; performing the 1 st round of comparison, comparing the 0 th round of comparison result with the value of the target analysis result corresponding to the 2 nd section of the electrocardiogram data segment, and if the value of the 0 th round of comparison result is large, determining the 1 st section of the electrocardiogram data segment as the 1 st round of comparison result; if the target analysis result corresponding to the 2 nd section of the electrocardiogram data segment is large, determining the 2 nd section of the electrocardiogram data segment as a 1 st round comparison result; performing 2 nd round comparison (taking the 1 st round comparison result as the 2 nd section of electrocardiogram data as an example), comparing the 1 st round comparison result with the 3 rd section of electrocardiogram data corresponding to the target analysis result, and if the 1 st round comparison result is large, determining the 2 nd section of electrocardiogram data as the 2 nd round comparison result; and if the target analysis result corresponding to the 3 rd section of the electrocardiogram data segment is large, determining the 3 rd section of the electrocardiogram data segment as the 2 nd round comparison result. By analogy, when the 3 rd round of comparison is carried out, the electrocardiogram data segment corresponding to the target analysis result with a larger value can be determined from the 2 nd round of comparison result and the 4 th section of electrocardiogram data segment.
Specifically, for the jth round, the target analysis result corresponding to the comparison result of the jth-1 round is compared with the target analysis result corresponding to the ith section of the electrocardiographic data segment, and the electrocardiographic data segment corresponding to the target analysis result with a larger value is selected as the jth round comparison result, wherein i is a positive integer from 1 to N, j is a positive integer from 1 to N-1, j is i-1, and the 0 th round comparison result is the 1 st section of the electrocardiographic data segment.
Further, in a possible implementation manner, after comparing the target analysis result corresponding to the comparison result of the j-1 th round with the target analysis result corresponding to the i-th segment of the electrocardiographic data, the method further includes: when the values of the target analysis result corresponding to the comparison result of the j-1 th round are equivalent to the values of the target analysis result corresponding to the i-th section of the electrocardiogram data segment, comparing the pre-analysis result corresponding to the comparison result of the j-1 th round with the pre-analysis result corresponding to the i-th section of the electrocardiogram data segment; and selecting the electrocardiogram data segment corresponding to the pre-analysis result with a larger value as the jth round of comparison result.
For example, when the 2 nd round of comparison is performed (taking the 1 st round of comparison result as the 2 nd segment of electrocardiographic data as an example), the value of the target analysis result R2 corresponding to the 2 nd segment of electrocardiographic data is equivalent to the value of the target analysis result R3 corresponding to the 3 rd segment of electrocardiographic data, at this time, the value of the pre-analysis result corresponding to the 2 nd segment of electrocardiographic data is compared with the value of the pre-analysis result corresponding to the 3 rd segment of electrocardiographic data, and the electrocardiographic data segment corresponding to the pre-analysis result with the larger value is taken as the comparison result of the current round.
In this embodiment, the same type of pre-analysis results of two electrocardiographic data segments are compared. If the pre-analysis results of the two electrocardiogram data segments are all equivalent, any one of the electrocardiogram data segments is selected as the current round of comparison results.
For the situation that the target analysis results of the two electrocardiographic data segments are equivalent, the embodiment also compares the pre-analysis results of the two electrocardiographic data segments of the same type, so as to ensure that the electrocardiographic data segment corresponding to the target analysis result is successfully and optimally determined.
In a possible implementation manner, the comparing the pre-analysis result corresponding to the comparison result of the j-1 th round with the pre-analysis result corresponding to the i-th section of the electrocardiographic data segment includes:
determining the priority of a pre-analysis result corresponding to a preset analysis strategy according to the priority of the preset analysis strategy;
comparing the pre-analysis result with higher priority corresponding to the comparison result of the j-1 th round with the pre-analysis result with higher priority corresponding to the section i of the electrocardiogram data segment;
and when the numerical values of the pre-analysis result with higher priority corresponding to the comparison result of the j-1 th round are equivalent to the numerical values of the pre-analysis result with higher priority corresponding to the i-th section of the electrocardiogram data segment, comparing the pre-analysis result with lower priority corresponding to the comparison result of the j-1 th round with the pre-analysis result with lower priority corresponding to the i-th section of the electrocardiogram data segment.
Taking the example that three pre-analysis results are obtained by analyzing and processing each section of electrocardio data segment by adopting three preset analysis strategies, wherein the three preset analysis strategies are respectively waveform signal quality analysis, abnormal electrocardio signal screening analysis and arrhythmia event analysis; the priority of the waveform signal quality analysis is lower than that of the abnormal electrocardiosignal screening analysis, and the priority of the abnormal electrocardiosignal screening analysis is lower than that of the arrhythmia event analysis; correspondingly, the priority of the total waveform signal quality result Q is lower than that of the abnormal electrocardiosignal screening result P, and the priority of the abnormal electrocardiosignal screening result P is lower than that of the arrhythmia event result A. According to the embodiment, the optimal electrocardiogram data segment corresponding to the target analysis result reflecting the real disease condition of the patient can be selected by determining the comparison sequence according to the pre-analysis result according to the priority of the preset analysis strategy.
Wherein, the target analysis result R2 corresponding to the 2 nd segment of the electrocardiographic data fragment, and the three pre-analysis results of the 2 nd segment of the electrocardiographic data fragment are respectively: a total waveform signal quality result Q2, an abnormal electrocardiosignal screening result P2 and an arrhythmia event result A2.
The corresponding target analysis result R3 of the 3 rd section of the electrocardiographic data segment and the three pre-analysis results of the 3 rd section of the electrocardiographic data segment are respectively as follows: a total waveform signal quality result Q3, an abnormal electrocardiosignal screening result P3 and an arrhythmia event result A3.
When making round 2 comparisons, R2 equals R3; at this time, according to the priority level, comparing the numerical values of A2 and A3, and if A2 is greater than A3, determining the 2 nd segment of electrocardiogram data segment as the result of the comparison; when A2 is equal to A3, the numerical values of P2 and P3 are compared; by analogy, when P2 is equal to P3, the values of Q2 and Q3 are compared.
And S206, generating a target electrocardiogram waveform according to the electrocardiogram data segment corresponding to the optimal target analysis result.
The implementation manner of step S206 in this embodiment is the same as the implementation manner of step S105 in the above embodiment, and is not described herein again.
According to the electrocardio data segment selection method provided by the embodiment of the invention, a weighting algorithm is adopted to perform data fusion on at least one pre-analysis result so as to obtain a target analysis result, so that the reference value of the target analysis result can be improved; the electrocardiogram data segments corresponding to the optimal target analysis result are selected through one-by-one comparison, and if the target analysis results of the two electrocardiogram data segments are equivalent in the successive comparison process, the electrocardiogram data segments corresponding to the optimal target analysis result are successfully screened out through comparing the pre-analysis results of the two electrocardiogram data segments of the same type. In addition, the sequence of comparison according to the pre-analysis results is determined according to the priority of the preset analysis strategy, and the electrocardio data segment corresponding to the optimal target analysis result which reflects the real state of an illness of a patient can be selected, so that the target electrocardio waveform which can better reflect the real state of the illness of the patient is obtained, the accurate diagnosis result is obtained based on the target electrocardio waveform subsequently, and the risk of misdiagnosis or missed diagnosis is reduced as much as possible.
Fig. 5 is a schematic structural diagram of an electrocardiographic data segmentation apparatus according to an embodiment of the present invention. As shown in fig. 5, the electrocardiographic data segmentation apparatus provided in the embodiment of the present invention includes:
the acquisition module 11 is used for acquiring original electrocardiogram data;
the segmentation module 12 is configured to perform segmentation processing on the original electrocardiographic data to obtain N segments of electrocardiographic data, where N is a positive integer;
the processing module 13 is configured to analyze and process each segment of the electrocardiographic data by using at least one preset analysis strategy, so as to obtain at least one analysis result of each segment of the electrocardiographic data, where different preset analysis strategies correspond to different analysis results;
the judging module 14 is configured to comprehensively judge at least one analysis result of each segment of the electrocardiographic data segment to obtain an electrocardiographic data segment corresponding to an optimal target analysis result;
and the generating module 15 is configured to generate a target electrocardiographic waveform according to the electrocardiographic data segment corresponding to the optimal target analysis result.
Further, the judging module 14 includes a summing unit, a selecting unit;
and the summation unit is used for carrying out weighted summation on at least one pre-analysis result of each section of the electrocardiogram data segments so as to obtain a target analysis result of each section of the electrocardiogram data segments.
And the selecting unit is used for selecting a target analysis result with the largest numerical value from the target analysis results of the electrocardio data segments, and determining the electrocardio segment corresponding to the target analysis result with the largest numerical value as the electrocardio data segment corresponding to the optimal target analysis result.
Further, the selection unit is specifically configured to perform N-1 round comparison on target analysis results corresponding to the electrocardiographic data segments; aiming at the jth round, comparing a target analysis result corresponding to the comparison result of the jth round-1 with a target analysis result corresponding to the ith section of the electrocardiogram data segment, and selecting the electrocardiogram data segment corresponding to the target analysis result with a larger numerical value as the jth round comparison result, wherein i is a positive integer from 1 to N, j is a positive integer from 1 to N-1, j is i-1, and the 0 th round comparison result is the 1 st section of the electrocardiogram data segment; and determining the comparison result of the (N-1) th round as the electrocardiogram data segment corresponding to the optimal target analysis result.
The specific manner in which the respective modules perform operations has been described in detail in relation to the apparatus in this embodiment, and will not be elaborated upon here.
The electrocardiographic data section selection device provided by the embodiment acquires original electrocardiographic data; carrying out segmentation processing on the original electrocardiogram data to obtain N segments of electrocardiogram data fragments, wherein N is a positive integer; analyzing each section of the electrocardiogram data fragments by adopting at least one preset analysis strategy to obtain at least one pre-analysis result of each section of the electrocardiogram data, wherein different preset analysis strategies correspond to different pre-analysis results; comprehensively judging at least one pre-analysis result of each section of the electrocardiogram data segments to obtain the electrocardiogram data segments corresponding to the optimal target analysis result; and generating a target electrocardiogram waveform according to the electrocardiogram data segment corresponding to the optimal target analysis result. The device analyzes each section of the electrocardiogram data segments by utilizing a plurality of different preset analysis strategies, comprehensively judges a plurality of pre-analysis results of each section of the electrocardiogram data segments to select the electrocardiogram data segments corresponding to the optimal target analysis result, thereby obtaining the target electrocardiogram waveform capable of reflecting the real state of an illness of a patient, further ensuring that an accurate diagnosis result is obtained based on the target electrocardiogram waveform subsequently, and reducing the risk of misdiagnosis or missed diagnosis as much as possible.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims (9)

1. A method for selecting electrocardiographic data segments, comprising:
acquiring original electrocardiogram data;
carrying out segmentation processing on the original electrocardiogram data to obtain N segments of electrocardiogram data fragments, wherein N is a positive integer;
analyzing each section of the electrocardiogram data fragments by adopting at least one preset analysis strategy to obtain at least one pre-analysis result of each section of the electrocardiogram data, wherein different preset analysis strategies correspond to different pre-analysis results; the at least one preset analysis strategy is respectively waveform signal quality analysis, abnormal electrocardiosignal screening analysis and arrhythmia event analysis;
comprehensively judging at least one pre-analysis result of each section of the electrocardiogram data segments to obtain the electrocardiogram data segments corresponding to the optimal target analysis result;
generating a target electrocardiogram waveform according to the electrocardiogram data segment corresponding to the optimal target analysis result;
the comprehensive judgment of at least one pre-analysis result of each section of the electrocardiogram data segment to obtain the electrocardiogram data segment corresponding to the optimal target analysis result comprises the following steps:
weighting and summing at least one pre-analysis result of each section of the electrocardiogram data segment to obtain a target analysis result of each section of the electrocardiogram data segment; acquiring an execution sequence corresponding to a preset analysis strategy, wherein the execution sequence comprises synchronous execution or asynchronous execution; the weighted summation of the at least one pre-analysis result of each section of the electrocardiogram data segment is performed to obtain a target analysis result of each section of the electrocardiogram data segment, and the weighted summation comprises the following steps: analyzing and processing each section of the electrocardiogram data segment according to waveform signal quality analysis based on the execution sequence to obtain a pre-analysis result corresponding to the waveform signal quality analysis; analyzing and processing each section of the electrocardiogram data fragments according to abnormal electrocardiogram signal screening analysis based on the execution sequence to obtain a pre-analysis result corresponding to the abnormal electrocardiogram signal screening analysis; analyzing and processing each section of the electrocardiogram data fragments according to arrhythmia event analysis based on the execution sequence to obtain a pre-analysis result corresponding to the arrhythmia event analysis; weighting and summing a pre-analysis result corresponding to the waveform signal quality analysis, a pre-analysis result corresponding to the abnormal electrocardiosignal screening analysis and a pre-analysis result corresponding to the arrhythmia event analysis to obtain a target analysis result corresponding to each section of the electrocardio data segment;
and selecting a target analysis result with the largest value from the target analysis results of all the sections of the electrocardiogram data segments, and determining the electrocardiogram segment corresponding to the target analysis result with the largest value as the electrocardiogram data segment corresponding to the optimal target analysis result.
2. The method of claim 1, wherein the waveform signal quality analysis comprises:
judging lead falling and judging signal noise;
the analyzing and processing of each section of the electrocardiogram data segment according to the waveform signal quality analysis to obtain a pre-analysis result corresponding to the waveform signal quality analysis comprises the following steps:
judging whether the electrocardiogram data segments have lead falling according to the lead falling;
if the judgment result is yes, determining the analysis result corresponding to the lead falling judgment as a pre-analysis result corresponding to the waveform signal quality analysis;
if the judgment result is negative, judging and analyzing each section of the electrocardiogram data segment according to signal noise, and determining an analysis result corresponding to the signal noise judgment as a pre-analysis result corresponding to the waveform signal quality analysis.
3. The method according to claim 1, wherein the target analysis result with the largest value is selected from the target analysis results of the electrocardiographic data segments; determining the electrocardiogram data segment corresponding to the target analysis result with the maximum value as the electrocardiogram data segment corresponding to the optimal target analysis result, wherein the electrocardiogram data segment comprises:
carrying out N-1 rounds of comparison on target analysis results corresponding to the electrocardio data segments;
aiming at the jth round, comparing a target analysis result corresponding to the comparison result of the jth-1 round with a target analysis result corresponding to the ith section of the electrocardiogram data segment, and selecting an electrocardiogram data segment corresponding to a target analysis result with a larger numerical value as the jth round comparison result, wherein i is a positive integer from 1 to N, j is a positive integer from 1 to N-1, and j = i-1, and the 0 th round comparison result is the 1 st section of the electrocardiogram data segment;
and determining the comparison result of the (N-1) th round as the electrocardiogram data segment corresponding to the optimal target analysis result.
4. The method as claimed in claim 3, wherein after comparing the target analysis result corresponding to the j-1 th round of comparison result with the target analysis result corresponding to the i-th segment of electrocardiographic data, the method further comprises:
when the values of the target analysis result corresponding to the comparison result of the j-1 th round are equivalent to the values of the target analysis result corresponding to the i-th section of the electrocardiogram data segment, comparing the pre-analysis result corresponding to the comparison result of the j-1 th round with the pre-analysis result corresponding to the i-th section of the electrocardiogram data segment;
and selecting the electrocardiogram data segment corresponding to the pre-analysis result with a larger value as the jth round of comparison result.
5. The method as claimed in claim 4, wherein the comparing the pre-analysis result corresponding to the j-1 th round of comparison result with the pre-analysis result corresponding to the i-th section of the electrocardiographic data segment comprises:
determining the priority of a pre-analysis result corresponding to a preset analysis strategy according to the priority of the preset analysis strategy;
comparing the pre-analysis result with higher priority corresponding to the comparison result of the j-1 th round with the pre-analysis result with higher priority corresponding to the section i of the electrocardiogram data segment;
and when the numerical values of the pre-analysis result with higher priority corresponding to the comparison result of the j-1 th round are equivalent to the numerical values of the pre-analysis result with higher priority corresponding to the i-th section of the electrocardiogram data segment, comparing the pre-analysis result with lower priority corresponding to the comparison result of the j-1 th round with the pre-analysis result with lower priority corresponding to the i-th section of the electrocardiogram data segment.
6. The method of claim 1, further comprising, after generating a target electrocardiographic waveform from the corresponding electrocardiographic data segment of the optimal target analysis result:
when an arrhythmia event exists in the target electrocardiogram waveform, popping up prompt information, wherein the prompt information is used for prompting a user to detect the arrhythmia event and to prolong and print a rhythm electrocardiogram report;
acquiring a time-delay printing selection of a user;
and when the delayed printing is selected to start the delayed printing, the rhythm electrocardio report is printed at the delayed set time.
7. The method of claim 1, further comprising, after generating a target electrocardiographic waveform from the corresponding electrocardiographic data segment of the optimal target analysis result:
acquiring a system printing report corresponding to the target electrocardiogram waveform and printing reports of other electrocardiogram waveforms;
and correcting the target analysis result corresponding to the electrocardiogram data segment according to the comparison result of the system print report corresponding to the target electrocardiogram waveform and the print reports of other electrocardiogram waveforms.
8. The method of claim 7, wherein modifying the target analysis result corresponding to the electrocardiographic data segment based on the comparison of the system printed report corresponding to the target electrocardiographic waveform to the printed reports of other electrocardiographic waveforms comprises:
extracting a first pre-analysis result in a system printing report of the target electrocardiogram waveform, wherein the first pre-analysis result is an analysis result obtained by analyzing and processing the target electrocardiogram fragment by using a preset analysis strategy;
extracting a second pre-analysis result in the printing report of the other electrocardiographic waveforms, wherein the second pre-analysis result is an analysis result obtained by analyzing and processing electrocardiographic segments corresponding to the other electrocardiographic waveforms by using a preset analysis strategy;
comparing the first pre-analysis result with the second pre-analysis result;
and when the first pre-analysis result is smaller than the second pre-analysis result, modifying the weight of a preset analysis strategy so as to modify a target analysis result corresponding to the electrocardiogram data segment.
9. An electrocardiographic data segmentation apparatus, comprising:
the acquisition module is used for acquiring original electrocardiogram data;
the segmentation module is used for carrying out segmentation processing on the original electrocardiogram data to obtain N segments of electrocardiogram data, wherein N is a positive integer;
the processing module is used for analyzing and processing each section of the electrocardiogram data fragments by adopting at least one preset analysis strategy to obtain at least one analysis result of each section of the electrocardiogram data, and different preset analysis strategies correspond to different analysis results;
the judging module is used for comprehensively judging at least one analysis result of each section of the electrocardiogram data fragments so as to obtain the electrocardiogram data fragments corresponding to the optimal target analysis result;
the generating module is used for generating a target electrocardiogram waveform according to the electrocardiogram data segment corresponding to the optimal target analysis result;
the judging module comprises a summing unit and a selecting unit;
the summing unit is used for carrying out weighted summation on at least one pre-analysis result of each section of the electrocardiogram data segment so as to obtain a target analysis result of each section of the electrocardiogram data segment; acquiring an execution sequence corresponding to a preset analysis strategy, wherein the execution sequence comprises synchronous execution or asynchronous execution; the summation unit is specifically used for analyzing and processing each section of the electrocardiogram data segment according to waveform signal quality analysis based on the execution sequence to obtain a pre-analysis result corresponding to the waveform signal quality analysis; analyzing and processing each section of the electrocardiogram data fragments according to abnormal electrocardiogram signal screening analysis based on the execution sequence to obtain a pre-analysis result corresponding to the abnormal electrocardiogram signal screening analysis; analyzing and processing each section of the electrocardiogram data fragments according to arrhythmia event analysis based on the execution sequence to obtain a pre-analysis result corresponding to the arrhythmia event analysis; weighting and summing a pre-analysis result corresponding to the waveform signal quality analysis, a pre-analysis result corresponding to the abnormal electrocardiosignal screening analysis and a pre-analysis result corresponding to the arrhythmia event analysis to obtain a target analysis result corresponding to each section of the electrocardio data segment;
and the selecting unit is used for selecting a target analysis result with the largest numerical value from the target analysis results of the electrocardio data segments, and determining the electrocardio segment corresponding to the target analysis result with the largest numerical value as the electrocardio data segment corresponding to the optimal target analysis result.
CN201711132057.7A 2017-11-15 2017-11-15 Electrocardiogram data section selection method and device Active CN109770889B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711132057.7A CN109770889B (en) 2017-11-15 2017-11-15 Electrocardiogram data section selection method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711132057.7A CN109770889B (en) 2017-11-15 2017-11-15 Electrocardiogram data section selection method and device

Publications (2)

Publication Number Publication Date
CN109770889A CN109770889A (en) 2019-05-21
CN109770889B true CN109770889B (en) 2022-03-11

Family

ID=66495173

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711132057.7A Active CN109770889B (en) 2017-11-15 2017-11-15 Electrocardiogram data section selection method and device

Country Status (1)

Country Link
CN (1) CN109770889B (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1113739A (en) * 1994-06-23 1995-12-27 王湘生 Function testing system for vegetative nervous system and its method
US5827196A (en) * 1997-07-15 1998-10-27 Hewlett-Packard Company Method and system for providing characterizations of waveform representations of heart function
CN1951320A (en) * 2006-11-16 2007-04-25 上海交通大学 Abnormal electrocardiogram recognition method based on ultra-complete characteristics
CN101259016A (en) * 2007-03-06 2008-09-10 李小俚 Method for real time automatically detecting epileptic character wave
EP1495716B1 (en) * 2003-07-11 2009-02-11 C.R. Bard Inc. Processing electrocardiac signals having superimposed complexes
CN103020472A (en) * 2012-12-27 2013-04-03 中国科学院深圳先进技术研究院 Physiological signal quality evaluation method and system based on constrained estimation
CN104188649A (en) * 2014-09-15 2014-12-10 南京大学 Method for guaranteeing signal linear synthesis instantaneity in multipoint physiological electricity monitoring
WO2016045262A1 (en) * 2014-09-23 2016-03-31 京东方科技集团股份有限公司 Electroencephalographic processing device and method, and device worn for sleep monitoring
CN105852845A (en) * 2016-03-26 2016-08-17 深圳市前海安测信息技术有限公司 Wearable 12-lead remote electrocardiograph monitoring device as well as application system and method thereof
CN105942974A (en) * 2016-04-14 2016-09-21 禅客科技(上海)有限公司 Sleep analysis method and system based on low frequency electroencephalogram
CN107085464A (en) * 2016-09-13 2017-08-22 天津大学 Emotion identification method based on P300 characters spells tasks
CN107137072A (en) * 2017-04-28 2017-09-08 北京科技大学 A kind of ventricular ectopic beating detection method based on 1D convolutional neural networks
CN108399376A (en) * 2018-02-07 2018-08-14 华中师范大学 Student classroom learning interest intelligent analysis method and system

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7769434B2 (en) * 2006-11-30 2010-08-03 General Electric Company Method of physiological data analysis and measurement quality check using principal component analysis
CN101467879B (en) * 2007-12-26 2012-11-21 深圳迈瑞生物医疗电子股份有限公司 Method and device for processing multi-lead synchronized electrocardiosignal
CN105411567B (en) * 2015-12-15 2018-04-24 北京世纪今科医疗器械有限公司 A kind of ECG data analysis method and system
CN105725966A (en) * 2016-01-27 2016-07-06 浙江铭众科技有限公司 Electrocardiosignal quality discrimination method based on neural network model
CN105726016B (en) * 2016-02-02 2019-12-31 深圳市理邦精密仪器股份有限公司 Electrocardio output method and device
CN105997054B (en) * 2016-06-22 2019-07-09 天津理工大学 A kind of method of electrocardiosignal preanalysis

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1113739A (en) * 1994-06-23 1995-12-27 王湘生 Function testing system for vegetative nervous system and its method
US5827196A (en) * 1997-07-15 1998-10-27 Hewlett-Packard Company Method and system for providing characterizations of waveform representations of heart function
EP1495716B1 (en) * 2003-07-11 2009-02-11 C.R. Bard Inc. Processing electrocardiac signals having superimposed complexes
CN1951320A (en) * 2006-11-16 2007-04-25 上海交通大学 Abnormal electrocardiogram recognition method based on ultra-complete characteristics
CN101259016A (en) * 2007-03-06 2008-09-10 李小俚 Method for real time automatically detecting epileptic character wave
CN103020472A (en) * 2012-12-27 2013-04-03 中国科学院深圳先进技术研究院 Physiological signal quality evaluation method and system based on constrained estimation
CN104188649A (en) * 2014-09-15 2014-12-10 南京大学 Method for guaranteeing signal linear synthesis instantaneity in multipoint physiological electricity monitoring
WO2016045262A1 (en) * 2014-09-23 2016-03-31 京东方科技集团股份有限公司 Electroencephalographic processing device and method, and device worn for sleep monitoring
CN105852845A (en) * 2016-03-26 2016-08-17 深圳市前海安测信息技术有限公司 Wearable 12-lead remote electrocardiograph monitoring device as well as application system and method thereof
CN105942974A (en) * 2016-04-14 2016-09-21 禅客科技(上海)有限公司 Sleep analysis method and system based on low frequency electroencephalogram
CN107085464A (en) * 2016-09-13 2017-08-22 天津大学 Emotion identification method based on P300 characters spells tasks
CN107137072A (en) * 2017-04-28 2017-09-08 北京科技大学 A kind of ventricular ectopic beating detection method based on 1D convolutional neural networks
CN108399376A (en) * 2018-02-07 2018-08-14 华中师范大学 Student classroom learning interest intelligent analysis method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
A real-time quality monitoring system for optimal recording of 12-lead resting ECG;Irena Jekova;《Biomedical Signal Processing and Control》;20170430;第34卷;全文 *
科技评价中效用函数合成方法的比较研究;俞立平;《科技进步与对策》;20100110;第27卷(第1期);参见第107-108页 2研究方法 *

Also Published As

Publication number Publication date
CN109770889A (en) 2019-05-21

Similar Documents

Publication Publication Date Title
AU2016332207B2 (en) Quantitative heart testing
EP1890595B1 (en) Medical data signal processing systems
JP6901399B2 (en) ECG controller for ECG device, method of operation of the ECG controller
CN107837082A (en) Electrocardiogram automatic analysis method and device based on artificial intelligence self study
Goovaerts et al. A machine-learning approach for detection and quantification of QRS fragmentation
CA2861500A1 (en) Methods and systems for atrial fibrillation detection
US20090281441A1 (en) System for Heart Performance Characterization and Abnormality Detection
Erickson et al. Automated gastric slow wave cycle partitioning and visualization for high-resolution activation time maps
US9237881B2 (en) Ultrasonic diagnostic apparatus and method of retrieving and displaying heart function test period
US8364248B2 (en) System for cardiac pathology detection and characterization
JP2022536552A (en) Seizure detection system and method based on changes in electroencephalogram (EEG) nonlinearity
WO2018101413A1 (en) Electrocardiographic waveform display method and electrocardiogram analysis device
US11678831B2 (en) Electrocardiogram processing system for detecting and/or predicting cardiac events
WO2023236724A1 (en) High-frequency qrs waveform curve analysis method and apparatus, computer device, and storage medium
CN104066382A (en) Diagnostic imaging apparatus and image display method
WO2018101412A1 (en) Electrocardiographic waveform display method and electrocardiogram analysis device
US20220233127A1 (en) Vital-sign data statistics system and patient monitor
JP5449207B2 (en) System for morphological feature analysis of physiological data
CN109770889B (en) Electrocardiogram data section selection method and device
US11013469B2 (en) Automatic classification/intepretation of ECG waves for non-athletes/athletes
CN103961086A (en) Electrocardiogram analyzer
JP2008167799A (en) Device for analyzing auscultatory sound and program
CN111317463B (en) Heart beat insertion method, heart beat automatic insertion device and storage medium
JP2022523835A (en) Atrial fibrillation prediction model and its prediction system
US20230277107A1 (en) Systems and methods for visual tracing of abnormality in diagnostic and monitoring clinical applications

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant