CN119679428B - Cardiac transportation and open chest operation monitoring method based on high space-time resolution electrical mapping - Google Patents
Cardiac transportation and open chest operation monitoring method based on high space-time resolution electrical mapping Download PDFInfo
- Publication number
- CN119679428B CN119679428B CN202411821235.7A CN202411821235A CN119679428B CN 119679428 B CN119679428 B CN 119679428B CN 202411821235 A CN202411821235 A CN 202411821235A CN 119679428 B CN119679428 B CN 119679428B
- Authority
- CN
- China
- Prior art keywords
- mapping
- abnormal
- waveform
- electrode
- output result
- 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
Links
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a heart transportation and open chest operation monitoring method based on high space-time resolution electrical mapping. The method comprises the steps of S1, generating correlation between an electrical mapping image and mapping electrodes, acquiring a plurality of electrical mapping signal target waveforms, S2, analyzing an ECG signal in real time, denoising, acquiring a plurality of target waveforms, S3, dividing each target waveform into a plurality of sub-waveforms according to waveform types, inputting a first model, acquiring a first output result, when the target waveform is abnormal, executing S4, when the target waveform is normal, inputting a plurality of second normal waveforms which are continuous in time before the first normal waveforms as waveform sequences into the second model, acquiring a second output result, S4, calculating, analyzing, acquiring abnormal positions, generating a dynamic image, and marking the dynamic image in the electrical mapping image. The invention solves the problem of insufficient heart monitoring precision and improves the heart monitoring precision.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a heart transportation and open chest operation monitoring method based on high space-time resolution electrical mapping.
Background
With the development of medical electronics, high spatial-temporal resolution electrical mapping technique monitoring methods are widely used in clinic, particularly in and after heart transplant delivery and heart surgery open chest surgery, a similar prior art has a chinese patent publication No. CN109688904a, which proposes a system and method for detecting arrhythmic electrocardiographic signals comprising a plurality of threshold heart rates and a plurality of rate-based sensitivity levels for detecting arrhythmic ECG segments, wherein a heart rate with a higher clinical relevance is assigned a rate-based sensitivity level with a higher sensitivity. The ECG signals are monitored by the medical device and the monitored ECG signals are processed using the plurality of threshold heart rates and the plurality of rate-based sensitivity levels to detect and capture arrhythmic ECG segments. Also of similar prior art is U.S. patent publication No. US20140330145A1, which discloses a method of automatically determining local activation times in a multi-channel electrocardiogram signal comprising a plurality of heart channels, the method comprising storing the heart channel signals, calculating a first LAT value at a plurality of mapped channel locations using ventricles, referencing and mapping channels, monitoring the quality of at least one ventricle, referencing and mapping channels, replacing a sub-standard channel with another channel of the plurality of channels having a quality above the standard if the quality of the monitored heart channel is below the standard, and calculating a second LAT value based on the replaced heart channel. Both patents solve the problem of heart monitoring, but do not consider the problem of combined monitoring of epicardial electrical mapping and ECG signals, the accuracy is not high enough, and the requirement of high-accuracy monitoring cannot be met.
Disclosure of Invention
In order to better solve the problems, the invention provides a method for monitoring cardiac transportation and open chest surgery based on high spatial-temporal resolution electrical mapping, which comprises the following steps:
Step S1, acquiring an electric mapping signal of each mapping electrode in a monitoring object in a first preset period through an electric mapping unit, acquiring physiological information of the monitoring object through calculation and analysis based on a plurality of electric mapping signals, and generating a correlation between an electric mapping image and each mapping electrode based on the physiological information and the position information of each mapping electrode, wherein the mapping electrodes are arranged on an outer membrane of the monitoring object;
Step S2, an ECG signal acquisition unit acquires an ECG signal of a monitoring object in real time, an analysis result is obtained by analyzing the ECG signal in real time, denoising processing is carried out on the ECG signal when the analysis result is abnormal, and a plurality of target waveforms are obtained based on the ECG signal;
Step S3, dividing each target waveform into a plurality of sub-waveforms according to waveform types, inputting the sub-waveforms into a first model, obtaining a first output result, executing step S4 when the first output result is abnormal, obtaining a first normal waveform according to the first output result when the first output result is normal, and inputting N second normal waveforms which are continuous in time before the first normal waveform into a second model as a waveform sequence, and obtaining a second output result;
And S4, when the first output result is abnormal, acquiring all abnormal electrodes according to the first output result, acquiring abnormal positions based on the electrical mapping signals of all the abnormal electrodes, when the second output result is abnormal, acquiring a target electrode according to the second output result, generating a dynamic image according to the electrical mapping signals of the target electrode, and labeling the abnormal positions and the dynamic image in the electrical mapping image.
As a preferable technical scheme, the mapping electrodes in the electrical mapping unit are at least 32 channels, and the distance between electrode points in each mapping electrode is less than or equal to 4mm.
As a preferred embodiment, the step S1 includes:
Step S11, acquiring an electric mapping signal of each mapping electrode by the electric mapping unit in a first preset period, and acquiring conduction information of the monitored object according to the setting position of each mapping electrode and the corresponding electric mapping signal, wherein the conduction information comprises exciting points, a conduction direction, a conduction speed, a pole removal dispersion, a repolarization dispersion, a conduction phase and a frequency spectrum characteristic;
And S12, acquiring an electrical mapping image based on the position information and the conduction information of each mapping electrode, and further calculating a conduction characteristic point on each electrical mapping waveform by extracting each electrical mapping signal according to a heart beat, and acquiring a waveform relationship and a conduction relationship based on the time-space sequence of the electrical mapping waveform and the conduction characteristic point, wherein the related relationship comprises the waveform relationship and the conduction relationship.
As a preferred embodiment, the step S2 includes:
step S21, the ECG signal of a monitored object is acquired in real time through the ECG signal acquisition unit, and a plurality of first waveforms in the ECG signal are extracted, wherein the first waveforms are R waves;
Step S22, obtaining the maximum value of each first waveform and the maximum potential fluctuation value of the corresponding reference potential interval, calculating the first difference value of the maximum value and the first threshold value, calculating the second difference value of the maximum potential fluctuation value and the second threshold value, when the first difference value and the second difference value corresponding to each first waveform are in the corresponding setting range, the analysis result corresponding to the ECG signal is normal, otherwise, the analysis result corresponding to the ECG signal is abnormal, taking the ECG signal as a noise waveform, denoising the noise waveform, and taking the ECG signal after denoising and the ECG signal when the analysis result is normal as the target waveform.
As a preferred embodiment, the step S3 includes:
Step S31, dividing each target waveform into a plurality of sub-waveforms according to waveform types, inputting the plurality of sub-waveforms into the first model, and obtaining the first output result, wherein the first model is a machine learning model trained through first learning data, and the first learning data comprises sub-waveforms corresponding to ECG signals of historical heart disease patients and corresponding disease types stored in a database, and further comprises sub-waveforms corresponding to ECG signals of normal people;
step S32, when the first output result is abnormal, acquiring the disease types corresponding to the plurality of input sub-waveforms through the first output result, and executing the step S4;
And step S33, when the first output result is normal, acquiring the input multiple wavelet waveforms corresponding to the target waveform, taking the target waveform as a first normal waveform, acquiring N time-continuous second normal waveforms before the first normal waveform, taking the first normal waveform and the N second normal waveforms as waveform sequences, and inputting the first normal waveform and the N second normal waveforms into the second model, and acquiring a second output result, wherein the second model is a machine learning model trained by second learning data.
As a preferred technical solution, the second learning data includes historical abnormal electrical mapping data stored in a database, a historical ECG signal sequence within a preset time period before the time of collecting the historical abnormal electrical mapping data, and a disease type corresponding to the historical abnormal electrical mapping data.
As a preferred technical solution, the step S4 includes the following steps:
step 41, when the first output result is abnormal, acquiring a first acquisition time of the target waveform corresponding to the first output result, acquiring the electrical mapping signals acquired by each mapping electrode at a second acquisition time closest to the first acquisition time, extracting electrical mapping waveforms from each electrical mapping signal according to heart beats, calculating conductive characteristic points on each electrical mapping waveform, acquiring electrode conductive relations based on the electrical mapping waveforms and the time-space sequences of the conductive characteristic points of the electrode and other electrodes around the electrode, comparing the electrode conductive relations with correlation relations of the corresponding mapping electrodes, and when the electrode conductive relations and the correlation relations of the mapping electrodes are consistent, the mapping electrode is a normal electrode, and when the electrode conductive relations and the correlation relations are inconsistent, the mapping electrode is an abnormal electrode, acquiring an abnormal electrode position closest to the excitation point position and other abnormal electrode positions, generating an abnormal position based on the abnormal electrode position and the other abnormal electrode positions, and marking the abnormal position in the electrical mapping image;
Step S42, when the second output result is abnormal, acquiring a target position corresponding to the electric mapping image according to historical abnormal electric mapping data in the second output result, acquiring a corresponding target electrode based on the target position, reducing the acquisition period of the electric mapping unit on the target electrode to a second preset period, storing electric mapping signals acquired by the target electrode, generating a dynamic image within a corresponding range of the electric mapping image by the stored electric mapping signals of the target electrode, and marking the dynamic image in the electric mapping image;
and step S43, the user takes corresponding measures based on the abnormal position and the electrical mapping signals at the abnormal position, and identifies the abnormality in real time according to the dynamic image.
As a preferred embodiment, the step S4 further includes:
And when the second output result is normal, increasing the acquisition period of the electrical mapping unit to a third preset period, wherein the third preset period is smaller than the first preset period, and the first preset period is smaller than the second preset period.
As a preferred embodiment, the mapping electrode is flexible and biocompatible.
The invention also provides a heart transportation and open chest operation monitoring system based on high spatial-temporal resolution electrical mapping, which is used for realizing the method, and comprises the following steps:
The electric mapping unit is used for collecting electric mapping signals of each mapping electrode in a monitoring object in a first preset period, acquiring physiological information of the monitoring object through calculation and analysis based on a plurality of electric mapping signals, and generating an electric mapping image and a correlation between the mapping electrodes based on the physiological information and the position information of each mapping electrode, wherein the mapping electrodes are arranged on an outer membrane of the monitoring object;
An ECG signal acquisition unit configured to acquire an ECG signal of a monitoring object in real time, acquire an analysis result by analyzing the ECG signal in real time, perform denoising processing on the ECG signal when the analysis result is abnormal, and acquire a plurality of target waveforms based on the ECG signal;
The judging and predicting unit is used for dividing each target waveform into a plurality of sub-waveforms according to waveform types, inputting the sub-waveforms into a first model, obtaining a first output result, executing step S4 when the first output result is abnormal, obtaining a first normal waveform according to the first output result when the first output result is normal, inputting N second normal waveforms which are continuous in time before the first normal waveform into a second model as a waveform sequence, and obtaining a second output result;
And the display generating unit is used for acquiring all abnormal electrodes according to the first output result when the first output result is abnormal, acquiring abnormal positions based on the electrical mapping signals of all the abnormal electrodes, acquiring target electrodes according to the second output result when the second output result is abnormal, generating a dynamic image according to the electrical mapping signals of the target electrodes, and labeling the abnormal positions and the dynamic image in the mapping image.
Compared with the prior art, the invention has the following beneficial effects:
The invention acquires the electrical mapping signals of each mapping electrode in a first preset period through the electrical mapping unit, acquires the electrical mapping image according to the position information and the conduction information of each mapping electrode, and acquires the correlation between the mapping electrodes, wherein the mapping electrodes are arranged on the adventitia of the heart, the electrical mapping unit is a multichannel mapping with high resolution, and can monitor each position of the heart at the same time, accurately and quickly acquire the abnormal state and the abnormal position of the monitoring object, acquires the electrical mapping signals of the monitoring object in real time through the ECG signal acquisition unit, acquires a target waveform, inputs a plurality of the sub-waveforms corresponding to the target waveform into the first model, acquires the first output result, judges whether the target waveform is normal, compares each electrical mapping signal acquired at a second acquisition time with four electrical mapping signals adjacent to the surroundings when the first output result is abnormal, acquires a comparison result, acquires the correlation between the electrode and the second output electrode based on the correlation between the second mapping signal acquired at a second acquisition time and the adjacent four electrical mapping signals, and the second output electrode, and the correlation between the second output waveform and the second output waveform is more accurate, and the correlation between the second output waveform and the second output waveform is reduced when the second output waveform is more normal, and the correlation between the second waveform is acquired at the second output time and the second output electrode is more accurate, and the correlation between the second waveform is more normal, and the electric mapping signals of the target electrode are also stored, dynamic images are generated and marked in the electric mapping images, and through the mutual matching of the technical scheme, more abundant monitoring information is obtained, so that a user can conveniently and rapidly and accurately identify the abnormal position and take corresponding measures.
Drawings
FIG. 1 is a flow chart of a method for monitoring cardiac transit and open chest procedures based on high spatial-temporal resolution electrical mapping in accordance with the present invention;
FIG. 2 is a block diagram of a cardiac transit and open chest procedure monitoring system based on high spatial-temporal resolution electrical mapping in accordance with the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention provides a heart transportation and open chest operation monitoring method based on high spatial-temporal resolution electrical mapping, which is shown in fig. 1 and comprises the following steps:
Step S1, acquiring an electric mapping signal of each mapping electrode in a monitoring object in a first preset period through an electric mapping unit, acquiring physiological information of the monitoring object through calculation and analysis based on a plurality of electric mapping signals, and generating a correlation between an electric mapping image and each mapping electrode based on the physiological information and the position information of each mapping electrode, wherein the mapping electrodes are arranged on an outer membrane of the monitoring object;
Specifically, because in the heart transplantation transfer process or in cardiac surgery open chest operation, the health state of the heart needs to be acquired in real time with high precision, the ECG signal can continuously record the electrocardio condition of the patient, rich diagnosis information is provided, but the specificity is insufficient, sometimes the type and the position of arrhythmia cannot be accurately judged, the high-frequency amplitude, the high-frequency relative power, the QRS duration, the polar duration, the asymmetry, the morphological variation and other time-frequency parameters can be calculated, thereby the electric activity of the heart can be accurately detected, the position of the micro-abnormality can be effectively captured, the position of the abnormal electric activity is positioned, the electrophysiological parameters are used for better evaluating the heart health state before the heart transplantation transfer process or after the cardiac surgery open chest operation, the medical staff can conveniently adjust the treatment scheme in time, thereby better protecting the heart, meanwhile, the postoperative risk of the patient is also reduced, the postoperative survival rate and the recovery quality of the patient are improved, the method is particularly suitable for the complex arrhythmia condition of cardiac arrhythmia diagnosis, the problems of data acquisition and the calculation amount are solved, therefore, the method of mapping the high-time-space-time resolution electric mapping and the morphological variation is adopted, the electric mapping is combined with the specific mapping, the electric potential information is obtained by the electric mapping unit, the electric potential is accurately measured through the electric mapping, the electric mapping is obtained through the electrode, the electric potential of the electric mapping unit, the electric mapping is combined with the electric mapping information, and the electric potential is obtained through the electric mapping unit, and the electric mapping information is obtained through the electric mapping of the specific mapping unit, and the electric mapping information, and the electric potential is better, and comparing the electrical mapping signals of each mapping electrode with the electrical mapping signals of adjacent mapping electrodes around the electrical mapping signals to obtain the correlation between the mapping electrodes, and simultaneously, as the mapping electrodes are positioned on the adventitia of the heart, the abnormal positions can be intuitively positioned through the abnormal electrodes.
Step S2, an ECG signal acquisition unit acquires an ECG signal of a monitoring object in real time, an analysis result is obtained by analyzing the ECG signal in real time, denoising processing is carried out on the ECG signal when the analysis result is abnormal, and a plurality of target waveforms are obtained based on the ECG signal;
Specifically, the ECG signal of the monitored object is acquired in real time by the ECG signal acquisition unit, the first waveform, i.e., the R wave, in the ECG signal is extracted, the maximum value of the first waveform and the maximum fluctuation value of the corresponding reference potential interval are obtained, whether noise is mixed in the ECG signal is judged by the maximum fluctuation potential of the reference voltage interval and the maximum value of the R wave, the noise waveform is denoised, the ECG signal without noise and the ECG signal after denoise are used as the target waveform, and the accurate target waveform can be obtained by the technical scheme, so that a foundation is laid for further accurately identifying an abnormality by the target waveform.
Step S3, dividing each target waveform into a plurality of sub-waveforms according to waveform types, inputting the sub-waveforms into a first model, obtaining a first output result, executing step S4 when the first output result is abnormal, obtaining a first normal waveform according to the first output result when the first output result is normal, and inputting N second normal waveforms which are continuous in time before the first normal waveform into a second model as a waveform sequence, and obtaining a second output result;
Specifically, the target waveform is divided into a plurality of sub-waveforms according to waveform types, the plurality of sub-waveforms corresponding to the target waveform are input into the first model, the first output result is obtained, the first model is a machine learning model trained by using sub-waveforms corresponding to ECG signals of historical heart disease patients and corresponding disease types, and sub-waveforms corresponding to ECG signals of normal people as training data, whether the target waveform is normal or not can be judged according to the first output result, whether the target waveform is ill or not can not be judged according to the ECG signals, but specific position information of the ill can not be well determined, but the high space-time resolution electrical mapping technology can well solve the problem, therefore, when the first output result is abnormal, the step S4 is executed, specific abnormal positions and more diseased information are determined according to the electrical mapping technology, when the first output result is normal, some heart diseases which are not obvious on the ECG signals can not be identified, the target waveform corresponding to the first output result is used as the first waveform, the first waveform and the second waveform can be accurately obtained according to the second waveform, and the second waveform can be accurately monitored according to the second waveform, and the second state can be accurately obtained, and the second state can be accurately monitored.
And S4, when the first output result is abnormal, acquiring all abnormal electrodes according to the first output result, acquiring abnormal positions based on the electrical mapping signals of all the abnormal electrodes, when the second output result is abnormal, acquiring a target electrode according to the second output result, generating a dynamic image according to the electrical mapping signals of the target electrode, and labeling the abnormal positions and the dynamic image in the electrical mapping image.
Specifically, when the first output result is abnormal, each electrical mapping signal acquired at a second acquisition time closest to a first acquisition time of a target waveform corresponding to the first output result is taken as an analysis object, each electrical mapping signal is compared with four adjacent electrical mapping signals around, a comparison result is obtained, the electrode conduction relation is obtained based on the comparison result, the electrode conduction relation is compared with the corresponding electrode correlation relation, the abnormal electrode position closest to the exciting point is obtained, other abnormal electrode positions and abnormal positions are obtained, a medical staff can take corresponding measures according to the abnormal positions and the electrical mapping signals at the abnormal positions conveniently, when the second output result is abnormal, the target positions and the target electrodes are obtained through the target positions of the target positions in the historical abnormal electrical mapping data in the second output result, the more precise and accurate electrical mapping signals of the target electrodes are obtained through reducing the sampling period of the electrical mapping units, the electrical mapping signals of the target electrodes are also stored, the electrical mapping signals of the target electrodes are conveniently obtained, the abnormal positions are conveniently detected by the medical staff, the abnormal positions can be quickly identified in the user, or the abnormal position is accurately detected in real time, and the abnormal position is detected when the user is detected, or the abnormal position is detected, and the abnormal position is accurately, and the abnormal position is detected.
Further, the mapping electrodes in the electrical mapping unit are at least 32 channels, and the distance between electrode points in each mapping electrode is less than or equal to 4mm.
In particular, electrical mapping data can use multiple mapping electrodes simultaneously, data of multiple parts such as atria, ventricles and the like can be recorded simultaneously, high-space-time resolution electrical mapping data can be provided with a higher sampling rate so that high-frequency potential information can be recorded, fine changes of heart electrical activity can be captured by recording high-space-time resolution electrical mapping records, and electrocardiographic data is a standard heart monitoring tool widely used clinically and is provided with multiple leads, and each lead records the electrical activity of the heart from different angles, so that a comprehensive view of heart functions is provided.
Further, the step S1 includes:
Step S11, acquiring an electric mapping signal of each mapping electrode by the electric mapping unit in a first preset period, and acquiring conduction information of the monitored object according to the setting position of each mapping electrode and the corresponding electric mapping signal, wherein the conduction information comprises exciting points, a conduction direction, a conduction speed, a pole removal dispersion, a repolarization dispersion, a conduction phase and a frequency spectrum characteristic;
And S12, acquiring an electrical mapping image based on the position information and the conduction information of each mapping electrode, and further calculating a conduction characteristic point on each electrical mapping waveform by extracting each electrical mapping signal according to a heart beat, and acquiring a waveform relationship and a conduction relationship based on the time-space sequence of the electrical mapping waveform and the conduction characteristic point, wherein the related relationship comprises the waveform relationship and the conduction relationship.
Specifically, the electrical mapping unit is used for acquiring the electrical mapping signals of each mapping electrode in a first preset period, namely, the electrical signals and the conduction time of the mapping electrodes, and the electrical mapping signals of the mapping electrodes are used for acquiring the conduction information of the monitoring object, wherein the excitation point in the conduction information is used as the starting point of the electric wave conduction of the monitoring object, the electrical mapping image is acquired according to the position information and the conduction information of each mapping electrode, the electrical mapping waveforms are extracted from each electrical mapping signal according to heart beat, the conduction characteristic points on each electrical mapping waveform are calculated, and the waveform relation and the conduction relation at the adjacent electrode positions are acquired based on the time-space sequence of the electrical mapping waveforms and the conduction characteristic points at the position of each mapping electrode, and the waveform relation comprises the waveform similarity and the difference of waveforms.
Further, the step S2 includes:
step S21, the ECG signal of a monitored object is acquired in real time through the ECG signal acquisition unit, and a plurality of first waveforms in the ECG signal are extracted, wherein the first waveforms are R waves;
Step S22, obtaining the maximum value of each first waveform and the maximum potential fluctuation value of the corresponding reference potential interval, calculating the first difference value of the maximum value and the first threshold value, calculating the second difference value of the maximum potential fluctuation value and the second threshold value, when the first difference value and the second difference value corresponding to each first waveform are in the corresponding setting range, the analysis result corresponding to the ECG signal is normal, otherwise, the analysis result corresponding to the ECG signal is abnormal, taking the ECG signal as a noise waveform, denoising the noise waveform, and taking the ECG signal after denoising and the ECG signal when the analysis result is normal as the target waveform.
Specifically, the ECG signal of the monitoring object is acquired in real time by the ECG signal acquisition unit, the first waveform, i.e., the R wave, in the ECG signal is extracted, the maximum value of the first waveform and the maximum fluctuation value of the corresponding reference potential interval are acquired, and since the reference potential interval of the R wave is one equipotential interval in the ECG signal waveform and the potential change in one cardiac cycle is small, whether the ECG signal is mixed with noise is determined by the maximum fluctuation potential of the reference potential interval and the maximum value of the R wave, and when at least one of the first difference value and the second difference value is not within the corresponding setting range, i.e., the first difference value is greater than the first setting range or the second difference value is greater than the second setting range, the ECG signal is a noise waveform, and the noise waveform is denoised, and when both the first difference value and the second difference value are within the corresponding setting range, i.e., the first difference value is less than or equal to the first setting range and the second difference value is less than the second setting range, the noise is not mixed with noise, and the target ECG signal is not accurately acquired, and the target ECG signal is not processed.
Further, the step S3 includes:
Step S31, dividing each target waveform into a plurality of sub-waveforms according to waveform types, inputting the plurality of sub-waveforms into the first model, and obtaining the first output result, wherein the first model is a machine learning model trained through first learning data, and the first learning data comprises sub-waveforms corresponding to ECG signals of historical heart disease patients and corresponding disease types stored in a database, and further comprises sub-waveforms corresponding to ECG signals of normal people;
step S32, when the first output result is abnormal, acquiring the disease types corresponding to the plurality of input sub-waveforms through the first output result, and executing the step S4;
specifically, the target waveform is divided into a plurality of sub-waveforms according to waveform types, the waveform types include P-wave, T-wave and QRS-wave, the plurality of sub-waveforms corresponding to the target waveform are input into the first model, the first output result is obtained, the first model is a machine learning model trained by using sub-waveforms corresponding to ECG signals of historic heart disease patients and corresponding disease types, and sub-waveforms corresponding to ECG signals of normal people as training data, whether the target waveform is normal or not, that is, whether the target waveform is a diseased ECG signal or not can be judged according to the first output result, and when the target waveform is abnormal, the corresponding disease type is also output.
And step S33, when the first output result is normal, acquiring the input multiple wavelet waveforms corresponding to the target waveform, taking the target waveform as a first normal waveform, acquiring N time-continuous second normal waveforms before the first normal waveform, taking the first normal waveform and the N second normal waveforms as waveform sequences, and inputting the first normal waveform and the N second normal waveforms into the second model, and acquiring a second output result, wherein the second model is a machine learning model trained by second learning data.
Specifically, although the first output result indicates that the target waveform is normal, since the ECG signal alone at a certain time is limited in information reflecting the monitoring object, it is not possible to accurately identify some diseases which are not clearly reflected on the ECG signal, and therefore when the first output result is normal, the corresponding target waveform is used as a first normal waveform, N time-continuous second normal waveforms before the first normal waveform are obtained, the first normal waveform and the N time-continuous second normal waveforms are used as the waveform sequence, the waveform sequence is input into the second model, a second output result is obtained, and further, the health state of the monitoring object is more accurately judged through the time-dependent change information of each target waveform in the waveform sequence, wherein the second model is a machine learning model trained by second learning data, the second learning data is historical abnormal electrical mapping data and a historical ECG signal sequence in a preset time period before the acquisition time of the historical abnormal electrical mapping data, and the machine learning model further comprises a disease type corresponding to the historical abnormal electrical mapping data, when the second output result is normal, the monitoring object is normal, and when the second output result is abnormal, the monitoring object may be abnormal in a future time period, wherein when the second output result is abnormal, the second output result also outputs corresponding historical abnormal mapping data and disease types, according to the technical scheme, when the first output result is normal, the monitoring state of the monitored object in the future time period can be predicted more accurately through the waveform sequence.
Further, the second learning data includes historical abnormal electrical mapping data stored in a database, a historical ECG signal sequence within a preset time period before the acquisition time of the historical abnormal electrical mapping data, and a disease type corresponding to the historical abnormal electrical mapping data.
Specifically, the health state of the monitoring object in the future time period can be accurately predicted by using the second model trained by the second learning data, and medical staff can know the state of the monitoring object in the future time period in advance, so that the state parameters of the monitoring object can be accurately and timely acquired when the monitoring object is transplanted and transported or subjected to cardiac surgery open chest surgery.
Further, the step S4 includes:
step 41, when the first output result is abnormal, acquiring a first acquisition time of the target waveform corresponding to the first output result, acquiring the electrical mapping signals acquired by each mapping electrode at a second acquisition time closest to the first acquisition time, extracting electrical mapping waveforms from each electrical mapping signal according to heart beats, calculating conductive characteristic points on each electrical mapping waveform, acquiring electrode conductive relations based on the electrical mapping waveforms and the time-space sequences of the conductive characteristic points of the electrode and other electrodes around the electrode, comparing the electrode conductive relations with correlation relations of the corresponding mapping electrodes, and when the electrode conductive relations and the correlation relations of the mapping electrodes are consistent, the mapping electrode is a normal electrode, and when the electrode conductive relations and the correlation relations are inconsistent, the mapping electrode is an abnormal electrode, acquiring an abnormal electrode position closest to the excitation point position and other abnormal electrode positions, generating an abnormal position based on the abnormal electrode position and the other abnormal electrode positions, and marking the abnormal position in the electrical mapping image;
Specifically, when the first output result is abnormal, it is indicated that an abnormal state, i.e. a disease state, may occur in the monitored object, and more abundant abnormal information needs to be obtained through the electrical mapping unit in time, so that medical staff can conveniently and accurately and timely rescue, and since the electrical mapping signals collected closer to the first collection time of the target waveform corresponding to the first output result are more accurate, each electrical mapping signal collected at the second collection time is taken as an analysis object, wherein the second collection time may be before or after the first collection time, each electrical mapping signal is compared with other adjacent electrical mapping signals around to obtain a comparison result, and the electrode conduction relationship is obtained based on the comparison result, the electrode conduction relation comprises the conduction sequence and the conduction speed of the electrode and four adjacent electrodes around, the electrode conduction relation is compared with the corresponding electrode correlation relation, when the electrode conduction relation is consistent with the electrode correlation relation, the electrode is normal, and when the electrode conduction relation is inconsistent with the electrode correlation relation, the electrode is an abnormal electrode, because the electric conduction of a monitoring object starts from an exciting point, the electric conduction of a position close to the exciting point is inaccurate, and the later is abnormal, therefore, firstly, the position of the abnormal electrode closest to the exciting point is acquired, and the positions of other abnormal electrodes are also acquired, wherein the positions of the other abnormal electrodes are related to the positions of the abnormal electrodes and are marked in the electric mapping image as the first abnormal positions, so that medical staff can conveniently take corresponding measures according to the abnormal positions and the electric mapping signals at the abnormal positions, the method can rapidly and accurately acquire the abnormal position and the electrical mapping signals at the abnormal position, is convenient for medical staff to acquire corresponding measures in time, and prevents the state of the monitored object from further deteriorating.
Step S42, when the second output result is abnormal, acquiring a target position corresponding to the electric mapping image according to historical abnormal electric mapping data in the second output result, acquiring a corresponding target electrode based on the target position, reducing the acquisition period of the electric mapping unit on the target electrode to a second preset period, storing electric mapping signals acquired by the target electrode, generating a dynamic image within a corresponding range of the electric mapping image by the stored electric mapping signals of the target electrode, and marking the dynamic image in the electric mapping image;
and step S43, the user takes corresponding measures based on the abnormal position and the electrical mapping signals at the abnormal position, and identifies the abnormality in real time according to the dynamic image.
Specifically, when the second output result is abnormal, it is indicated that the monitored object may be abnormal next, because the historical abnormal electrical mapping data includes not only abnormal data but also mapping positions corresponding to the abnormal data, the target positions corresponding to the electrical mapping images are obtained through the mapping positions in the historical abnormal electrical mapping data in the second output result, the target electrodes at the target positions are obtained based on the target positions, the sampling period of the electrical mapping units is reduced, so that more precise and accurate electrical mapping signals of the target electrodes are obtained, the electrical mapping signals of the target electrodes are stored, all stored electrical mapping signals of the target electrodes are used as electrical mapping signal sequences, the dynamic image is generated in the electrical mapping images based on the electrical mapping signal sequences, so that a user can conveniently identify the abnormal positions and take corresponding measures, and when the monitored object is transplanted or operated, the real-time state of the monitored object can be obtained in real time, and the abnormal position is detected immediately or immediately after the abnormal position occurs.
Further, the step S4 further includes:
And when the second output result is normal, increasing the acquisition period of the electrical mapping unit to a third preset period, wherein the third preset period is smaller than the first preset period, and the first preset period is smaller than the second preset period.
Specifically, although the high spatial-temporal resolution electrical mapping technology can monitor the state of the monitoring object more accurately and acquire the monitoring information of the monitoring object more abundant, the high spatial-temporal resolution electrical mapping technology has larger data volume, more storage occupied resources, larger data transmission pressure, larger power consumption of analog-to-digital conversion needed during acquisition, and possibly rising temperature of equipment, so that in the initial state, the electrical mapping unit acquires electrical mapping signals and creates electrical mapping images in a first preset period, and when the second output result is normal, the probability of occurrence of abnormality of the monitoring object is smaller, and in order to save the storage resource occupation and reduce the rising of equipment temperature, the acquisition period is increased to a third preset period when the probability of occurrence of abnormality of the monitoring object is smaller.
Further, the mapping electrode is flexible and biocompatible.
The invention also provides a heart transportation and open chest operation monitoring system based on high spatial-temporal resolution electrical mapping, which is used for realizing the method, as shown in fig. 2, and comprises the following steps:
The electric mapping unit is used for collecting electric mapping signals of each mapping electrode in a monitoring object in a first preset period, acquiring physiological information of the monitoring object through calculation and analysis based on a plurality of electric mapping signals, and generating an electric mapping image and a correlation between the mapping electrodes based on the physiological information and the position information of each mapping electrode, wherein the mapping electrodes are arranged on an outer membrane of the monitoring object;
An ECG signal acquisition unit configured to acquire an ECG signal of a monitoring object in real time, acquire an analysis result by analyzing the ECG signal in real time, perform denoising processing on the ECG signal when the analysis result is abnormal, and acquire a plurality of target waveforms based on the ECG signal;
The judging and predicting unit is used for dividing each target waveform into a plurality of sub-waveforms according to waveform types, inputting the sub-waveforms into a first model, obtaining a first output result, executing step S4 when the first output result is abnormal, obtaining a first normal waveform according to the first output result when the first output result is normal, inputting N second normal waveforms which are continuous in time before the first normal waveform into a second model as a waveform sequence, and obtaining a second output result;
And the display generating unit is used for acquiring all abnormal electrodes according to the first output result when the first output result is abnormal, acquiring abnormal positions based on the electrical mapping signals of all the abnormal electrodes, acquiring target electrodes according to the second output result when the second output result is abnormal, generating a dynamic image according to the electrical mapping signals of the target electrodes, and labeling the abnormal positions and the dynamic image in the mapping image.
In summary, the present invention obtains the electrical mapping signals of each of the mapping electrodes in a first preset period by the electrical mapping unit, obtains the electrical mapping image according to the position information of each of the mapping electrodes and the conduction information, and obtains the correlation between the mapping electrodes, wherein the mapping electrodes are disposed on the adventitia of the heart, the electrical mapping unit is a multichannel mapping with high resolution, and is capable of simultaneously monitoring each position of the heart, establishes a basis for accurately and rapidly obtaining an abnormal state and an abnormal position of the monitoring object, acquires the ECG signals of the monitoring object in real time by the ECG signal acquisition unit, and obtains a target waveform, inputs a plurality of the sub-waveforms corresponding to the target waveform into the first model, and obtains the first output result, judges whether the target waveform is normal, compares each of the electrical mapping signals acquired at a second acquisition time with four electrical mapping signals adjacent to the surroundings when the first output result is abnormal, obtains a comparison result based on the comparison result, and obtains the correlation between the second output waveform and the second output waveform is normal, and the correlation between the second output waveform is obtained by the second output signal acquisition unit, and the correlation between the second output waveform is reduced when the second output waveform is abnormal, and the correlation between the second waveform is obtained by the second output signal is the second output model and the second output waveform is normal, therefore, the electric mapping signals of the target electrode are acquired more precisely and accurately, the electric mapping signals of the target electrode are also saved, dynamic images are generated, the dynamic images are marked in the electric mapping images, and through the mutual matching of the technical scheme, more abundant monitoring information is acquired, so that a user can conveniently and rapidly and accurately identify abnormal positions and take corresponding measures.
The technical features of the above embodiments may be arbitrarily combined, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as the scope of the description of the present specification as long as there is no contradiction between the combinations of the technical features.
The foregoing examples have been presented to illustrate only a few embodiments of the invention and are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411821235.7A CN119679428B (en) | 2024-12-11 | 2024-12-11 | Cardiac transportation and open chest operation monitoring method based on high space-time resolution electrical mapping |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411821235.7A CN119679428B (en) | 2024-12-11 | 2024-12-11 | Cardiac transportation and open chest operation monitoring method based on high space-time resolution electrical mapping |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119679428A CN119679428A (en) | 2025-03-25 |
| CN119679428B true CN119679428B (en) | 2025-06-13 |
Family
ID=95040633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411821235.7A Active CN119679428B (en) | 2024-12-11 | 2024-12-11 | Cardiac transportation and open chest operation monitoring method based on high space-time resolution electrical mapping |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119679428B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101856271A (en) * | 2009-04-13 | 2010-10-13 | 韦伯斯特生物官能公司 | Epicardial Mapping and Ablation Catheters |
| CN106691438A (en) * | 2016-12-07 | 2017-05-24 | 首都医科大学附属北京安贞医院 | Integralheart three-dimensional mapping system for complex arrhythmias |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9717429B2 (en) * | 2013-10-31 | 2017-08-01 | St. Jude Medical, Cardiology Division, Inc. | System and method for analyzing biological signals and generating electrophyisology maps |
| US9259165B2 (en) * | 2014-02-26 | 2016-02-16 | Biosense Webster (Israel) Ltd. | Determination of reference annotation time from multi-channel electro-cardiogram signals |
| CN109091138B (en) * | 2018-07-12 | 2021-10-26 | 上海微创电生理医疗科技股份有限公司 | Arrhythmia origin point judging device and mapping system |
| CN115054263A (en) * | 2022-07-06 | 2022-09-16 | 北京斯高科技有限公司 | Isolated multichannel electrical mapping system |
-
2024
- 2024-12-11 CN CN202411821235.7A patent/CN119679428B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101856271A (en) * | 2009-04-13 | 2010-10-13 | 韦伯斯特生物官能公司 | Epicardial Mapping and Ablation Catheters |
| CN106691438A (en) * | 2016-12-07 | 2017-05-24 | 首都医科大学附属北京安贞医院 | Integralheart three-dimensional mapping system for complex arrhythmias |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119679428A (en) | 2025-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107358196B (en) | Heart beat type classification method and device and electrocardiograph | |
| CN109411041B (en) | ECG information processing method and ECG workstation system | |
| US7142907B2 (en) | Method and apparatus for algorithm fusion of high-resolution electrocardiograms | |
| JP6381444B2 (en) | Method and system for automatically measuring ST level of electrocardiogram in real-time ECG | |
| AL-Ziarjawey et al. | Heart rate monitoring and PQRST detection based on graphical user interface with Matlab | |
| US8755876B2 (en) | Methods and systems for atrial fibrillation detection | |
| CN109411042B (en) | ECG information processing method and ECG workstation | |
| CN112237431A (en) | Electrocardio parameter calculation method based on deep learning | |
| CN109288515B (en) | Method and device for periodic monitoring of premature beats in wearable ECG signals | |
| US20210007621A1 (en) | Method to analyze cardiac rhythms using beat-to-beat display plots | |
| US20120330557A1 (en) | System for Cardiac Condition Analysis Based on Cardiac Operation Patterns | |
| US20160206287A1 (en) | Wearable Doppler Ultrasound Based Cardiac Monitoring | |
| US20190374123A1 (en) | Predicting atrial fibrillation or stroke using p-wave analysis | |
| CN115770054A (en) | Electrocardiosignal processing method, portable electrocardiosignal acquisition equipment and storage medium | |
| CN119679428B (en) | Cardiac transportation and open chest operation monitoring method based on high space-time resolution electrical mapping | |
| CN114533081B (en) | Paroxysmal atrial fibrillation detection device fused with premature beat inhibition strategy | |
| US12023165B2 (en) | Screening cardiac conditions using cardiac vibrational energy spectral heat maps | |
| CN113288156B (en) | A method for generating ECG data from any lead perspective | |
| Merdjanovska et al. | Benchmarking deep learning methods for arrhythmia detection | |
| JP2021030080A (en) | Method for determining r peak of electrocardiogram | |
| WO2012119665A1 (en) | Method and device for long-term variability monitoring of cardiovascular parameters based on ambulatory registration of electrocardiogram and pulse wave signals | |
| JP7692130B1 (en) | Method for extracting abnormal waveforms in a portable electrocardiogram measuring device | |
| KR20200055582A (en) | Electrocardiogram signal diagnostic parameter extraction device and extraction method | |
| Singh et al. | Signal Quality Evaluation and Processing for QRS Detection in ECG based Smart Healthcare Systems | |
| KR20150081763A (en) | Method and system for r wave detection from electrocardiogram |
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 |