Method for monitoring cardiac transport and thoracotomy based on high spatiotemporal resolution electrical mapping

Abstract

Provided is a method for monitoring cardiac transport and thoracotomy based on high spatiotemporal resolution electrical mapping, which comprises: step S1: generating an electrical mapping image and correlation relationships between mapping electrodes, and acquiring a plurality of electrical mapping signal target waveforms; step S2: analyzing ECG signals in real time, performing denoising processing, and acquiring a plurality of target waveforms; step S3: dividing each target waveform into a plurality of sub-waveforms according to waveform types, inputting the plurality of sub-waveforms into a first model to acquire a first output result; if the result is abnormal, executing step S4, and if the result is normal, inputting a plurality of temporally consecutive second normal waveforms preceding the first normal waveform as a waveform sequence into a second model, and acquiring a second output result; and step S4: calculating and analyzing to acquire an abnormal position, generating a dynamic image, and marking the abnormal position on the electrical mapping image.

Description

Methods for monitoring cardiac transport and open-chest surgery based on high spatiotemporal resolution electrical mapping Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically to a method for monitoring cardiac transport and open-chest surgery based on high spatiotemporal resolution electrical mapping. Background Technology

[0002] With the development of medical electronics, high spatiotemporal resolution electrocardiography (ECG) monitoring methods are widely used in clinical practice, especially during and after heart transplant transport and open-heart surgery in cardiac surgery. A similar prior art is Chinese Patent Publication No. CN109688904A, which proposes a system and method for detecting arrhythmic ECG signals. This includes multiple threshold heart rates and multiple rate-based sensitivity levels for detecting arrhythmic ECG segments, wherein heart rates with higher clinical relevance are assigned a rate-based sensitivity level with higher sensitivity. The ECG signal is monitored by a medical device, and the monitored ECG signal is processed using the multiple threshold heart rates and the multiple rate-based sensitivity levels to detect and capture arrhythmic ECG segments. Furthermore, a similar prior art exists in US Patent Publication No. US20140330145A1, which discloses a method for automatically determining the local activation time (LAT) in a multi-channel electrocardiogram (ECG) signal comprising multiple cardiac channels. The method includes: storing the cardiac channel signals; calculating a first LAT value at multiple mapped channel locations using ventricular, reference, and mapping channels; monitoring the quality of at least one ventricular, reference, and mapping channel; if the quality of the monitored cardiac channel is below a standard, replacing the substandard channel with another channel from a plurality of channels having a quality above the standard; and calculating a second LAT value based on the replaced cardiac channel. Both of these patents address the problem of cardiac monitoring, but they do not consider the issue of combined monitoring of epicardial electrical mapping and ECG signals, resulting in insufficient accuracy and failing to meet the requirements of high-precision monitoring. This invention, by employing high-resolution epicardial electrical mapping and combined monitoring with ECG signals, not only provides a direct view of abnormal locations but also further improves monitoring accuracy. Summary of the Invention

[0003] To better address the aforementioned problems, this invention provides a method for monitoring cardiac transport and open-chest surgery based on high spatiotemporal resolution electrical mapping, the method comprising the following steps:

[0004] Step S1: The electro-mapping signal of each mapping electrode in the monitored object is collected by the electro-mapping unit at a first preset cycle, and the physiological information of the monitored object is obtained by calculation and analysis based on multiple electro-mapping signals. Based on the physiological information and the position information of each mapping electrode, an electro-mapping image and the correlation between the mapping electrodes are generated, wherein the mapping electrodes are set on the outer membrane of the monitored object.

[0005] Step S2: The ECG signal of the monitored object is acquired in real time through the ECG signal acquisition unit. The analysis result is obtained by analyzing the ECG signal in real time. When the analysis result is abnormal, the ECG signal is denoised and multiple target waveforms are obtained based on the ECG signal.

[0006] Step S3: Divide each target waveform into multiple sub-waveforms according to waveform type, and input the sub-waveforms into the first model to obtain the first output result. If the first output result is abnormal, execute step S4. If the first output result is normal, obtain the first normal waveform according to the first output result. Also, input the N consecutive second normal waveforms before the first normal waveform as a waveform sequence into the second model and obtain the second output result.

[0007] Step S4: When the first output result is abnormal, obtain all abnormal electrodes according to the first output result, and obtain the abnormal position based on the electrical measurement signal of all the abnormal electrodes. When the second output result is abnormal, obtain the target electrode according to the second output result, and generate a dynamic image according to the electrical measurement signal of the target electrode. Mark the abnormal position and the dynamic image in the electrical measurement image.

[0008] As a preferred technical solution, the calibration electrode in the electrical calibration unit has at least 32 channels, and the distance between the electrode points in each calibration electrode is less than or equal to 4 mm.

[0009] As a preferred technical solution, step S1 includes:

[0010] Step S11: The electrical measurement unit acquires the electrical measurement signal of each measurement electrode at a first preset period. Based on the setting position of each measurement electrode and the corresponding electrical measurement signal, the conduction information of the monitored object is acquired. The conduction information includes excitation point, conduction direction, conduction velocity, depolarization dispersion and repolarization dispersion, conduction phase and spectral characteristics.

[0011] Step S12: Obtain the electrical mapping image based on the position information of each mapping electrode and the conduction information. Also, extract the electrical mapping waveform according to the heartbeat of each electrical mapping signal, calculate the conduction feature points on each electrical mapping waveform, and obtain the waveform relationship and conduction relationship based on the temporal and spatial order of the electrical mapping waveform and the conduction feature points. The correlation relationship includes the waveform relationship and the conduction relationship.

[0012] As a preferred technical solution, step S2 includes:

[0013] Step S21: The ECG signal of the monitored object is acquired in real time by the ECG signal acquisition unit, and multiple first waveforms are extracted from the ECG signal, wherein the first waveform is an R wave;

[0014] Step S22: Obtain the maximum value of each first waveform and the maximum potential fluctuation value of the corresponding reference potential range, calculate the first difference between the maximum value and the first threshold, and the second difference between the maximum potential fluctuation value and the second threshold. When the first difference and the second difference corresponding to each first waveform are within the corresponding set range, the analysis result corresponding to the ECG signal is normal; otherwise, the analysis result corresponding to the ECG signal is abnormal. The ECG signal is treated as a noise waveform, and the noise waveform is denoised. The denoised ECG signal and the ECG signal when the analysis result is normal are used as the target waveform.

[0015] As a preferred technical solution, step S3 includes:

[0016] Step S31: Divide each target waveform into multiple sub-waveforms according to waveform type, input the multiple sub-waveforms into the first model, and obtain the first output result. The first model is a machine learning model trained with first learning data. The first learning data includes sub-waveforms corresponding to ECG signals of historical heart disease patients and corresponding disease types stored in the database, as well as sub-waveforms corresponding to ECG signals of normal people.

[0017] Step S32: When the first output result is abnormal, obtain the disease types corresponding to the multiple input sub-waveforms through the first output result, and execute step S4;

[0018] Step S33: When the first output result is normal, obtain the target waveform corresponding to the multiple input sub-waveforms, and take the target waveform as the first normal waveform. Obtain the N consecutive second normal waveforms before the first normal waveform. Input the first normal waveform and the N second normal waveforms as a waveform sequence into the second model and obtain the second output result. The second model is a machine learning model trained with the second learning data.

[0019] As a preferred technical solution, the second learning data includes historical abnormal electroencephalogram (EEG) data stored in the database and historical ECG signal sequences within a preset time period prior to the acquisition time of the historical abnormal EEG data, as well as the disease type corresponding to the historical abnormal EEG data.

[0020] As a preferred technical solution, step S4 includes the following steps:

[0021] Step S41: When the first output result is abnormal, obtain the first acquisition time of the target waveform corresponding to the first output result, obtain the electrical mapping signal acquired by each mapping electrode at the second acquisition time closest to the first acquisition time, extract the electrical mapping waveform of each electrical mapping signal according to the heartbeat, calculate the conduction feature points on each electrical mapping waveform, obtain the electrode conduction relationship based on the temporal and spatial order of the electrical mapping waveforms and conduction feature points of the electrode and other electrodes around the electrode, compare the electrode conduction relationship with the correlation relationship of the corresponding mapping electrode, if the two are consistent, the mapping electrode is a normal electrode, if the two are inconsistent, the mapping electrode is an abnormal electrode, and obtain the abnormal electrode position closest to the excitation point position and other abnormal electrode positions, generate an abnormal position based on the abnormal electrode position and the other abnormal electrode positions and mark it in the electrical mapping image;

[0022] Step S42: When the second output result is abnormal, obtain the target position in the corresponding electrical measurement image according to the historical abnormal electrical measurement data in the second output result, obtain the corresponding target electrode based on the target position, reduce the acquisition cycle of the electrical measurement unit for the target electrode to the second preset cycle, save the electrical measurement signal acquired by the target electrode, generate a dynamic image in the corresponding range of the electrical measurement image using the saved electrical measurement signal of the target electrode, and mark it in the electrical measurement image;

[0023] Step S43: The user takes corresponding measures based on the abnormal location and the electrical measurement signal at the abnormal location, and identifies the abnormality in real time based on the dynamic image.

[0024] As a preferred technical solution, step S4 further includes:

[0025] When the second output result is normal, the acquisition period of the electrical measurement unit is increased to a third preset period, wherein the third preset period is less than the first preset period, and the first preset period is less than the second preset period.

[0026] As a preferred technical solution, the calibration electrode is flexible and biocompatible.

[0027] The present invention also provides a cardiac transport and open-chest surgery monitoring system based on high spatiotemporal resolution electrography, the system being used to implement the above-described method, the system comprising:

[0028] An electro-labeling unit is used to collect electro-labeling signals from each labeling electrode in the monitored object at a first preset cycle, and to obtain the physiological information of the monitored object through calculation and analysis based on multiple electro-labeling signals. Based on the physiological information and the position information of each labeling electrode, an electro-labeling image and the correlation between the labeling electrodes are generated. The labeling electrodes are disposed on the outer membrane of the monitored object.

[0029] The ECG signal acquisition unit is used to acquire the ECG signal of the monitored object in real time, obtain the analysis result by analyzing the ECG signal in real time, and perform noise reduction processing on the ECG signal when the analysis result is abnormal, and acquire multiple target waveforms based on the ECG signal.

[0030] The discrimination and prediction unit is used to divide each target waveform into multiple sub-waveforms according to the waveform type, input the sub-waveforms into the first model, obtain the first output result, execute step S4 when the first output result is abnormal, obtain the first normal waveform according to the first output result when the first output result is normal, and input the N consecutive second normal waveforms before the first normal waveform into the second model as a waveform sequence, and obtain the second output result.

[0031] The display generation unit is configured to, when the first output result is abnormal, obtain all abnormal electrodes according to the first output result and obtain the abnormal position based on the electrical measurement signal of all the abnormal electrodes; when the second output result is abnormal, obtain the target electrode according to the second output result and generate a dynamic image according to the electrical measurement signal of the target electrode, and mark the abnormal position and the dynamic image in the measurement image.

[0032] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0033] This invention acquires the electrical mapping signal of each mapping electrode at a first preset period using the aforementioned electrical mapping unit. Based on the position information and conduction information of each mapping electrode, it acquires the electrical mapping image and obtains the correlation between the mapping electrodes. The mapping electrodes are placed on the epicardium of the heart. The electrical mapping unit is a high-resolution multi-channel mapping unit capable of simultaneously monitoring various locations of the heart, laying the foundation for accurately and quickly acquiring the abnormal state and location of the monitored object. The ECG signal acquisition unit acquires the ECG signal of the monitored object in real time and obtains the target waveform. Multiple sub-waveforms corresponding to the target waveform are input into the first model, and a first output result is obtained. The system determines whether the target waveform is normal. If the first output result is abnormal, each electrical mapping signal acquired at a second acquisition time is compared with four adjacent electrical mapping signals. The comparison results are obtained, and the electrode conduction relationship is obtained based on the comparison results. This relationship is then compared with the corresponding electrode correlation relationship. The location of the abnormal electrode closest to the excitation point and other abnormal electrode locations are obtained, thereby identifying the abnormal location. When the first output result is normal, the first normal waveform and the previous N consecutive second normal waveforms are input into the second model to obtain the second output result. When the second output result is abnormal, the target location and target electrode are obtained through the second output result. By reducing the sampling period of the electrical mapping unit, a more refined and accurate electrical mapping signal of the target electrode is obtained. The electrical mapping signal of the target electrode is also saved and a dynamic image is generated and marked in the electrical mapping image. Through the cooperation of the above technical solutions, richer monitoring information is obtained, which facilitates users to quickly and accurately identify abnormal locations and take corresponding measures. Attached Figure Description

[0034] Figure 1 is a flowchart of the cardiac transport and open-chest surgery monitoring method based on high spatiotemporal resolution electrical mapping according to the present invention.

[0035] Figure 2 is a structural diagram of the cardiac transport and open-chest surgery monitoring system based on high spatiotemporal resolution electrical mapping according to the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0037] This invention provides a method for monitoring cardiac transport and open-chest surgery based on high spatiotemporal resolution electrical mapping, as shown in Figure 1. The method includes the following steps:

[0038] Step S1: The electro-mapping signal of each mapping electrode in the monitored object is collected by the electro-mapping unit at a first preset cycle, and the physiological information of the monitored object is obtained by calculation and analysis based on multiple electro-mapping signals. Based on the physiological information and the position information of each mapping electrode, an electro-mapping image and the correlation between the mapping electrodes are generated, wherein the mapping electrodes are set on the outer membrane of the monitored object.

[0039] Specifically, during heart transplant transport or open-heart surgery, high-precision real-time acquisition of the heart's health status is required. While ECG signals can continuously record the patient's electrocardiogram and provide rich diagnostic information, their specificity is insufficient, sometimes failing to accurately determine the type and location of arrhythmias. High temporal resolution recording can calculate various time-frequency parameters such as high-frequency amplitude, high-frequency relative power, QRS duration, depolarization duration, asymmetry, and morphological variations. This allows for precise mapping of cardiac electrical activity, effectively capturing minute abnormalities, and locating the location of abnormal electrical activity. More detailed electrophysiological parameters enable better assessment of the heart's health status before and after heart transplant transport or open-heart surgery, facilitating timely adjustments to treatment plans by medical staff. This better protects the heart, reduces postoperative risks, and improves postoperative survival and recovery quality. It is particularly suitable for complex arrhythmias that cannot be clearly diagnosed by ECG. However, it involves significant data acquisition and computational loads. Therefore, combining the aforementioned high spatiotemporal resolution electro-mapping technology with ECG signals improves diagnostic accuracy and treatment efficacy. Specifically, the electro-mapping unit acquires the electro-mapping signal of each of the aforementioned mapping electrodes at a first preset cycle, i.e., the potential information and conduction time of the mapping electrodes. The conduction information of the monitored object is obtained through the electro-mapping signals of the mapping electrodes. Based on the position information and conduction information of each of the aforementioned mapping electrodes, an electro-mapping image is acquired. The electro-mapping signal of each of the aforementioned mapping electrodes is compared with the electro-mapping signals of its neighboring mapping electrodes to obtain the correlation between the mapping electrodes. Furthermore, since the mapping electrodes are located on the epicardium of the heart, abnormal locations can be directly located through the abnormal electrodes. This technical solution not only acquires the electro-mapping image but also obtains the correlation between each of the aforementioned mapping electrodes and its neighboring mapping electrodes, laying the foundation for accurately and quickly acquiring the abnormal state and location of the monitored object.

[0040] Step S2: The ECG signal of the monitored object is acquired in real time through the ECG signal acquisition unit. The analysis result is obtained by analyzing the ECG signal in real time. When the analysis result is abnormal, the ECG signal is denoised and multiple target waveforms are obtained based on the ECG signal.

[0041] Specifically, the ECG signal of the monitored object is acquired in real time by the ECG signal acquisition unit, and the first waveform, i.e., the R-wave, is extracted from the ECG signal. The maximum value of the first waveform and the maximum fluctuation value of the corresponding reference potential range are obtained. The maximum fluctuation potential of the reference voltage range and the maximum value of the R-wave are used to determine whether there is noise mixed in the ECG signal. The noise waveform is then denoised. The noise-free ECG signal and the denoised ECG signal are used as the target waveform. Through the above technical solution, the accurate target waveform can be obtained, laying the foundation for further accurate identification of anomalies through the target waveform.

[0042] Step S3: Divide each target waveform into multiple sub-waveforms according to waveform type, and input the sub-waveforms into the first model to obtain the first output result. If the first output result is abnormal, execute step S4. If the first output result is normal, obtain the first normal waveform according to the first output result. Also, input the N consecutive second normal waveforms before the first normal waveform as a waveform sequence into the second model and obtain the second output result.

[0043] Specifically, by dividing the target waveform into multiple sub-waveforms according to waveform type, and inputting the multiple sub-waveforms corresponding to the target waveform into the first model, the first output result is obtained. The first model is a machine learning model trained with sub-waveforms corresponding to ECG signals of historical heart disease patients and their corresponding disease types, as well as sub-waveforms corresponding to ECG signals of normal individuals as training data. The first output result can determine whether the target waveform is normal. Since ECG signals can only determine whether a disease exists, but cannot determine the specific location of the disease, high spatiotemporal resolution electroporation technology can effectively solve this problem. Therefore, when the first output result is abnormal, by executing step S4, the specific abnormal location and more disease information can be determined through electroporation technology. When the first output result is normal, some heart diseases that are not clearly reflected in ECG signals cannot be identified. Therefore, the target waveform corresponding to the first output result is taken as the first normal waveform. The first normal waveform and the previous N consecutive second normal waveforms are input into the second model to obtain the second output result. Through the above technical solution, the monitoring status of the monitored object can be more accurately determined.

[0044] Step S4: When the first output result is abnormal, obtain all abnormal electrodes according to the first output result, and obtain the abnormal position based on the electrical measurement signal of all the abnormal electrodes. When the second output result is abnormal, obtain the target electrode according to the second output result, and generate a dynamic image according to the electrical measurement signal of the target electrode. Mark the abnormal position and the dynamic image in the electrical measurement image.

[0045] Specifically, when the first output result is abnormal, each of the above-mentioned electrical marker signals acquired at the second acquisition time closest to the first acquisition time of the target waveform corresponding to the first output result is taken as the analysis object. Each of the above-mentioned electrical marker signals is compared with the four surrounding electrical marker signals to obtain the comparison result. Based on the comparison result, the above-mentioned electrode conduction relationship is obtained, and the above-mentioned electrode conduction relationship is compared with the corresponding above-mentioned electrode correlation relationship to obtain the abnormal electrode position closest to the above-mentioned excitation point. At the same time, other abnormal electrode positions and abnormal positions are also obtained, so that medical staff can take corresponding measures according to the abnormal positions and the above-mentioned electrical marker signals at the abnormal positions. When an anomaly is detected, the target location and target electrode are obtained from the target location in the historical abnormal electrical mapping data in the second output result. By reducing the sampling period of the electrical mapping unit, a more refined and accurate electrical mapping signal of the target electrode is obtained. The electrical mapping signal of the target electrode is also saved, and a dynamic image is generated and marked in the electrical mapping image. This facilitates the user to identify the abnormal location and take corresponding measures. Through the above technical solution, when the monitored object is transplanted, transported, or undergoes surgery, the real-time status of the monitored object can be obtained in real time. When the monitored object shows an abnormality or is about to show an abnormality, the abnormal location can be accurately and quickly determined, and timely measures can be taken.

[0046] Furthermore, the calibration electrode in the electrical calibration unit has at least 32 channels, and the distance between electrode points in each calibration electrode is less than or equal to 4 mm.

[0047] Specifically, electrocardiography data can use multiple mapping electrodes simultaneously to record data from multiple sites such as the atria and ventricles. High spatiotemporal resolution electrocardiography data should have a high sampling rate to record high-frequency potential information. By recording high spatiotemporal resolution electrocardiography data, subtle changes in cardiac electrical activity can be captured. Electrocardiogram (ECG) data is a standard cardiac monitoring tool widely used in clinical practice. It has multiple leads, each of which records cardiac electrical activity from different angles, providing a comprehensive view of cardiac function.

[0048] Further, step S1 includes:

[0049] Step S11: The electrical measurement unit acquires the electrical measurement signal of each measurement electrode at a first preset period. Based on the setting position of each measurement electrode and the corresponding electrical measurement signal, the conduction information of the monitored object is acquired. The conduction information includes excitation point, conduction direction, conduction velocity, depolarization dispersion and repolarization dispersion, conduction phase and spectral characteristics.

[0050] Step S12: Obtain the electrical mapping image based on the position information of each mapping electrode and the conduction information. Also, extract the electrical mapping waveform according to the heartbeat of each electrical mapping signal, calculate the conduction feature points on each electrical mapping waveform, and obtain the waveform relationship and conduction relationship based on the temporal and spatial order of the electrical mapping waveform and the conduction feature points. The correlation relationship includes the waveform relationship and the conduction relationship.

[0051] Specifically, the electrical mapping unit acquires the electrical mapping signal of each of the aforementioned mapping electrodes at a first preset period, namely the electrical signal and conduction time of the mapping electrodes. Since the electrical mapping unit is a high spatiotemporal resolution electrical mapping unit, and the conduction information of the monitored object is obtained through the electrical mapping signal of the aforementioned mapping electrodes, wherein the excitation point in the conduction information is the starting point of the electromagnetic wave conduction of the monitored object, the electrical mapping image is also acquired based on the position information of each of the aforementioned mapping electrodes and the conduction information, the electrical mapping waveform is extracted according to the heartbeat of each electrical mapping signal, the conduction feature points on each electrical mapping waveform are calculated, and the waveform relationship and conduction relationship at the adjacent electrode positions are obtained based on the temporal and spatial order of the electrical mapping waveform and conduction feature points at each mapping electrode position. The waveform relationship includes the waveform similarity and difference of the waveforms. Through the above technical solution, not only can the electrical mapping image be acquired, but also the correlation between each of the aforementioned mapping electrodes and the surrounding adjacent mapping electrodes can be acquired, laying the foundation for accurately and quickly acquiring the abnormal state and abnormal position of the monitored object.

[0052] Further, step S2 includes:

[0053] Step S21: The ECG signal of the monitored object is acquired in real time by the ECG signal acquisition unit, and multiple first waveforms are extracted from the ECG signal, wherein the first waveform is an R wave;

[0054] Step S22: Obtain the maximum value of each first waveform and the maximum potential fluctuation value of the corresponding reference potential range, calculate the first difference between the maximum value and the first threshold, and the second difference between the maximum potential fluctuation value and the second threshold. When the first difference and the second difference corresponding to each first waveform are within the corresponding set range, the analysis result corresponding to the ECG signal is normal; otherwise, the analysis result corresponding to the ECG signal is abnormal. The ECG signal is treated as a noise waveform, and the noise waveform is denoised. The denoised ECG signal and the ECG signal when the analysis result is normal are used as the target waveform.

[0055] Specifically, the ECG signal of the monitored object is acquired in real time by the ECG signal acquisition unit, and the first waveform, i.e., the R wave, is extracted from the ECG signal. The maximum value of the first waveform and the maximum fluctuation value of the corresponding reference potential range are obtained. Since the reference potential range of the R wave is an isoelectric range in the ECG signal waveform and the potential change is small within a cardiac cycle, the maximum fluctuation potential of the reference voltage range and the maximum value of the R wave are used to determine whether there is noise in the ECG signal. When at least one of the first difference and the second difference is not within the corresponding set range, i.e., the first difference is greater than... When the first set range or the second difference is greater than the second set range, the ECG signal is a noise waveform, and the noise waveform is denoised. When both the first difference and the second difference are within their respective set ranges, that is, when the first difference is less than or equal to the first set range and the second difference is less than or equal to the second set range, the ECG signal is free of noise. The noise-free ECG signal and the denoised ECG signal are taken as the target waveform. Through the above technical solution, the accurate target waveform can be obtained, laying the foundation for further accurate identification of anomalies through the target waveform.

[0056] Further, step S3 includes:

[0057] Step S31: Divide each target waveform into multiple sub-waveforms according to waveform type, input the multiple sub-waveforms into the first model, and obtain the first output result. The first model is a machine learning model trained with first learning data. The first learning data includes sub-waveforms corresponding to ECG signals of historical heart disease patients and corresponding disease types stored in the database, as well as sub-waveforms corresponding to ECG signals of normal people.

[0058] Step S32: When the first output result is abnormal, obtain the disease types corresponding to the multiple input sub-waveforms through the first output result, and execute step S4;

[0059] Specifically, the target waveform is divided into multiple sub-waveforms according to waveform type, including P wave, T wave, and QRS wave. These sub-waveforms are then input into the first model, and the first output result is obtained. The first model is a machine learning model trained using sub-waveforms and corresponding disease types from ECG signals of historical heart disease patients and sub-waveforms from ECG signals of normal individuals as training data. By inputting the sub-waveforms of the target waveform into the first model, the first output result can determine whether the target waveform is normal, i.e., whether it is a diseased ECG signal. When the target waveform is abnormal, the corresponding disease type is also output. Since ECG signals can only determine whether a disease is present but not the specific location of the disease, high spatiotemporal resolution electroporation technology can effectively solve this problem. Therefore, by executing step S4, the specific location of the disease and more disease information can be determined through electroporation technology, enabling medical personnel to take timely measures to ensure that the abnormal state of the monitored subject does not worsen further.

[0060] Step S33: When the first output result is normal, obtain the target waveform corresponding to the multiple input sub-waveforms, and take the target waveform as the first normal waveform. Obtain the N consecutive second normal waveforms before the first normal waveform. Input the first normal waveform and the N second normal waveforms as a waveform sequence into the second model and obtain the second output result. The second model is a machine learning model trained with the second learning data.

[0061] Specifically, although the first output result shows that the target waveform is normal, since the ECG signal at a single moment can only reflect limited information about the monitored object, it cannot accurately identify some diseases that are not clearly reflected in the ECG signal. Therefore, when the first output result is normal, the target waveform corresponding to that time is taken as the first normal waveform, and N consecutive second normal waveforms preceding the first normal waveform are obtained. The first normal waveform and the N consecutive second normal waveforms are taken as the waveform sequence, and the waveform sequence is input into the second model to obtain the second output result. Then, the health status of the monitored object is more accurately judged by the change information of each target waveform over time in the waveform sequence. The second model is a machine learning model trained with second learning data. The second learning data consists of historical abnormal electrocardiogram (ECG) data and historical ECG signal sequences within a preset time period prior to the acquisition time of the historical abnormal ECG data. It also includes the disease type corresponding to the historical abnormal ECG data. When the second output result is normal, it indicates that the monitored object is normal. When the second output result is abnormal, it indicates that the monitored object may have abnormalities in the future time period. When the second output result is abnormal, the second output result also outputs the corresponding historical abnormal ECG data and disease type. Through the above technical solution, when the first output result is normal, the monitoring status of the monitored object in the future time period can be predicted more accurately through the waveform sequence.

[0062] Furthermore, the second learning data includes historical abnormal electroencephalogram (EEG) data stored in the database and historical ECG signal sequences within a preset time period prior to the acquisition time of the historical abnormal EEG data, as well as the disease type corresponding to the historical abnormal EEG data.

[0063] Specifically, the second model trained using the second learning data can accurately predict the health status of the monitored subjects in the future. Medical staff can understand the status of the monitored subjects in the future in advance, ensuring that the monitored subjects can accurately and timely obtain their status parameters during transplantation or open-heart surgery.

[0064] Further, step S4 includes:

[0065] Step S41: When the first output result is abnormal, obtain the first acquisition time of the target waveform corresponding to the first output result, obtain the electrical mapping signal acquired by each mapping electrode at the second acquisition time closest to the first acquisition time, extract the electrical mapping waveform of each electrical mapping signal according to the heartbeat, calculate the conduction feature points on each electrical mapping waveform, obtain the electrode conduction relationship based on the temporal and spatial order of the electrical mapping waveforms and conduction feature points of the electrode and other electrodes around the electrode, compare the electrode conduction relationship with the correlation relationship of the corresponding mapping electrode, if the two are consistent, the mapping electrode is a normal electrode, if the two are inconsistent, the mapping electrode is an abnormal electrode, and obtain the abnormal electrode position closest to the excitation point position and other abnormal electrode positions, generate an abnormal position based on the abnormal electrode position and the other abnormal electrode positions and mark it in the electrical mapping image;

[0066] Specifically, when the first output result is abnormal, it indicates that the monitored object may be in an abnormal state, i.e., a disease state. It is necessary to promptly obtain more detailed abnormal information through the electro-gauge measurement unit to facilitate accurate and timely treatment by medical personnel. Since the electro-gauge signal acquired closer to the first acquisition time of the target waveform corresponding to the first output result is more accurate, each electro-gauge signal acquired at the second acquisition time is used as the analysis object. The second acquisition time can be before or after the first acquisition time. Each electro-gauge signal is compared with other adjacent electro-gauge signals to obtain the comparison result. Based on the comparison result, the electrode conduction relationship is obtained. The electrode conduction relationship includes the conduction sequence and conduction speed relationship between the electrode and its four adjacent electrodes. The electrode conduction relationship is compared with the corresponding electrode correlation relationship. When they are consistent, the electrode is normal; when they are inconsistent, the electrode is abnormal. Since the electrical conduction of the monitored object starts from the excitation point, if the conduction is inaccurate at the position close to the excitation point, the subsequent conduction will be abnormal. Therefore, the position of the abnormal electrode closest to the excitation point is obtained first, and other abnormal electrode positions are also obtained. These other abnormal electrode positions are related to the above abnormal electrode positions and are marked as the first abnormal position in the above electrical mapping image. This allows medical staff to take corresponding measures based on the abnormal position and the electrical mapping signal at the abnormal position. Through the above technical solution, the abnormal position and the electrical mapping signal at the abnormal position can be obtained quickly and accurately, which facilitates medical staff to collect corresponding measures in a timely manner and prevent the condition of the monitored object from deteriorating further.

[0067] Step S42: When the second output result is abnormal, obtain the target position in the corresponding electrical measurement image according to the historical abnormal electrical measurement data in the second output result, obtain the corresponding target electrode based on the target position, reduce the acquisition cycle of the electrical measurement unit for the target electrode to the second preset cycle, save the electrical measurement signal acquired by the target electrode, generate a dynamic image in the corresponding range of the electrical measurement image using the saved electrical measurement signal of the target electrode, and mark it in the electrical measurement image;

[0068] Step S43: The user takes corresponding measures based on the abnormal location and the electrical measurement signal at the abnormal location, and identifies the abnormality in real time based on the dynamic image.

[0069] Specifically, when the second output result is abnormal, it indicates that the monitored object may experience an anomaly. Since the historical abnormal electrical mapping data includes not only abnormal data but also the mapping location corresponding to the abnormal data, the target location in the electrical mapping image is obtained through the mapping location in the historical abnormal electrical mapping data in the second output result. The target electrode at the target location is also obtained based on the target location. By reducing the sampling period of the electrical mapping unit, a more refined and accurate electrical mapping signal of the target electrode is obtained, and the electrical mapping signal of the target electrode is saved. All the saved electrical mapping signals of the target electrode are also used as an electrical mapping signal sequence. Based on the electrical mapping signal sequence, the dynamic image is generated in the electrical mapping image, which facilitates the user to identify the abnormal location and take corresponding measures. Through the above technical solution, when the monitored object is transplanted or undergoes open-chest surgery, the real-time status of the monitored object can be obtained in real time, and when the monitored object experiences an anomaly or is about to experience an anomaly, the abnormal location can be accurately and quickly determined, and timely measures can be taken.

[0070] Furthermore, step S4 also includes:

[0071] When the second output result is normal, the acquisition period of the electrical measurement unit is increased to a third preset period, wherein the third preset period is less than the first preset period, and the first preset period is less than the second preset period.

[0072] Specifically, although high spatiotemporal resolution electrical beacon measurement technology can more accurately monitor the state of the monitored object and obtain richer monitoring information, it also has a large data volume, consumes more storage resources, and faces greater data transmission pressure. Furthermore, it requires analog-to-digital conversion during acquisition, which consumes more power and may cause the device to heat up and its temperature to rise. Therefore, in the initial state, the electrical beacon measurement unit acquires electrical beacon measurement signals and creates electrical beacon measurement images at a first preset period. When the second output result is normal, it indicates that the probability of the monitored object being abnormal is low. In order to save storage resources and reduce the rise in device temperature, the acquisition period is increased to the third preset period when the probability of the monitored object being abnormal is low.

[0073] Furthermore, the mapping electrode is flexible and biocompatible.

[0074] The present invention also provides a cardiac transport and open-chest surgery monitoring system based on high spatiotemporal resolution electrical mapping. The system is used to implement the above-described method, as shown in Figure 2. The system includes:

[0075] An electro-labeling unit is used to collect electro-labeling signals from each labeling electrode in the monitored object at a first preset cycle, and to obtain the physiological information of the monitored object through calculation and analysis based on multiple electro-labeling signals. Based on the physiological information and the position information of each labeling electrode, an electro-labeling image and the correlation between the labeling electrodes are generated. The labeling electrodes are disposed on the outer membrane of the monitored object.

[0076] The ECG signal acquisition unit is used to acquire the ECG signal of the monitored object in real time, obtain the analysis result by analyzing the ECG signal in real time, and perform noise reduction processing on the ECG signal when the analysis result is abnormal, and acquire multiple target waveforms based on the ECG signal.

[0077] The discrimination and prediction unit is used to divide each target waveform into multiple sub-waveforms according to the waveform type, input the sub-waveforms into the first model, obtain the first output result, execute step S4 when the first output result is abnormal, obtain the first normal waveform according to the first output result when the first output result is normal, and input the N consecutive second normal waveforms before the first normal waveform into the second model as a waveform sequence, and obtain the second output result.

[0078] The display generation unit is configured to, when the first output result is abnormal, obtain all abnormal electrodes according to the first output result and obtain the abnormal position based on the electrical measurement signal of all the abnormal electrodes; when the second output result is abnormal, obtain the target electrode according to the second output result and generate a dynamic image according to the electrical measurement signal of the target electrode, and mark the abnormal position and the dynamic image in the measurement image.

[0079] In summary, this invention acquires the electrical mapping signal of each mapping electrode at a first preset period using the aforementioned electrical mapping unit, acquires the electrical mapping image based on the position information and conduction information of each mapping electrode, and obtains the correlation between the mapping electrodes. The mapping electrodes are placed on the epicardium of the heart. The electrical mapping unit is a high-resolution multi-channel mapping unit capable of simultaneously monitoring various locations of the heart, laying the foundation for accurately and quickly acquiring the abnormal state and location of the monitored object. The ECG signal acquisition unit acquires the ECG signal of the monitored object in real time and obtains the target waveform. Multiple sub-waveforms corresponding to the target waveform are input into the first model, and the first output result is obtained. It is determined whether the target waveform is normal. When the first output result is abnormal, each electrical mapping signal acquired at the second acquisition time is compared with four adjacent electrical mapping signals. The comparison is performed to obtain the comparison results. Based on the comparison results, the electrode conduction relationship is obtained and compared with the corresponding electrode correlation relationship. The abnormal electrode position closest to the excitation point and other abnormal electrode positions are obtained, thereby obtaining the abnormal position. When the first output result is normal, the first normal waveform and the previous N consecutive second normal waveforms are input into the second model to obtain the second output result. When the second output result is abnormal, the target position and target electrode are obtained through the second output result. By reducing the sampling period of the electrical mapping unit, a more refined and accurate electrical mapping signal of the target electrode is obtained. The electrical mapping signal of the target electrode is also saved and a dynamic image is generated and marked in the electrical mapping image. Through the cooperation of the above technical solutions, richer monitoring information is obtained, which makes it easier for users to quickly and accurately identify abnormal positions and take corresponding measures.

[0080] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] The above-described embodiments are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0082] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for monitoring cardiac transport and open-chest surgery based on high spatiotemporal resolution electrical mapping, characterized in that, The method includes the following steps: Step S1: The electro-mapping signal of each mapping electrode in the monitored object is collected by the electro-mapping unit at a first preset cycle, and the physiological information of the monitored object is obtained by calculation and analysis based on multiple electro-mapping signals. Based on the physiological information and the position information of each mapping electrode, an electro-mapping image and the correlation between the mapping electrodes are generated, wherein the mapping electrodes are set on the outer membrane of the monitored object. Step S2: The ECG signal of the monitored object is acquired in real time through the ECG signal acquisition unit. The analysis result is obtained by analyzing the ECG signal in real time. When the analysis result is abnormal, the ECG signal is denoised and multiple target waveforms are obtained based on the ECG signal. Step S3: Divide each target waveform into multiple sub-waveforms according to waveform type, and input the sub-waveforms into the first model to obtain the first output result. If the first output result is abnormal, execute step S4. If the first output result is normal, obtain the first normal waveform according to the first output result. Also, input the N consecutive second normal waveforms before the first normal waveform as a waveform sequence into the second model and obtain the second output result. Step S4: When the first output result is abnormal, obtain all abnormal electrodes according to the first output result, and obtain the abnormal position based on the electrical measurement signal of all the abnormal electrodes. When the second output result is abnormal, obtain the target electrode according to the second output result, and generate a dynamic image according to the electrical measurement signal of the target electrode. Mark the abnormal position and the dynamic image in the electrical measurement image.

2. The method according to claim 1, characterized in that, The calibration electrode in the electrical calibration unit has at least 32 channels, and the distance between electrode points in each calibration electrode is less than or equal to 4 mm.

3. The method according to claim 1, characterized in that, Step S1 includes: Step S11: The electrical measurement unit acquires the electrical measurement signal of each measurement electrode at a first preset period. Based on the setting position of each measurement electrode and the corresponding electrical measurement signal, the conduction information of the monitored object is acquired. The conduction information includes excitation point, conduction direction, conduction velocity, depolarization dispersion and repolarization dispersion, conduction phase and spectral characteristics. Step S12: Obtain the electrical mapping image based on the position information of each mapping electrode and the conduction information. Also, extract the electrical mapping waveform according to the heartbeat of each electrical mapping signal, calculate the conduction feature points on each electrical mapping waveform, and obtain the waveform relationship and conduction relationship based on the temporal and spatial order of the electrical mapping waveform and the conduction feature points. The correlation relationship includes the waveform relationship and the conduction relationship.

4. The method according to claim 1, characterized in that, Step S2 includes: Step S21: The ECG signal of the monitored object is acquired in real time by the ECG signal acquisition unit, and multiple first waveforms are extracted from the ECG signal. The first waveforms are R waves and other ECG waveform features. Step S22: Obtain the maximum value of each first waveform and the maximum potential fluctuation value of the corresponding reference potential range, calculate the first difference between the maximum value and the first threshold, and the second difference between the maximum potential fluctuation value and the second threshold. When the first difference and the second difference corresponding to each first waveform are within the corresponding set range, the analysis result corresponding to the ECG signal is normal; otherwise, the analysis result corresponding to the ECG signal is abnormal. The ECG signal is treated as a noise waveform, and the noise waveform is denoised. The denoised ECG signal and the ECG signal when the analysis result is normal are used as the target waveform.

5. The method according to claim 1, characterized in that, Step S3 includes: Step S31: Divide each target waveform into multiple sub-waveforms according to waveform type, input the multiple sub-waveforms into the first model, and obtain the first output result. The first model is a machine learning model trained with first learning data. The first learning data includes sub-waveforms corresponding to ECG signals of historical heart disease patients and corresponding disease types stored in the database, as well as sub-waveforms corresponding to ECG signals of normal people. Step S32: When the first output result is abnormal, obtain the disease types corresponding to the multiple input sub-waveforms through the first output result, and execute step S4; Step S33: When the first output result is normal, obtain the target waveform corresponding to the multiple input sub-waveforms, and take the target waveform as the first normal waveform. Obtain the N consecutive second normal waveforms before the first normal waveform. Input the first normal waveform and the N second normal waveforms as a waveform sequence into the second model and obtain the second output result. The second model is a machine learning model trained with the second learning data.

6. The method according to claim 5, characterized in that, The second learning data includes historical abnormal electroencephalogram (EEG) data stored in the database and historical ECG signal sequences within a preset time period prior to the acquisition time of the historical abnormal EEG data, as well as the disease type corresponding to the historical abnormal EEG data.

7. The method according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: When the first output result is abnormal, obtain the first acquisition time of the target waveform corresponding to the first output result, obtain the electrical mapping signal acquired by each mapping electrode at the second acquisition time closest to the first acquisition time, extract the electrical mapping waveform of each electrical mapping signal according to the heartbeat, calculate the conduction feature points on each electrical mapping waveform, obtain the electrode conduction relationship based on the temporal and spatial order of the electrical mapping waveforms and conduction feature points of the electrode and other electrodes around the electrode, compare the electrode conduction relationship with the correlation relationship of the corresponding mapping electrode, if the two are consistent, the mapping electrode is a normal electrode, if the two are inconsistent, the mapping electrode is an abnormal electrode, and obtain the abnormal electrode position closest to the excitation point position and other abnormal electrode positions, generate an abnormal position based on the abnormal electrode position and the other abnormal electrode positions and mark it in the electrical mapping image; Step S42: When the second output result is abnormal, obtain the target position in the corresponding electrical measurement image according to the historical abnormal electrical measurement data in the second output result, obtain the corresponding target electrode based on the target position, reduce the acquisition cycle of the electrical measurement unit for the target electrode to the second preset cycle, save the electrical measurement signal acquired by the target electrode, generate a dynamic image in the corresponding range of the electrical measurement image using the saved electrical measurement signal of the target electrode, and mark it in the electrical measurement image; Step S43: The user takes corresponding measures based on the abnormal location and the electrical measurement signal at the abnormal location, and identifies the abnormality in real time based on the dynamic image.

8. The method according to claim 7, characterized in that, Step S4 further includes: When the second output result is normal, the acquisition period of the electrical measurement unit is increased to a third preset period, wherein the third preset period is less than the first preset period, and the first preset period is less than the second preset period.

9. The method according to claim 1, characterized in that, The calibration electrode is flexible and biocompatible.

10. A cardiac transport and open-chest surgery monitoring system based on high spatiotemporal resolution electrical mapping, the system being used to implement the method as described in any one of claims 1-8, characterized in that, The system includes: An electro-labeling unit is used to collect electro-labeling signals from each labeling electrode in the monitored object at a first preset cycle, and to obtain the physiological information of the monitored object through calculation and analysis based on multiple electro-labeling signals. Based on the physiological information and the position information of each labeling electrode, an electro-labeling image and the correlation between the labeling electrodes are generated. The labeling electrodes are disposed on the outer membrane of the monitored object. The ECG signal acquisition unit is used to acquire the ECG signal of the monitored object in real time, obtain the analysis result by analyzing the ECG signal in real time, and perform noise reduction processing on the ECG signal when the analysis result is abnormal, and acquire multiple target waveforms based on the ECG signal. The discrimination and prediction unit is used to divide each target waveform into multiple sub-waveforms according to the waveform type, input the sub-waveforms into the first model, obtain the first output result, execute step S4 when the first output result is abnormal, obtain the first normal waveform according to the first output result when the first output result is normal, and input the N consecutive second normal waveforms before the first normal waveform into the second model as a waveform sequence, and obtain the second output result. The display generation unit is configured to, when the first output result is abnormal, obtain all abnormal electrodes according to the first output result and obtain the abnormal position based on the electrical measurement signal of all the abnormal electrodes; when the second output result is abnormal, obtain the target electrode according to the second output result and generate a dynamic image according to the electrical measurement signal of the target electrode, and mark the abnormal position and the dynamic image in the measurement image.

Images