72 results about "Electrocardiogram QRS complex" patented technology

Techniques are disclosed for segmenting electrocardiogram (ECG) signals. In one example, a method to segment an electrocardiogram (ECG) signal may include detecting consecutive heartbeats in an ECG signal. The method also includes segmenting the ECG signal into multiple ECG segments surrounding the detected consecutive heartbeats and generating an ECG data set by joining consecutive ECG segments. The generated the ECG data set represents the detected heartbeats. In some such examples, each ECG segment is of a duration to include a QRS complex, a P wave, and a T wave.

The invention discloses an ultra-high heart rate electrocardio acquisition system, which comprises a signal acquisition unit adopting an ADS131E08 chip and supporting 8 channels, a 24-bit delta-sigma ADC (Analog to Digital Converter) and programmable gain amplification; the dynamic sampling rate adjusting unit is used for dynamically adjusting the sampling rate between 1kSPS and 64kSPS according to the heart rate change, and the sampling rate is increased to be greater than or equal to 2kSPS when the heart rate exceeds 200 times per minute; a low-noise design circuit has a common-mode rejection ratio greater than or equal to 110dB, a dynamic range greater than or equal to 118dB and total harmonic distortion less than or equal to-90dB, and power frequency interference is suppressed; the morphological enhancement module is used for enhancing QRS wave group characteristics by using digital morphological filtering; the multi-lead fusion module is used for fusing multi-lead signals through time sequence alignment and R-wave phase difference analysis; and the anti-interference module is integrated with a hardware comparator, and is used for lead falling detection and dynamic digital notch filtering. The system is suitable for researches on myocardial ischemia, arrhythmia and drug cardiotoxicity. Compared with the prior art, the device has the advantages of being simple in structure, low in cost, high in precision, high in reliability and the like, and can effectively solve the problem of animal ultrahigh heart rate electrocardio collection.

The invention discloses a coronary artery lesion risk prediction method, a coronary artery lesion risk processing device, a coronary artery lesion risk prediction system and a computer readable storage medium. Obtaining a point sequence according to high-frequency QRS wave group data obtained by the exercise electrocardiogram data; aiming at a point sequence corresponding to any electrocardiogram lead, taking any sampling point in a plurality of sampling points in the point sequence as a current reference sampling point in a traversal cycle, and traversing sampling points in a preset time interval from the current reference sampling point, determining whether a first sampling point and a second sampling point meeting a preset condition exist in the preset time interval, wherein the first sampling point is earlier than the second sampling point in time sequence; and if the preset condition is met, determining that the high-frequency QRS wave group data has waveform characteristics indicating the coronary artery lesion, thereby determining the possibility of the coronary artery lesion. Compared with a previous scheme, the scheme has the advantage that the qualitative accuracy of coronary artery lesion is improved.

The disclosure relates to a computer-implemented method for monitoring diaphragmatic response to phrenic nerve stimulation. The method comprises receiving in real-time a diaphragmatic CMAP signal. The method comprises computing a baseline value of a characteristic of the CMAP signal. The characteristic represents a diaphragmatic response intensity to a phrenic nerve stimulation. The method comprises determining a threshold value of the characteristic, representing a boundary of values of the characteristic indicative of upcoming diaphragmatic palsy. The determining of the threshold value includes shifting the baseline value. The method comprises receiving in real-time a ECG signal. The method comprises repeating in real-time: detecting a QRS complex in the ECG signal, monitoring the CMAP signal, computing a real-time value of the characteristic, comparing the real-time value to the threshold value, and outputting an alert when the threshold is passed. The real-time value of the characteristic is asynchronous to the QRS complex.

The present disclosure presents arrhythmia analysis systems and methods. One such method comprises processing an acquired ECG waveform signal to remove noise artifacts and form a denoised ECG waveform signal; processing the denoised ECG waveform signal to remove low quality segments and form a high quality ECG waveform signal; analyzing the high quality ECG waveform to detect a presence of a beat-independent ventricular arrhythmia; processing the denoised ECG signal to extract beat (R-peak) locations corresponding to QRS complexes from the denoised ECG signal; analyzing the denoised ECG signal to detect a presence of a beat-dependent ventricular arrhythmia based on the extracted beat (R-peak) locations; analyzing the denoised ECG signal to detect a presence of one or more supraventricular arrhythmias based on the extracted beat locations of the ECG signal; and outputting a report containing one or more arrhythmias detected by the analyzing steps. Other methods / systems are also provided.

The invention discloses an electrocardio data processing and coronary heart disease risk prediction method, device and system and a medium. The method comprises the steps of obtaining exercise electrocardio data output through at least one electrocardiogram lead; analyzing the exercise electrocardiogram data to obtain a heart rate sequence corresponding to each electrocardiogram lead; extracting a QRS wave group corresponding to each heart beat from the exercise electrocardio data; dividing a plurality of heart rate intervals according to the obtained heart rate sequence; according to the heart rate interval to which the heart rate corresponding to each QRS wave group belongs, classifying the QRS wave group into a group corresponding to the corresponding heart rate interval; determining an average QRS wave group corresponding to each heart rate interval according to all the QRS wave groups in each group; extracting the high-frequency energy of the average QRS wave group corresponding to each heart rate interval; and determining an energy sequence according to the high-frequency energy corresponding to each heart rate interval. According to the scheme, high-frequency components and dynamic load information which are more sensitive to ischemia are utilized, so that the detection rate and the identification capability of coronary heart diseases, particularly early and mild lesions, can be remarkably improved.

The invention relates to an electrocardiosignal processing method based on an intelligent filtering algorithm, which adopts a segmented filtering processing strategy, and can implement targeted filtering measures according to different types of noise characteristics on the basis of completely retaining the original form and key information of a QRS complex wave, such as low-frequency noise of a non-QRS wave band. According to the method, wavelet transformation and other methods are adopted, a low-pass filter is adopted for high-frequency noise, Kalman filtering is combined with an RC filter for local self-adaptive noise reduction for an abnormal wave band, signal distortion possibly caused by global filtering is avoided through segmentation processing, and key feature waveforms such as a QRS wave group of an original signal are more accurately reserved; meanwhile, the distortion degree of the whole signal is remarkably reduced, and the problems of information loss and signal distortion possibly caused by a traditional filtering method are avoided.

The invention belongs to the technical field of electrocardiosignal classification, and discloses an electrocardiosignal quality automatic identification and classification method, which comprises the following steps: carrying out discrete wavelet decomposition on an electrocardiosignal to obtain a low-frequency sub-band, a reconstructed sub-band and a high-frequency sub-band, and carrying out time domain feature extraction on the low-frequency sub-band, the reconstructed sub-band and the high-frequency sub-band; according to the method, wavelet analysis, time domain feature extraction and a fault diagnosis technology are organically combined, and automatic identification and classification of electrocardiogram signal quality are achieved on the premise of not depending on event features such as QRS complex waves and RR intervals.

The invention discloses an electrocardio feature point positioning method based on double U-Net fused long and short range context information, comprising: preprocessing an electrocardio signal, including re-sampling to a unified sampling rate, and removing noise interference; segmenting the electrocardiosignal, wherein the electrocardiosignal is segmented into a single-cardiac-beat segment and a neighbor multi-cardiac-beat segment based on the R peak position; data enhancement operation is applied to the segmented cardiac beat segments; using double U-Net to extract features, including a first U-Net to extract local semantic features of a single cardiac beat segment and a second U-Net to extract global semantic features of a multi-cardiac beat segment; fusing the local semantic features and the global semantic features through a cross-level dual gating module to generate purified fused features; and positioning feature points of the electrocardiosignal based on the fusion features, wherein the feature points comprise the positions of P waves, QRS wave groups and T waves. According to the invention, the precision and robustness of feature point positioning are improved.

A method, device, system and medium for electrocardio data processing and coronary heart disease risk prediction, motion electrocardio data output through at least one electrocardio lead is acquired; the motion electrocardio data is analyzed to obtain a heart rate sequence corresponding to each electrocardio lead; each QRS complex corresponding to each heartbeat is extracted from the motion electrocardio data; a plurality of heart rate intervals are divided according to the obtained heart rate sequence; each QRS complex is classified into a group corresponding to a heart rate interval according to the heart rate interval to which the heart rate corresponding to the QRS complex belongs; the average QRS complex corresponding to each heart rate interval is determined according to all QRS complexes in each group; the high-frequency energy of the average QRS complex corresponding to each heart rate interval is extracted; and an energy sequence is determined according to the high-frequency energy corresponding to each heart rate interval. The present scheme uses high-frequency components and dynamic load information which are more sensitive to ischemia, and can significantly improve the detection rate and discrimination ability for coronary heart disease, especially early and mild lesions.

The present invention proposes a method for reconstructing an ECG signal based on hybrid optimization and multimodal feature fusion, the method comprising: obtaining a 12-lead ECG signal, processing the 12-lead ECG signal in sequence through a linear regression model, a genetic algorithm, and a simulated annealing algorithm to obtain an optimal three-lead ECG signal, processing the optimal three-lead ECG signal in sequence through a one-dimensional convolutional layer and a maximum pooling layer to obtain time domain features, fusing the time domain features, frequency domain features, and expert features into a multimodal feature to obtain fused features, and inputting the fused features into a Transformer mechanism for processing to obtain a reconstructed ECG signal. The present invention achieves significant results in long-range time series modeling and local waveform detail optimization. Traditional CNN / RNN is limited by the local receptive field or gradient vanishing problem, making it difficult to balance the global rhythm and local morphology. The present invention adopts a QRS-aware Transformer architecture, combined with multi-head self-attention and a nonlinear feedforward network, to reduce the error in the width of the QRS complex.

The application relates to the technical field of electrocardiosignal processing, and discloses a monitoring electrocardio data analysis method based on online monitoring, wherein the method comprises the following steps: performing multistage filtering pretreatment on an original electrocardio signal; detecting a QRS complex and extracting an RR interval sequence; extracting time domain statistical features, frequency domain features and wavelet coefficients to form an electrocardio feature vector; inputting the electrocardio feature vector and an electrocardio signal segment into an atrial fibrillation detection model containing a signal feature learning branch and a sequence feature learning branch, and outputting an atrial fibrillation detection result; and generating an alarm information based on the detection result and pushing the alarm information to a medical terminal. Through atrial fibrillation load statistics and stroke risk grade evaluation, the single abnormality detection result is expanded into a continuous risk quantization index, a coherent analysis link from abnormality identification to risk evaluation is provided for clinical doctors, complete data storage is associated with a patient identifier and a time stamp, all analysis processes can be traced back, and the needs of clinical audit and department review are met.

Disclosed are a myocardial bridge risk prediction method, a processing device, a system and a computer readable storage medium. The method comprises the following steps: determining a point sequence according to candidate high-frequency QRS complex data in which a waveform feature indicating coronary artery lesion does not exist in exercise electrocardiogram data, and traversing the sampling points in the point sequence. If there are two sampling points that meet the preset condition, it is determined that there is a myocardial bridge risk. The scheme can improve the specificity and sensitivity of auxiliary diagnosis from the electrophysiological mechanism in a non-invasive environment, and is convenient and effective.

According to one aspect of the present invention, provided is a method for classifying an electrocardiogram signal, the method comprising the steps of: converting an electrocardiogram signal into first graph data including a P node corresponding to a P wave, a QRS node corresponding to a QRS complex, and a T node corresponding to a T wave; and outputting the classification result of the electrocardiogram signal by processing the first graph data by using a graph convolutional network (GCN)-based classification model.

The invention relates to the technical field of sleep-aiding monitoring, in particular to a personalized sleep-aiding system and method based on artificial intelligence. The method comprises the steps that multi-source data such as sleep videos and ECG signals of a user are collected, the advanced graph neural network technology is used for conducting feature extraction and analysis on the sleep videos, the sleep stage of the user is accurately determined, meanwhile, QRS complex wave information in the ECG signals is extracted to obtain a breathing oscillogram of the user, the breathing standard reaching coefficient is calculated, and the sleep stage of the user is determined. The sleep state parameter is combined to calculate the sleep state quality coefficient, finally, the sleep environment parameter of the user is dynamically adjusted according to the respiration standard coefficient and the sleep state quality coefficient, personalized sleep aiding service is provided for the user, and therefore the sleep quality of the user is improved, and the sleep condition of the user is improved.

Embodiments of the present application disclose an atrial fibrillation detection method and device, a storage medium and a computer device. The method comprises: receiving an ECG signal sequence of a preset length and performing a preprocessing operation on the ECG signal; determining a QRS complex position based on the processed ECG signal; extracting a plurality of characteristic parameters according to the QRS complex position; and identifying and classifying the plurality of characteristic parameters based on a classifier. The present application simultaneously utilizes two features of an atrial fibrillation waveform, i.e., irregular changes in an RR interval and a baseline of a heartbeat interval being an irregular continuous high-frequency low-amplitude fibrillation wave, to detect and analyze an atrial fibrillation signal. Specifically, by determining a QRS complex position and extracting a plurality of characteristic parameters based on the position, the change rule of the RR interval and the related plurality of characteristic parameter values of the fibrillation wave are obtained. Further, a support vector machine (SVM) classifier is used to perform binary classification prediction on the above characteristic parameters, thereby achieving detection and identification of the atrial fibrillation signal and greatly improving the accuracy of the analysis result of the atrial fibrillation signal.

Embodiments of a wearable cardioverter defibrillator (WCD) system include a support structure for wearing by an ambulatory patient, a posture detector and at least one processor. When worn, the support structure maintains electrodes on the patient's body, and using the posture detector and the patient's ECG received via the electrodes, the processor determines the patient's posture, formulates posture-based templates of QRS complexes, and the patient's heart rate. The processor can use these determinations to distinguish between VT and SVT and make no-shock, and shock decisions.

The invention relates to the technical field of intelligent wearable equipment, and provides an ECG electrocardio measurement and analysis method of an intelligent ring based on an AI model. The method is applied to the intelligent ring and comprises the following steps: acquiring an original signal and performing multi-band decomposition on the original signal; identifying a characteristic frequency band corresponding to a plurality of noise types in the decomposed original signal; the noise types at least comprise motion artifacts, muscle vibration and electromagnetic interference; extracting ECG key features from the decomposed original signal according to an attention mechanism, wherein the ECG key features at least comprise an RR interval and a QRS wave group; filtering the characteristic frequency band according to the ECG key characteristics, and outputting an ECG characteristic signal; inputting the ECG characteristic signal into a pre-trained AI model, and outputting a signal quality score; and if the ECG characteristic signal is determined to be qualified according to the signal quality score, outputting the ECG characteristic signal for ECG equivalent index calculation.

Disclosed is a method for obtaining a start point and an end point of a QRS complex by using an imaginary number. The method of obtaining a start point and an end point of a QRS complex by using an imaginary number comprises: receiving, by a receiving unit, a measured electrocardiogram signal, performing, by a transform unit, Hilbert transform on the electrocardiogram signal, and obtaining, by a measurement unit, the amplitude of the electrocardiogram signal by creating a phase space map on the basis of the Hilbert transformed electrocardiogram signal, wherein a vertex of an imaginary part representing the start point and the end point of the QRS complex exists in the phase space map, and the vertex exists in a phase space region of the QRS complex.

A method to monitor a patient's heart health is described. The method may include processing at least one electrocardiogram (ECG) signal and diagnosing an episode of nonsustained ventricular tachycardia (NSVT) based at least in part on the processing of the at least one ECG signal. In some embodiments, the NSVT episode may satisfy an NSVT time duration and a QRS criterion. The NSVT time duration may be between 5 seconds and 15 seconds. In some instances, the QRS criterion may be a temporary QRS template of two sequential incoming QRS complexes. In some embodiments, the method may determine a similarity between the temporary QRS template and at least two subsequent QRS complexes by calculating a feature correlation coefficient between the QRS template and the subsequent QRS complexes.

The application provides an arrhythmia signal detection method and system based on expert knowledge, wherein the method comprises the following steps: performing signal filtering on an acquired electrocardio signal to filter out high-frequency noise and baseline drift in the electrocardio signal; performing P-QRS-T positioning detection on the signal-filtered electrocardio signal to obtain a QRS complex and P / T wave; performing expert-knowledge-based feature mapping on the obtained QRS complex and P / T wave to obtain a category feature of the electrocardio signal; comparing the obtained category feature of the electrocardio signal with a preset threshold to determine an arrhythmia signal, thereby completing detection of the arrhythmia signal. Meanwhile, a corresponding terminal and medium are provided. The application improves the detection accuracy; fully considers the morphology of an abnormal heartbeat and the timing of positioning the P / T wave, can effectively avoid the case that the P-QRS-T positioning is inaccurate due to the abnormal heartbeat, has high robustness, and has low computational complexity.

The application provides a processing method and device of a QRS complex anomaly classification model and processing equipment. The QRS complex anomaly classification model is constructed by introducing a QRS complex anomaly classification mechanism based on 4 leads or 8 leads. Experimental results show that the detection accuracy of different types of abnormal QRS complexes is significantly improved in the 8-lead format. In addition, due to the simplification of data, especially in the 4-lead format, the application cost in terms of data processing time, data application time and data storage time is obviously improved, and the personnel workload in clinical work is also significantly reduced, so the application value is better.

The invention relates to the technical field of medical instruments, in particular to a heart health state assessment method, a processing device, a system and a computer readable storage medium. Obtaining a first maximum voltage according to first high-frequency QRS wave group data obtained according to the exercise electrocardio data, obtaining a waveform type of a first high-frequency QRS wave group corresponding to each electrocardiogram lead, obtaining a first lead positive index, and obtaining a second maximum voltage according to a second high-frequency QRS wave group number obtained according to the resting electrocardio data, and obtaining a wave crest number corresponding to each electrocardiogram lead; a high-frequency form index, a second lead positive index and a QRS time limit; respectively obtaining a cardiopulmonary function index, a vascular response capability index and a myocardial cell vitality index based on the data; and determining a heart health assessment result according to the cardiopulmonary function index, the vascular response capability index and the myocardial cell vitality index. According to the scheme, the evaluation dimensionality is comprehensive, the defect of single-dimensional evaluation in the prior art is overcome, and the requirement for integrated evaluation of heart health clinically is met.

Techniques are disclosed for segmenting electrocardiogram (ECG) signals. In one example, a method to segment an electrocardiogram (ECG) signal may include detecting consecutive heartbeats in an ECG signal. The method also includes segmenting the ECG signal into multiple ECG segments surrounding the detected consecutive heartbeats and generating an ECG data set by joining consecutive ECG segments. The generated the ECG data set represents the detected heartbeats. In some such examples, each ECG segment is of a duration to include a QRS complex, a P wave, and a T wave.

Techniques that include applying machine learning models to episode data, including a cardiac electrogram, stored by a medical device are disclosed. In some examples, based on the application of one or more machine learning models to the episode data, processing circuitry derives, for each of a plurality of arrhythmia type classifications, class activation data indicating varying likelihoods of the classification over a period of time associated with the episode. The processing circuitry may display a graph of the varying likelihoods of the arrhythmia type classifications over the period of time. In some examples, processing circuitry may use arrhythmia type likelihoods and depolarization likelihoods to identify depolarizations, e.g., QRS complexes, during the episode.

The invention discloses a myocardial bridge risk prediction method, a processing device, a system and a computer readable storage medium, and the method comprises the steps: determining a point sequence according to candidate high-frequency QRS wave group data in motion electrocardio data, and if two sampling points meeting the preset condition exist, determining that the myocardial bridge risk exists. According to the scheme, the auxiliary diagnosis specificity and sensitivity can be improved from the electrophysiological mechanism in a non-invasive environment, and convenience and effectiveness are achieved.

Methods and systems for dynamically modifying pacing timing and backup pacing delivery in cardiac stimulation devices include applying pacing impulses, measuring corresponding responses, and, based on such responses, automatically modifying timing or operational settings of the stimulation device to improve pacing functionality. Among other things, the approaches described herein reduce unnecessary backup pacing impulses in HIS bundle pacing applications, facilitate fusion in bundle branch block applications, and automatically enable or disable backup pacing in response to achieving QRS complex correction.

The invention relates to an information detection method and device, equipment, a storage medium and a program product. According to one embodiment of the invention, the method comprises the following steps: transmitting a wireless sensing signal to a detected object based on a wireless sensing assembly, and receiving a reflected signal of the wireless sensing signal, the reflected signal comprising a signal transmitted after the wireless sensing signal is in contact with the detected object; determining a target electrocardiosignal waveform of the detected object based on the reflected signal and the wireless sensing signal; identifying a QRS wave group from the target electrocardiosignal waveform; and in response to the identified at least two QRS wave groups, determining RR interval information of the detected object based on the at least two QRS wave groups. According to the method, the RR interval information of the QRS wave group in the electrocardiosignal can be accurately detected, and the requirement for finer health information detection is met.

Embodiments of a wearable cardioverter defibrillator (WCD) system include a support structure for wearing by an ambulatory patient, a posture detector and at least one processor. When worn, the support structure maintains electrodes on the patient's body, and using the posture detector and the patient's ECG received via the electrodes, the processor determines the patient's posture, formulates posture-based templates of QRS complexes, and the patient's heart rate. The processor can use these determinations to distinguish between VT and SVT and make no-shock, and shock decisions.

An embodiment of the present invention relates to a method and device for identifying the working state of a pacemaker based on electrocardiogram signals. The method includes: acquiring electrocardiogram signal data; identifying pacing pulses to generate first pacing pulse data, extracting the time information of the pulse peak points to generate first peak point data, and counting the number of pacing pulses as the first total number; identifying P waves to generate first P wave data, extracting the time information of the P wave peak points to generate second peak point data, and calculating the PP interval to generate a first interval data sequence; identifying QRS complexes to generate first QRS complex data, and extracting the time information of the R point to generate first R point data; calculating the cardiac cycle intervals to generate a second interval data sequence; when the first total number is empty, the working state of the pacemaker is that there is no pulse information in the pacemaker; when the first total number is not empty, the working state of the pacemaker is identified according to the pacemaker position information. The embodiment of the present invention provides a more accurate and convenient identification means for correctly judging the working state of the pacemaker.