90 results about "Electrocardiogram analysis" patented technology

The invention relates to the technical field of health monitoring, and discloses a patient health monitoring method and system based on dynamic electrocardiogram analysis, and the method comprises the steps: synchronously obtaining multi-lead dynamic electrocardiogram data continuously collected by a patient within a preset duration, and related physiological parameters of exercise intensity, respiratory rate and body position change; performing dynamic self-adaptive preprocessing on the dynamic electrocardiogram data based on the associated physiological parameters to obtain standardized electrocardiosignals; extracting a multi-dimensional characteristic parameter set from the standardized electrocardiosignal, and sampling according to a preset time window to generate a characteristic parameter sequence with a timestamp; and inputting the characteristic parameter sequence into a dynamic optimization analysis model capable of iteratively updating parameters through real-time physiological parameter feedback, and performing graded evaluation on the health state of the patient to generate an evaluation result. The system corresponds to the method. By adopting the method and the system, the accuracy of dynamic electrocardiogram monitoring and the evaluation refinement level meet the dynamic monitoring requirement of cardiovascular health.

Artificial intelligence enabled disease profiling is described. An electrocardiogram analysis module is configured to derive disease vectors for a plurality of diseases using electrocardiogram training data from both disease-negative and disease-positive individuals. A standardized input is generated, via a data preprocessor of the electrocardiogram analysis module, from an electrocardiogram recorded from an individual. The standardized input is encoded, by a deep learning autoencoder of the electrocardiogram analysis module, into an embedding, the embedding being a lower-dimensional latent space representation of features extracted from the standardized input. At least one disease risk score for the individual is generated, by a statistical modeling algorithm of the electrocardiogram analysis module, for the plurality of diseases based on the embedding and the disease vectors.

The invention discloses an electrocardiogram analysis method and device based on a deep learning model and a medium, and relates to the field of deep learning, and the method comprises the steps: carrying out the preprocessing of an electrocardiogram, and carrying out the noise suppression; inputting the electrocardiosignals into a pre-trained deep learning model, extracting time features and spatial features, and performing cross-modal feature fusion; synchronously executing a plurality of anomaly detection tasks, and synchronously executing a time sequence prediction task; aiming at the abnormal detection result, correcting the abnormal detection result according to the clinical information and the time sequence prediction result; and outputting an analysis result corresponding to the electrocardiogram. A complete closed loop is formed from signal processing to feature extraction, multi-task analysis and result correction, manual intervention links are reduced, electrocardiogram analysis time is remarkably shortened, result consistency is guaranteed, end-to-end automation is achieved, and efficiency is improved.

Methods and systems for automated electrocardiogram (ECG) analysis using neural networks, enhancing the accuracy of beat-by-beat cardiac monitoring. The system utilizes a Generative Adversarial Network (GAN) and beat classifiers to analyze ECG data and detect conditions various beast properties of an ECG at a discrete level. Additional neural networks may be trained to detect beat based conditions such as premature atrial contractions (PACs) and premature ventricular contractions (PVCs). The GAN generates realistic ECG beats, while classifiers detect abnormalities. Additional transformers may be trained to detect rhythm based conditions such as AFib and Aflutter. Methods and Systems support real-time cardiac health insights and integrates with ECG devices for continuous monitoring, offering a robust solution for improving diagnostic accuracy.

The invention discloses a paper electrocardiogram voltage value reconstruction method and system based on a dynamic diffusion threshold value, and belongs to the technical field of electrocardiogram analysis. Comprising the following steps: acquiring a standard paper electrocardiogram and a to-be-processed paper electrocardiogram, and extracting paper electrocardiogram parameters; based on a preset threshold value, carrying out iterative optimization to obtain an optimal threshold value so as to carry out binarization processing on the to-be-processed paper electrocardiogram to obtain a binarized paper electrocardiogram; the positioning of the electrocardiogram waveform lead position is realized; the electrocardio waveform information of the lead image area is converted into a digital signal; converting the obtained digital signal into a voltage signal; and resampling the voltage signal to obtain a digitalized reconstructed electrocardiosignal. Compared with the prior art, the method has the advantages that the image processing threshold value can be dynamically adjusted according to the local features of the paper electrocardiogram, so that the edge of the electrocardiogram waveform in the digitization process is clearer, and it is ensured that the digitization data can accurately reflect the original information of the paper electrocardiogram.

The invention relates to the technical field of electrocardiosignal analysis, and discloses a long-sequence electrocardiosignal disease recognition system based on a Transform architecture. The core defects that in traditional electrocardiogram analysis, waveform integrity is damaged by fixed window segmentation, a lead space topological relation is neglected, and long sequence modeling efficiency is low are overcome, a P-QRS-T waveform structure is completely reserved through the heart beat adaptive segmentation technology, and the fixed window truncation risk is eliminated; the lead anatomical topology and the space-time coding are fused, and multi-lead electrophysiological association is modeled; long sequence efficient processing is realized based on hierarchical sparse Transform, and the recognition sensitivity of complex pathologies such as arrhythmia and myocardial ischemia is improved; in combination with gradient directional regulation and control and a streaming processing mechanism, the clinical real-time requirement is met while the diagnosis accuracy is guaranteed, and finally, reliable, efficient and universal intelligent decision support is provided for early warning of heart diseases through lightweight deployment of an adaptive mobile terminal.

A cardiac rhythm condition recognition method based on a seismocardiogram signal comprises the steps that 1, the seismocardiogram signal and a gold standard electrocardiogram signal are collected, and filtering and standardization preprocessing are carried out on the seismocardiogram signal and the gold standard electrocardiogram signal; step 2, automatically labeling the heart rhythm condition based on the gold standard electrocardiogram signal: extracting at least one heart rhythm feature through an electrocardiogram analysis algorithm, and labeling the heart rhythm condition of the electrocardiogram signal based on a multi-evidence fusion labeling rule; step 3, mapping the labeling result of the electrocardiogram signal to the synchronous seismocardiogram signal: mapping the electrocardiogram labeling result to a corresponding time window of the synchronous seismocardiogram signal through a time alignment and priority mapping strategy, and endowing each seismocardiogram signal time window with a heart rhythm condition label; 4, constructing a deep learning model fusing a residual convolutional neural network and a long-short-term memory network, and training by using the marked seismocardiogram signal data; and 5, training model deployment and heart rhythm condition real-time identification.

A system for interactive ECG monitoring is described. The system includes a data repository storing pre-processed ECG data. The pre-processed ECG data is associated with historical data, real-time data, or both derived from a plurality of ECG recorders. The pre-processed ECG data includes ECG measurements extracted or derived from raw ECG signals and annotations of cardiac events. Further, the system includes a multi-agent query processor to receive and process an input message related to health of a subject, retrieve relevant data elements from the pre-processed ECG data, raw ECG signals, or both based on the processed input message, compute metrics corresponding to the input message based on the retrieved data elements, and generate a response to the input message using an LLM or at least one agent to integrate retrieved data elements and computed metrics. The response is presented on a user interface to a healthcare provider.

The invention discloses a wearable real-time nursing monitoring device for physiological signs. The wearable real-time nursing monitoring device comprises an electrocardio garment body, a sensor integration module, a micro-processing module, an electrode slice and a heating module, the electrocardio garment body is made of a flexible fabric material, has a shape fitting the curve of a human body and is used for being worn on the trunk of the human body; the sensor integration module is embedded in a fabric of the electrocardiograph garment body, and the sensor integration module comprises an electrode sensor, a heart rate sensor, a respiration sensor, a temperature sensor, a motion sensor, an optical sensor and an electrocardiogram analysis module; the intelligent electrocardiograph garment has the advantages that the electrocardiograph sensor, the heart rate sensor, the breathing sensor, the temperature sensor, the motion sensor and the optical sensor are embedded into the electrocardiograph garment in a fabric integration mode, multiple key vital signs can be collected synchronously for a long time in a non-sensitive mode in the natural living state of a user, and the flexible electrodes are matched with the special electrocardiograph analysis module, so that the user experience is improved. And the continuous and dynamic electrocardiogram monitoring capability is realized in a wearable clothing form.

Electrocardiogram-based deep learning for cardiac prediction is described. An electrocardiogram analysis module may include a data preprocessor configured to normalize an electrocardiogram to generate a standardized input for an electrocardiogram-based cardiac prediction. The electrocardiogram analysis module may further include a deep learning model including a neural network and at least one dense layer, the deep learning model trained to identify features associated with a cardiac condition that reflect underlying cardiac changes that result from or predispose development of the cardiac condition, and generate a cardiac prediction based on the identified features.

This assistance system comprises an electrocardiograph, an electrocardiogram analysis apparatus, and an assistance apparatus. The electrocardiograph is configured to acquire an electrocardiogram of a subject. The electrocardiogram analysis apparatus is configured to receive the electrocardiogram, divide the electrocardiogram into a plurality of sections, and extract sections other than a specific section from the plurality of sections as candidate sections. The assistance apparatus is configured to communicate with and connect to the electrocardiogram analysis apparatus. The assistance apparatus comprises a computing device and a display apparatus that is controlled by the computing device. The functions of the computing device are described in detail in a specification.

The support system includes an electrocardiograph, an electrocardiogram analyzer, and a support device. The electrocardiograph is configured to acquire an electrocardiogram of a subject. The electrocardiogram analyzer is configured to receive the electrocardiogram, to divide the electrocardiogram into a plurality of sections, and to extract the sections other than specified sections from the plurality of sections as candidate sections. The support device is configured to be communicatively connected to the electrocardiogram analyzer. The support device includes a computing device and a display device controlled by the computing device. The functions of the computing device are described in the specification in detail.

The present invention provides a method for batch analysis of missing QRS waves in dynamic electrocardiogram, which can assist clinicians in batch finding the missing QRS waves and simultaneously batch modifying and compensating for the missing QRS waves, greatly improving the efficiency of electrocardiogram analysis. By constructing a superimposed QRS waveform diagram and a bar chart of the number of QRS wave markers, and comparing the total number of heartbeats M at the QRS peak waveform in the superimposed QRS waveform diagram with the number of QRS wave markers N, all regions where QRS markers are missing can be found in batch, without the need for clinical staff to manually search item by item, greatly improving the efficiency of electrocardiogram analysis. At the same time, the present invention also discloses a system for batch analysis of missing QRS waves in dynamic electrocardiogram.

According to one embodiment of the present disclosure, there are disclosed a method, program and apparatus for providing a user interface for electrocardiogram analysis. The method may comprise: obtaining bio-data of an electrocardiogram reading target; and displaying a first control graphic configured to switch a visual representation and state according to the result of the electrocardiogram analysis performed based on the obtained bio-data in the first area of the user interface. Furthermore, the first control graphic may be constructed for each type of disease or electrocardiogram feature that can be read from an electrocardiogram.

This design is a graphical user interface for electrocardiogram analysis, characterized by the combination of the shape and form of the display screen on which the graphical user interface for electrocardiogram analysis is displayed. The dotted lines in this design do not form part of the design sought to be registered. Figure 5.2 is a reference view and does not form part of the design sought to be registered. 5.1) Front view; 5.2) Reference view

The invention relates to an ICU patient delirium risk early screening system based on AI electrocardiogram analysis. The system comprises a neural signal extraction module, a component mode determination module, a delirium type identification module, a risk trajectory prediction module and a risk alarm generation module, wherein the neural signal extraction module extracts neuromodulation related signal fragments based on an electrocardiogram signal sequence and a preset neuromodulation specificity index; a component mode determination module extracts time sequence features from the fragments and determines an abnormal component distribution mode; the delirium type identification module is used for matching potential delirium types through the feature database; the risk trajectory prediction module predicts a risk trajectory in combination with a long-short-term memory network; a risk alert generation module evaluates a risk level and generates an alert. With the adoption of the system, early and dynamic screening of delirium risks can be realized, the screening accuracy and timeliness are improved through multi-module collaborative analysis, and accurate monitoring support is provided for ICU (Intensive Care Unit) patients.

The invention relates to the technical field of electrocardiogram analysis, and discloses an unsupervised partial adversarial adaptive method and system for different label spaces, and the method comprises the steps: constructing a deep learning diagnosis model, a feature extractor, a feature classifier and a full-connection feature processor; constructing an entropy minimization loss function according to the source domain classification loss; a selection factor is obtained through calculation, and the weight of source domain data in diagnosis model training is adjusted according to the selection factor; and constructing a final loss function in the diagnosis model training process, and optimizing the feature extractor, the feature classifier and the full-connection feature processor by minimizing the final loss function. Through the above method, the unsupervised partial adversarial adaptive system for the different label spaces is realized, adversarial training is performed on the model by introducing the EL loss function, the selection factor and the final loss function, the cross-domain migration performance of the deep learning model can be effectively improved, and the diagnosis performance of the model in the different label spaces is ensured.

This design is an analysis area selection screen for a graphical user interface for electrocardiogram analysis, characterized by the combination of shape and form of the display screen on which the graphical user interface for electrocardiogram analysis is displayed. The dotted lines in this design do not form part of the design sought to be registered. Figure 4.2 is a reference view and does not form part of the design sought to be registered. 4.1) Front view; 4.2) Reference view

According to one embodiment of the present disclosure, there are disclosed a method, program and apparatus for providing a user interface for electrocardiogram analysis. The method may comprise: obtaining bio-data of an electrocardiogram reading target; and displaying a first control graphic configured to switch a visual representation and state according to the result of the electrocardiogram analysis performed based on the obtained bio-data in the first area of the user interface. Furthermore, the first control graphic may be constructed for each type of disease or electrocardiogram feature that can be read from an electrocardiogram.

When statistical values ​​calculated from a partial measurement section of electrocardiogram data are presented to an analyst, it is possible to prevent abnormalities in electrocardiogram data from being overlooked. [Solution] The electrocardiogram analysis device 3 has a first calculation unit 335 that calculates the difference between at least two feature points related to the position of a predetermined wave in the electrocardiogram data; a second calculation unit 336 that calculates a first statistical value of one or more differences in a specific section in the electrocardiogram data and a second statistical value of the difference different from the first statistical value; an identification unit 334 that identifies a second section in the electrocardiogram data for which the second statistical value satisfies a predetermined judgment condition, provided that the second statistical value in the first section in the electrocardiogram data does not satisfy a predetermined judgment condition, and that is different from the first section that is within a predetermined range based on the first section; and an output unit 339 that associates the first statistical value calculated for at least one of the first and second sections and outputs the calculated first statistical value for that section.

This design is a graphical user interface for electrocardiogram analysis, characterized by the combination of the shape and form of the display screen on which the graphical user interface for electrocardiogram analysis is displayed. The dotted lines in this design do not form part of the design sought to be registered. Figure 8.2 is a reference view and does not form part of the design sought to be registered. 8.1) Front view; 8.2) Reference view

The present invention provides a method for analyzing ambulatory electrocardiogram based on a two-stage template of waveform rhythm, which can analyze ambulatory electrocardiogram comprehensively and quickly. At the same time, the method is simple, the process is fixed, and it is easy to master, especially suitable for analyzing a large number of ambulatory electrocardiograms. In the technical solution of this application, the analysis process of ambulatory electrocardiogram is divided into two analysis stages: the analysis process based on waveform template and the analysis process based on rhythm template; all the waveforms of heart beats are batch-reviewed through the waveform superposition diagram corresponding to the clustering template, and the clutter template is browsed one by one in the way of sample diagram; through the generation process of the rhythm template, the missed beat template and supraventricular premature beat template that the analysts mainly focus on are screened out, and combined with other graphic tools, the data in the missed beat template and supraventricular premature beat template are comprehensively reviewed. At the same time, this application also discloses an ambulatory electrocardiogram analysis system based on a two-stage template of waveform rhythm.

To provide an electrocardiogram analysis system capable of determining the need for an electric shock to a patient undergoing cardiopulmonary resuscitation (CPR) with a higher accuracy. An electrocardiogram analysis system includes electrocardiogram (ECG) signal acquiring means 11, ECG signal sampling means 12, ECG spectrogram transforming means 13, impedance signal acquiring means 21, impedance signal sampling means 22, impedance spectrogram transforming means 23, a convolutional neural network (CNN) 4 including an input layer 4I, an output layer 4O, sample data accumulation means 4L, and sample data input means 4T, and electric shock indication reporting means 5. The CNN is a priori provided with sample data including sample ECG spectrograms and sample impedance spectrograms obtained from a large number of subjects, and sample response data on the need for an electric shock, and is optimized by self-learning the sample data.

To better support the rescuer's movements during cardiopulmonary resuscitation. [Solution] In the AED1, the detection unit 134 detects the patient's body movement during the CPR period after electrocardiogram analysis and discharge processing. The output control unit 131 outputs instructions to the rescuer regarding chest compressions based on whether or not the patient's body movement is present during the CPR period. The output control unit 131 also outputs a continuation instruction D1 to instruct the continuation of chest compressions, and outputs the continuation instruction D1 again when a first time has elapsed since the previous output of the continuation instruction D1. Furthermore, if the patient's body movement is not detected for a period of time shorter than the first time, the output control unit 131 outputs a start instruction D2 to instruct the start of chest compressions with priority over the continuation instruction D1, and outputs the start instruction D2 again when the second time has elapsed.

The present application provides an electrocardiogram analysis method based on a three-dimensional electrocardiogram superposition diagram, which can realize the rapid location of abnormal P wave and T wave sample data in the whole heartbeat for a large amount of dynamic electrocardiogram data, and the method is simple and easy to grasp. It constructs a three-dimensional electrocardiogram superposition diagram, and establishes a graphical correspondence between the waveform superposition diagram, the chromatogram, the characteristic parameter scatter diagram and the sample diagram through the three-dimensional electrocardiogram superposition diagram; the QRS wave with drastic amplitude changes is quickly found through the electrocardiogram superposition diagram, and the P wave or / and T wave with obvious changes is quickly found through the chromatogram, and the data suspected of abnormality is located; the characteristic parameter scatter diagram based on the characteristic parameter and time representation is designed to make up for the difficulty of observation caused by the voltage amplitude of the central electric wave of the chromatogram being converted into the depth of color, and the heartbeat characteristic parameter value of each heartbeat data is confirmed through the characteristic parameter scatter diagram, and each suspected data is confirmed in combination with the sample diagram, and finally the abnormal data is located.

The invention relates to an electrocardio data analysis system and method, an electronic device and a storage medium, and the electrocardio data analysis method comprises the steps: obtaining original electrocardio data, and generating a first electrocardio data analysis result according to the original electrocardio data and electrocardio analysis parameters; generating a second electrocardio data analysis result according to the first electrocardio data analysis result and the first target data; wherein the first target data comprises a target typicality heart beat model in the electrocardiogram data. By means of the method and device, the technical problem that in the prior art, when dynamic electrocardio data are reanalyzed, all modifications of a user in the early stage are ignored, and consequently the work of the user is repeated is solved, and in the electrocardio data reanalysis process, the diagnosis speed is greatly increased, the labor intensity of the user is reduced, and the user experience is improved. And the accuracy of the diagnosis conclusion is improved.

According to an embodiment of the present disclosure, disclosed is a method for evaluating qualities of electrocardiogram data and diagnosing a disease only with a signal having an excellent quality. Specifically, according to the present disclosure, a computing device evaluates qualities of electrocardiogram data obtained from a plurality of leads, excludes electrocardiogram data obtained from at least one lead among the plurality of leads based on the evaluation of the qualities of the electrocardiogram data, and performs electrocardiogram analysis based on remaining electrocardiogram data by using a pre-learned electrocardiogram analysis model.

The application provides a rare disease occurrence probability prediction method and device and an electrocardiogram analysis system. The method comprises the following steps: acquiring a plurality of to-be-evaluated electrocardiogram data and corresponding to-be-evaluated medical record text data; inputting the to-be-evaluated electrocardiogram data into an electrocardiogram pre-training model to obtain a target electrocardiogram feature vector; inputting the medical record text data corresponding to the to-be-evaluated electrocardiogram data into a medical text pre-training model to obtain a target text feature vector; inputting the to-be-evaluated electrocardiogram data into a preset risk detection model to obtain an electrocardiogram rare disease occurrence probability coefficient; presetting a rare disease feature dictionary; determining the occurrence probability of each rare disease according to the similarity between the target electrocardiogram feature vector and the reference text feature vector of each rare disease, the similarity between the target text feature vector and the reference text feature vector of each rare disease, and the electrocardiogram rare disease occurrence probability coefficient. The occurrence probability of the rare disease can be predicted without training a large number of electrocardiogram samples of the rare disease.

The invention belongs to the technical field of data analysis, and provides a dynamic electrocardiogram analysis method and device and terminal device.The method comprises the steps that firstly, electrocardiogram data of a to-be-detected object is obtained; generating change trend data based on the historical electrocardio data and the current electrocardio data; and analyzing the change trend data to generate event description information. According to the method, the multi-day electrocardiogram data of the to-be-detected object can be independently analyzed day by day, and the electrocardiogram analysis result of each day can be obtained; the analysis result of the whole electrocardiogram data is further analyzed, the statistical result of the development and change process of the related illness state of the to-be-detected object can be obtained, the change process of the heart state of the to-be-detected object can be visually displayed, and the electrocardiogram data analysis efficiency and accuracy are improved.

The present disclosure provides a method, an apparatus, an electronic device, and a storage medium for analyzing a paper electrocardiogram. In one embodiment of the method, the paper electrocardiogram is analyzed by inputting it into a machine learning model twice. For the first time, the binary image of the paper electrocardiogram is input into the first origin site determination model. For the second time, the eigenvalue of each relevant feature in the preset set of relevant features related to ventricular arrhythmia and the output result of the first origin site determination model are input into the second origin site determination model together. This is because the model input of the first origin site determination model is only the binary image, and the model interpretability is not strong. Each relevant feature in the preset set of relevant features related to ventricular arrhythmia has been medically proven to be related to ventricular arrhythmia, which can increase the interpretability of the second origin site determination model. In addition, through two classifications, the accuracy of the finally obtained origin site determination result can be improved.