3 results about "ECG feature" patented technology

This application proposes a classification model, construction method, and application of myocardial ischemia based on 12-lead ECG. By detecting the ST-T segment beat-by-beat changes using entropy domain, frequency domain, and Lyapunov domain analysis methods, spatiotemporal ECG feature parameters related to myocardial ischemia are obtained. A machine learning model for predicting myocardial ischemia is established, ultimately achieving optimal ECG feature selection related to myocardial ischemia. This addresses the problem that conventional 12-lead ECGs often lack clear ST segment or T wave features related to myocardial ischemia, severely affecting the sensitivity and accuracy of myocardial ischemia diagnosis. The method includes: acquiring a 12-lead ECG; calculating the ST-T segment sample entropy of the 12-lead ECG; converting the 12-lead ECG into a 3-lead ECG vector map; extracting the ST-T segment from the 3-lead ECG vector map and calculating its spatial and temporal feature values; and using a grid search method to select the optimal ECG features reflecting myocardial ischemia. Therefore, the sensitivity and accuracy of myocardial ischemia diagnosis are improved.

This invention provides a small-sample, multi-label electrocardiogram (ECG) classification method, comprising: acquiring a support set and a query set of ECGs, each including multiple ECG signals; for each ECG signal in the support set and query set, performing feature extraction at multiple different scales to obtain multiple extracted features corresponding to each ECG signal; performing attention enhancement on each extracted feature to obtain corresponding enhanced features, and then fusing all enhanced features across scales to obtain a fused feature map corresponding to each ECG signal; aggregating the fused feature maps corresponding to the support set into class prototypes, then calculating the similarity matrix between the class prototypes and the fused feature maps corresponding to the query set, and determining the category of each ECG signal in the query set based on the similarity matrix. This invention solves the problem in existing technologies that cannot fully extract ECG features and perform accurate classification.

This application relates to a supervised pre-training-based multimodal electrocardiogram (ECG) signal representation learning method. The method includes: entity extraction and standardized mapping of clinical text reports to obtain structured diagnostic labels; extraction of ECG features from raw ECG data through cross-channel slicing and routing aggregation using a multi-granularity ECG encoder; inputting the structured diagnostic labels and ECG features into a multimodal fusion network to complete text semantic extraction and cross-modal interaction, obtaining fused features; constructing modality consistency loss and classification loss to jointly optimize model parameters; and inputting the ECG data to be tested into the optimized model to complete diagnostic prediction. This method can fully exploit the value of clinical text, achieve fine-grained alignment of cross-modal features, reduce the computational complexity of long sequences, and take into account the multi-scale features of ECG signals, effectively improving the accuracy, robustness, and generalization ability of ECG analysis models.