一种基于无监督学习方法的心跳模板分类方法及设备
By using an unsupervised learning-based method that combines the R-wave characteristics of electrocardiogram (ECG) signals with clinical waveform parameters, heartbeat categories are automatically classified, solving the problem of misdiagnosis of ECG signals in existing technologies and improving the accuracy and efficiency of heartbeat classification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI SID MEDICAL CO LTD
- Filing Date
- 2023-08-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies using unsupervised classification methods based on electrocardiogram signals are prone to misdiagnosis, especially since atrial premature beats and ventricular premature beats are difficult to distinguish from normal heartbeats, leading to low diagnostic efficiency for doctors.
Using an unsupervised learning-based approach, the heartbeat is automatically classified by extracting R-wave features, calculating the RR interval and QRS width, and combining clinical waveform parameter features. A threshold is set to determine the heartbeat category, thereby reducing misdiagnosis.
It improves the accuracy and efficiency of heartbeat classification, reduces misclassification of normal electrocardiograms and ectopic heartbeats, and enhances the reliability of doctors' diagnoses.
Smart Images
Figure CN117179781B_ABST