System for detecting cardiac disorders based on electrocardiosignal

By employing a neural network module with an attention mechanism in the electrocardiogram signal detection system for multi-resolution analysis, the detection accuracy was improved. Furthermore, by visually explaining the model's decision-making process, the problems of low detection accuracy and poor interpretability in existing technologies were solved, thus achieving reliability for clinical applications.

CN117017309BActive Publication Date: 2026-06-26SHANDONG UNIV +1

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHANDONG UNIV
Filing Date
2023-06-29
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing heart disease detection systems lack sufficient accuracy and interpretability, making them difficult to promote in clinical applications.

Method used

A neural network module based on an attention mechanism is used to perform multi-resolution analysis of electrocardiogram (ECG) signals at the band, beat, and window levels. The disease detection decision-making process is explained through visualization, and a cardiac disease detection system based on ECG signals is constructed.

Benefits of technology

It improves the accuracy of heart disease detection and increases the transparency and interpretability of the model by visualizing the decision-making process of the neural network, thus gaining the trust of doctors and patients.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117017309B_ABST
    Figure CN117017309B_ABST
Patent Text Reader

Abstract

The application discloses a heart disease detection system based on an electrocardiosignal, and the system comprises an acquisition module configured to acquire an electrocardiosignal to be detected, a preprocessing module configured to perform a preprocessing operation on the electrocardiosignal to be detected, extract a wave band vector, a beat vector and a window segment vector from the preprocessed signal, convert the wave band vector into a wave band input matrix, and convert the beat vector into a beat input matrix, and a detection module configured to input the preprocessed electrocardiosignal into a trained heart disease detection model and output a heart disease detection result. The application can improve the accuracy of heart disease detection.
Need to check novelty before this filing date? Find Prior Art