A multi-modal cardiomyopathy auxiliary diagnosis method, electronic device and program product

CN122290956APending Publication Date: 2026-06-26SUZHOU ZHIXIN MEDICAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SUZHOU ZHIXIN MEDICAL TECH CO LTD
Filing Date
2026-03-26
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Traditional diagnostic methods for cardiomyopathy in the present technology mainly rely on single electrocardiogram data, resulting in low accuracy of identification results and making it difficult to meet the needs of early, accurate and efficient diagnosis.

Method used

A multimodal cardiomyopathy-assisted diagnostic method is adopted. Electrocardiogram, echocardiogram and biochemical data are acquired, preprocessed and then input into a multimodal feature fusion module, which includes a multi-scale convolution module, a feature fusion module and an LSTM module. The diagnostic model of multi-scale convolution, feature fusion and LSTM module is combined to extract and fuse cardiac feature information under multiple scales and multiple modalities.

Benefits of technology

It improves the accuracy and reliability of cardiomyopathy diagnosis. By combining multimodal information, it enriches the dimensions of diagnostic features, enhances the richness of feature expression and the accuracy of diagnostic results, and provides more efficient and reliable auxiliary diagnostic support.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122290956A_ABST
    Figure CN122290956A_ABST
Patent Text Reader

Abstract

This application provides a multimodal cardiomyopathy auxiliary diagnosis method, electronic device, and program product. By combining multimodal cardiac data fusion with multi-scale convolution, feature fusion, and LSTM modules, the diagnostic model effectively solves the problem of low accuracy caused by traditional cardiomyopathy identification relying solely on single electrocardiogram data. It can fully explore cardiac feature information at different scales and modalities, improve the richness of feature expression and the accuracy of diagnostic results, and provide more efficient and reliable auxiliary diagnostic support for cardiomyopathy.
Need to check novelty before this filing date? Find Prior Art