Method and system for predicting membranous nephropathy based on machine learning

By constructing a feature matrix integrating traditional Chinese and Western medicine and a multi-level prediction framework, the problems of insufficient integration of multi-source heterogeneous data and feature fusion were solved, and dynamic full-process prediction and personalized diagnosis and treatment support for membranous nephropathy were achieved.

CN120809267APending Publication Date: 2025-10-17CHANGCHUN UNIV OF CHINESE MEDICINE
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202510933104.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-08
Publication Date
2025-10-17

Smart Images

  • Figure CN120809267A_ABST
    Figure CN120809267A_ABST
Patent Text Reader

Abstract

The invention discloses a method and system for predicting membranous nephropathy based on machine learning, and relates to the technical field of medical diagnosis and treatment, and the method comprises the steps: collecting multi-source heterogeneous data of a patient; preprocessing the multi-source heterogeneous data, constructing a mapping relation between the traditional Chinese medicine syndrome type and the molecular biomarker, and generating a traditional Chinese and western medicine fusion feature matrix; screening a feature subset related to membranous nephropathy prediction from the traditional Chinese and western medicine fusion feature matrix; constructing a membranous nephropathy multi-level prediction framework according to the feature subset, and training each prediction model in the framework; and applying the trained and optimized membranous nephropathy multi-level prediction framework to the feature subset data of the new patient to generate a membranous nephropathy multi-dimensional prediction result. By establishing the Chinese and western medicine feature mapping relation, deep fusion of traditional Chinese medicine diagnosis and modern medical indexes is realized, and comprehensiveness and accuracy of disease diagnosis are improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Method and system for predicting mineral substance and bone abnormality marker of chronic kidney disease

    CN121211409A

  • Enhanced learning medical record data association mining method and system

    CN121460216A