Brain tumor survival prediction method and system based on multi-modal medical knowledge graph

By constructing a multimodal medical knowledge graph, integrating multi-source information and filling in missing modalities, the problems of low efficiency and insufficient interpretability of multimodal data fusion in brain tumor survival prediction are solved, achieving more accurate clinical applicability and reliable prediction.

CN121565447APending Publication Date: 2026-02-24BEIJING JIAOTONG UNIV
2 Cites 4 Cited by

Patent Information

Application Number
CN202511650203.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-12
Publication Date
2026-02-24

AI Technical Summary

Technical Problem

Existing technologies for predicting brain tumor survival suffer from low efficiency in multimodal data fusion, weak ability to handle missing modalities, and insufficient model interpretability, making them unsuitable for real-world clinical scenarios.

Method used

By constructing a multimodal medical knowledge graph and combining it with clinical guidelines and third-party knowledge bases, and through entity representation learning and feature completion, multi-source information is integrated to achieve multimodal heterogeneous feature interaction and reasonable medical completion of missing modalities, thereby improving the model's predictive performance and interpretability.

Benefits of technology

It improves the efficiency of multimodal data fusion, enhances the applicability and predictive accuracy of the model in clinical scenarios, provides traceable predictive evidence, and improves the interpretability of the model.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a brain tumor survival prediction method and system based on a multi-modal medical knowledge graph, and belongs to the technical field of brain tumor survival prediction. The multi-modal medical knowledge graph based on third-party knowledge base fusion is constructed; performing feature extraction on the brain tumor multi-modal data; searching an entity corresponding to the brain tumor related data in the multi-modal medical knowledge graph, and converting the entity into feature representation by using an entity representation learning method; the learned feature representation related to the brain tumor type complements the missing data mode, and finally the complemented features are input into a pre-trained survival prediction model to achieve brain tumor survival prediction. According to the multi-modal medical knowledge graph, comprehensive medical knowledge support meeting clinical requirements is provided; the multi-modal mapping knowledge domain is used for missing modal completion of brain tumor survival prediction, and a completion feature is generated by querying an associated entity through the mapping knowledge domain, so that the problem of weak modal missing processing capability in the prior art is solved.
Need to check novelty before this filing date? Find Prior Art