A drug interaction prediction method based on DS evidence theory

By integrating multimodal drug data and DS evidence theory into a decision fusion approach, the problem of inaccurate drug interaction prediction in existing technologies is solved, achieving higher accuracy and reliability in drug interaction prediction and reducing the risk of side effects from drug combinations.

CN115223731BActive Publication Date: 2026-01-13GUILIN UNIVERSITY OF TECHNOLOGY
0 Cites 0 Cited by

Patent Information

Application Number
CN202210837179.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-15
Publication Date
2026-01-13
Estimated Expiration
2042-07-15

AI Technical Summary

Technical Problem

Existing methods for predicting drug interactions only focus on the structural characteristics of drugs, resulting in inaccurate and unreliable predictions that cannot effectively predict the potential side effects of drug combinations.

Method used

A method based on Dirichlet evidence theory is adopted to integrate multimodal drug data, including molecular structure, target and metabolic enzyme data. Prediction results are generated through deep learning network, and decision fusion is performed using Dirichlet distribution and Dirichlet evidence theory to improve the reliability and accuracy of prediction.

Benefits of technology

It improves the accuracy and reliability of drug interaction prediction, can clearly express the confidence level of the prediction, and reduces the risk of side effects from drug combinations.

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

Abstract

The application discloses a drug interaction prediction method based on DS evidence theory. First, multi-modal data of drugs are acquired to construct a drug interaction dataset; then, multi-modal features of the drugs are extracted as inputs of a deep neural network, a multi-modal drug interaction prediction model is constructed, and the prediction model is trained; then, the trained prediction model is used to predict drug interactions. The prediction model uses Dirichlet distribution to calculate classification probability and uncertainty value, and obtains multi-modal prediction results and overall uncertainty value through Dempster-Shafer evidence theory fusion. Compared with existing prediction methods, the application uses multi-modal drug data, has a lower prediction error, can provide meaningful uncertainty information for guiding multi-modal prediction fusion and expressing prediction confidence, and has higher reliability and robustness.
Need to check novelty before this filing date? Find Prior Art