Drug curative effect multi-index evaluation method based on Bayesian network and three-dimensional mathematical model

Abstract

The embodiment of the invention provides a drug curative effect multi-index evaluation method based on a Bayesian network and a three-dimensional mathematical model. The method comprises the followingsteps: firstly, acquiring original experimental data of an evaluation drug according to a preset template, and preprocessing the original experimental data to obtain final experimental data for evaluation; carrying out heterogeneity analysis on the final experimental data, and respectively processing the final experimental data based on heterogeneity to obtain a Meta analysis evidence relation graph; calculating the relative sorting of the drug efficacy based on a multi-dimensional Bayesian model, and obtaining the area value under the cumulative sorting probability graph according to the relative sorting; and finally, performing multi-dimensional clustering on the drug efficacy based on the area value under the cumulative sorting probability graph to finish classification of the drug efficacy. According to the technical scheme, the blank in the aspect of drug efficacy evaluation based on a Bayesian method and clustering analysis under multi-outcome indexes is filled up, so that the evaluation and classification result of the drug efficacy is more accurate and more referential.

Description

【Technical field】 [0001] The invention relates to the technical field of biological information, in particular to a multi-index evaluation method for drug efficacy based on a Bayesian network and a three-dimensional mathematical model. 【Background technique】 [0002] In the field of drug clinical evaluation, the comprehensive analysis of RCT data is an important evaluation method. Since RCTs are mostly clinical trials comparing two drugs, the comprehensive comparison of the efficacy of multiple drugs for the same disease has always been a bottleneck in the medical field. Existing methods can only perform dual-index clustering evaluation. Based on the accurate collection of drug RCT test data, this patent uses Bayesian network and three-dimensional mathematical model as the core technology and meta-analysis as the basic technology to comprehensively present the multi-indicator clustering and comparison results among various drugs, providing a basis for clinical evaluation of ...

AI Technical Summary

Problems solved by technology

Existing methods can only perform dual-index clustering evaluation

Images