Intelligent-algorithm-based drug safety confidence index system and construction method

Abstract

The invention belonging to the technical field of medical data processing discloses an intelligent-algorithm-based drug safety confidence index system and a construction method. The construction method comprises: research data are collected; the research data are analyzed and a comprehensive evaluation index is obtained by a corresponding delphi method; and a drug safety evaluation index system is constructed and a PSO-BP-neural-network drug safety evaluation model is improved. The system is composed of a target layer, a project layer, a factor layer, and an index layer. According to the invention, a corresponding evaluation mode needs to be constructed in a future drug safety index analysis and the algorithm, data, and various factor weight ratios of drug safety evaluation index are analyzed in the evaluation result, so that the selected data source becomes accurate, the used algorithm meets the practical situation, and the constructed drug safety evaluation index is based on scientific, people-oriented, truth-seeking, rigorous, innovative principles.

Description

technical field [0001] The invention belongs to the technical field of medical data processing, and in particular relates to a drug safety confidence index system and construction method based on an intelligent algorithm. Background technique [0002] Drug safety is related to everyone's life and health. This invention aims at better evaluating and supervising drug safety, studies existing drug safety evaluation methods at home and abroad, and is committed to making contributions to the improvement of my country's drug safety supervision and management evaluation theory system. try. [0003] In recent years, the country has paid more and more attention to the issue of drug safety, and its supervision has also increased year by year. However, compared with the US Food and Drug Administration (FDA), the my country Food and Drug Administration (CFDA) started late in the supervision of drug safety. Relevant policies, laws and regulations are still incomplete, and the classifica...

AI Technical Summary

Problems solved by technology

[0010] In the existing technology, the classification of drug safety evaluation indicators and the weight setting of indicators at all levels are also relatively complicated, which cannot meet the needs of real-time, dynamic and comprehensive evaluation of drug safety;

[0011] In the prior art, for the BP neural network drug safety evaluation model, it is easy to fall into a local optimal solution during the drug safety evaluation process, resulting in insufficient accuracy of drug safety evaluation, and the PSO-BP neural network drug safety In the evaluation model, there are problems such as slow convergence speed and long training time

Images