摘要
随着信息技术的快速发展及数字化时代的到来,数字化技术在多个中医药研究领域,如中药质量控制、数据挖掘、新药发现、处方配伍优化以及中医临床诊断等方面发挥重要作用.机器学习(ML)、深度学习(DL)等数字化技术的应用可优化中医药研究设计、降低临床研究时间成本、将临床研究与基础研究有机结合,提高临床研究质量和效率,为中医药现代化研究的科学性、客观性、规范性提供了保障.因此,完善多种数据资源、实现多种数字化技术交叉结合使用、优化算法和模型是中医药未来发展的必然趋势.对近年来ML在中医药研究领域中的应用进展进行梳理,分析说明聚类、支持向量机(SVM)和深度学习(DL)等ML方法在中药药性、中药配伍、中药毒性分析、中药药效研究、中药制药过程工艺优化、中药饮片质量等级分类、中医药临床用药规律挖掘、中医药治疗原理及药效机制解析等研究中的具体应用.旨在探索ML在中医药研究中的应用趋势,并对其应用前景进行展望.
Abstract
With the rapid development of information technology and the arrival of the digital era,digital technology plays an important role in several Chinese medicine research areas,such as quality control of traditional Chinese medicine(TCM),data mining,discovery of new medicines,optimization of prescription compounding,and clinical diagnosis of Chinese medicine.The application of digital technologies such as machine learning(ML)and deep learning(DL)can optimize the design of TCM research,reduce the time and cost of clinical research,organically combine clinical research with basic research,improve the quality and efficiency of clinical research,and provide a guarantee for the scientificity,objectivity,and standardization of modernized TCM research.Therefore,it is an inevitable trend for the future development of TCM to improve multiple data resources,realize the cross-combined use of multiple digital technologies,and optimize algorithms and models.In recent years,the progress of ML application in the field of TCM research is sorted out,and the analysis illustrates the specific applications of ML methods such as clustering,support vector machine(SVM)and deep learning(DL)in the research of TCM medicinal properties,TCM compounding,TCM toxicity analysis,TCM efficacy research,TCM pharmaceutical process optimization,TCM tablets quality grade classification,mining of TCM clinical medication rules,and analysis of TCM therapeutic principles and pharmacological effect mechanisms.The research aims to explore the application of ML in the study of TCM.It aims to explore the trend of ML application in TCM research and to prospect its application prospect.
NETL
NSTL
万方数据