基于文献分析探讨数据挖掘在肺癌中药用药规律的应用

Analysis on Application of Data Mining in Medication Rules of Traditional Chinese Medicine in Lung Cancer Based on Literature Analysis

目的:分析数据挖掘在肺癌中药用药规律中的应用,进一步总结中医药治疗肺癌的规律,为中医药治疗肺癌提供新的思路。方法:检索中国知网、万方数据、维普网、Pubmed中采用数据挖掘技术探究中药治疗肺癌用药规律的文献,构建数据库,应用文献分析对文献的数据分析软件、算法、高频中药、药对等信息进行归纳总结。结果:得到88篇有效文献,文献数量呈逐年上升趋势;数据挖掘常用分析软件为MicrosoftExcel、SPSS及其系列软件、中医传承辅助平台;常用分析方法为频次分析、关联规则和聚类分析;97.73%文献统计了高频药物,合计得到151味高频药物,频数排名前三的为黄芪、白花蛇舌草和甘草;涉及的药类主要为清热药和补虚药;高频药物药性以寒性、温性最多,药味主要为甘味、苦味和辛味,归经主要归肝、肺、脾和胃经;80.90%文献分析了治疗肺癌的常用药对,共计得到239组常用药对,对高频药物的关联规则分析得到二项关联5条,两者结果呼应;37.65%文献总结了中医治疗肺癌的常用中药核心组合,57.95%文献总结了常用聚类方或新方,23.86%文献总结了不同中医证型肺癌的用药规律;聚类分析得到5个药物组合。结论:数据挖掘已广泛运用于中医药治疗肺癌的领域,且研究结果符合肺癌“虚、痰、瘀、毒”的病机,间接说明了中医治疗肺癌应以扶正为主,配合活血、化痰、祛湿、解毒等法,为中医药治疗肺癌提供依据。

Objective:Analyze the application of data mining technology in the treatment of lung cancer in Chinese medicine,further sum--marizes the law of traditional Chinese medicine in the treatment of lung cancer,and provide new ideas for the treatment of lung cancer by traditional Chinese medicine.Methods:Literatures of treatment of lung cancer in Chinese medicine using data mining technology are retrieved from CNKI,Wanfang,VIP and Pubmed,and the database is constructed.The data analysis software,analysis methods,high-frequency Chinese medicine and drug pairs and other information of included literatures are summarized and analyzed by literature analysis.Results:A total of 88 valid literatures are obtained,and the number of literatures is increasing year by year;The commonly used analysis software is Microsoft Excel,SPSS and its series software,and Traditional Chinese Medicine Inheritance and Assistance Platform System.The common analysis methods are frequency analysis,association rule analysis and cluster analysis;97.73%of the literature counted high-frequency drugs.A total of 151 high-frequency Chinese medicine are obtained,and the top three are Radix Astragali,Herba Hedy otidis Diffusae and Radix et Rhizoma Glycyrrhizae;The drugs involved are mainly concentrated on deficiency-nourishing and antipyretics drugs;The drug properties of high frequency drugs are mainly cold and warm,five flavors are mainly concentrated in sweet,bitter and spicy,and the meridian tropism are mainly liver,lung,spleen and stomach;80.90%of the literatures analyzed common drug pairs in the treatment of lung cancer,239 pairs of common drug pairs were obtained,and 5 binomial associations were obtained by association rule analysis of frequently used drugs,and the results of the two corresponded;37.65%of the literatures summarized the commonly used core combination of traditional Chinese medicine in the treatment of lung cancer,57.95%of the literatures summarized the commonly used clustering formula or new formula,and 23.86%of the literatures summarized the drug use rule of lung cancer of different traditional Chinese medicine syndromes;A total of 5 drug combinations are obtained by cluster analysis.Conclusion:Data mining has been widely used in the field of traditional Chinese medicine in the treatment of lung cancer,and the research results are consistent with the pathogenesis of"deficiency,phlegm,blood stasis,poison"of lung cancer,which indirectly indicates that the traditional Chinese medicine treatment of lung cancer should focus on strengthening and promoting blood circulation,eliminating phlegm,removing dampness and detoxification,providing a certain basis for the treatment of lung cancer by traditional Chinese medicine.