人工智能在中医药领域的应用进展及现状思考

人工智能（Artificial Intelligence，AI）的蓬勃兴起为现代社会带来了前所未有的机遇，中医药是中华民族传承千年的文化瑰宝。随着人工智能技术不断在中医药领域的科技创新中崭露头角，二者的融合不断加深，人工智能在中医药领域的发展前景、争议挑战也引发了诸多思考。本文将从人工智能在中医药领域的应用入手，对人工智能辅助中医诊断、智能决策与数据挖掘、健康管理及中草药现代化研究等方面，就近年来国内外研究进展进行总结与分析，以期为AI视域下实现中医药现代化、智能化赋能。     

基于文本挖掘和生物医学数据库的新型冠状病毒肺炎药物发现

目的 基于文本挖掘技术和生物医学数据库对新型冠状病毒肺炎（COVID-19）相关文献进行数据挖掘分析，探究COVID-19及其主要症状发热、咳嗽、呼吸障碍相关基因靶点，筛选潜在有效的化学药和中药。方法 使用GenCLiP 3网站获取COVID-19和其主要症状咳嗽、发热、呼吸障碍共4个关键词的共有靶点，在METASCAPE数据库中对其进行基因本体（GO）和通路富集分析，再利用String数据库和Cytoscape软件构建共有靶点的蛋白质相互作用网络，筛选获得核心基因，运用DGIdb数据库、SymMap数据库针对核心基因进行中西医治疗药物预测。结果 获得COVID-19及其主要症状共有基因靶点28个，其中有IL2、IL1B、CCL2等核心基因16个，使用DGIdb数据库筛选获得与16个关键靶点相互作用的化学药包括沙利度胺、来氟米特、环孢素等28种，中药包括虎杖、黄芪、芦荟等70味。结论 COVID-19及其主要症状的病理机制可能和CD4、KNG1、VEGFA等28个共有基因相关，可能通过介导TNF、IL-17等信号通路参与COVID-19病理过程。潜在有效药物可能通过作用相关靶点通路起到治疗COVID-19的作用。     

基于真实世界数据探讨中医药治疗糖尿病肾病用药规律的研究＊

目的 基于临床信息系统分析总结真实世界的数据，采用数据挖掘的方法探讨中医药治疗糖尿病肾病的用药规律。方法 收集2018年1月-2020年12月上海中医药大学附属曙光医院宝山分院健康信息系统确诊的糖尿病肾病的门诊或住院患者的诊疗信息，建立Excel数据库，采用Excel 2010软件统计高频药物的四气、五味、归经及功效；使用SPSS Modeler 18.0软件中的Apriori算法分析关联规则，采用web节点建构药对关联网状图；运用SPSS 25统计软件进行因子分析。结果 本研究最终纳入477例接受中药饮片治疗的DKD患者，在1203条方剂信息中，涉及中药462种；使用频数排名前5位的中药分别是黄芪、黄精、石斛、山茱萸、麦冬；使用频数前5类的中药类别分别是补气药、补阴药、清热燥湿药、活血调经药、息风止痉药；在30味高频药物中，苦、甘、辛药味最为常见；药性寒、温数量接近；归脾经、肝经、肺经、肾经居多；关联规则提示，药物组合中置信度最高的组合为地龙-当归-僵蚕，因子分析共得到5个有效因子，累积贡献率为47.33%。结论 中医药治疗DKD在补益气血阴阳的同时，兼顾对瘀血、湿邪和痰饮的治疗，结合证型，可考虑使用黄芪、黄精、石斛、山茱萸、麦冬、金蝉花等药物的使用，清热燥湿药物如黄连、黄芩、黄柏可适当加入，为使邪有去处，大黄、车前子或可增添疗效。     

“T” is for “transgender”: an analysis of children’s picture books featuring transgender protagonists and narrators

ABSTRACT

This project examined 55 picture books featuring transgender, gender expansive or genderqueer protagonists or narrators published between 2008 and 2018. The purpose of the study was to determine how this genre of children’s literature supports and challenges four gender assumptions: the gender binary, gender essentialism, sex/gender congruency and gender stability. Additionally, this critical analysis explored misgendering within this genre and themes of social rejection and acceptance. Protagonists and narrators were permitted a degree of gender nonconformity, however, the majority of picture books missed opportunities for a more complete exploration of gender possibilities.     

基于中医古籍文献的升降散应用溯源及探析

通过对中医古籍中有关升降散论述的文献梳理,全面探讨其内涵。本方是在大黄、僵蚕为雏形的基础上增加蝉蜕、姜黄而成方,几经易名,终在杨璿《伤寒瘟疫条辨》中为后人所熟知。本方广泛用于治疗瘟疫,以丸剂、散剂为主,方便携带,便于服用;重用大黄旨在祛邪、逐秽;应用时视人之体质强弱和量其毒之轻重而判断用药多寡,并辅以米酒、生蜜等以顾护正气。杨璿将其由治疗“热疫”的专方扩展为治疗“表里三焦大热”的通用方剂,扩大了本方治疗疾病范围。     

基于数据挖掘的国医大师刘祖贻治疗脑梗死恢复期方药规律研究

目的挖掘分析国医大师刘祖贻治疗脑梗死恢复期的处方用药规律,总结其学术思想。方法收集整理刘祖贻治疗脑梗死恢复期的病案处方,录入中医传承辅助平台软件中构建数据库,再使用该软件相关功能进行数据挖掘,分析处方中的组方用药规律。结果①共得处方147首,涉及药物179味,累计使用频次2 164次。②使用频次在20次及以上的药物,共有22味,其中前10味高频药物为黄芪、丹参、山楂、葛根、枸杞子、地龙、制何首乌、川芎、石菖蒲、淫羊藿。③黄芪用量从15 g至120 g均可见,最常用剂量为30 g,常用剂量范围主要集中于30～60 g。④药物功效分类排名靠前的为补虚药、活血化瘀药、平肝息风药等。⑤高频药组前5位为丹参-黄芪、黄芪-山楂、葛根-黄芪、葛根-丹参、丹参-山楂;关联度较高的药组有地龙-黄芪、葛根-地龙-黄芪、丹参-地龙-黄芪等。⑥通过聚类分析算法提取出核心组合12个,进而演化出潜在新方6首,如"白芍、威灵仙、桂枝、鸡血藤、白芥子""全蝎、菊花、蜈蚣、刺蒺藜"等。结论国医大师刘祖贻治疗脑梗死恢复期的用药以益气温阳、填精益髓、活血通络、息风化痰为主,重用黄芪,方以自拟芪仙通络方加减,体现出"气阳主用""脑髓阳生阴长"等学术思想。     

数据挖掘法探讨周珉教授治疗原发性肝癌用药规律及经验总结

[目的]数据挖掘法分析周珉教授治疗原发性肝癌的中医用药规律,探讨相关病机并进行经验总结。[方法]收集2016年2月—2018年5月周珉教授门诊期间治疗原发性肝癌的方剂,运用"中医传承辅助系统(V2.50)"进行数据挖掘,并结合周珉教授临床经验,进行原发性肝癌病机探讨及用药规律分析。[结果]共收集治疗原发性肝癌方剂176首,涉及中药235种,列出方剂中的高频药物及组合规律。[结论]总结原发性肝癌以"湿热痰毒、气阴两伤"为基础病机,"清热化湿、健脾养阴"治则贯穿原发性肝癌治疗始末,同时,根据疾病不同发展阶段及治疗措施,权衡"扶正"与"祛邪"的主次分配,斟酌应用"攻毒散结""行气化瘀"等治法,以达到改善患者生活质量、延缓疾病进展的目的。     

Reference set for performance testing of pediatric vaccine safety signal detection methods and systems

BackgroundSafety signal detection in spontaneous reporting system databases and electronic healthcare records is key to detection of previously unknown adverse events following immunization. Various statistical methods for signal detection in these different datasources have been developed, however none are geared to the pediatric population and none specifically to vaccines. A reference set comprising pediatric vaccine-adverse event pairs is required for reliable performance testing of statistical methods within and across data sources.MethodsThe study was conducted within the context of the Global Research in Paediatrics (GRiP) project, as part of the seventh framework programme (FP7) of the European Commission. Criteria for the selection of vaccines considered in the reference set were routine and global use in the pediatric population. Adverse events were primarily selected based on importance. Outcome based systematic literature searches were performed for all identified vaccine-adverse event pairs and complemented by expert committee reports, evidence based decision support systems (e.g. Micromedex), and summaries of product characteristics. Classification into positive (PC) and negative control (NC) pairs was performed by two independent reviewers according to a pre-defined algorithm and discussed for consensus in case of disagreement.ResultsWe selected 13 vaccines and 14 adverse events to be included in the reference set. From a total of 182 vaccine-adverse event pairs, we classified 18 as PC, 113 as NC and 51 as unclassifiable. Most classifications (91) were based on literature review, 45 were based on expert committee reports, and for 46 vaccine-adverse event pairs, an underlying pathomechanism was not plausible classifying the association as NC.ConclusionA reference set of vaccine-adverse event pairs was developed. We propose its use for comparing signal detection methods and systems in the pediatric population.     

Bibliometric analysis of orthopaedic related publications by Indian authors from the last decade

PurposeBibliometric studies have been established methods of analysing publications on a particular topic. These studies have been done on various orthopaedic topics and are increasing. The advantages of these studies have been highlighted in previous publications. Although some studies have been done on Indian publications from other specialties, those analysing Indian Orthopaedic Publications are lacking.MethodsWe performed a search in Scopus to look for all publications related to orthopaedics from India. Our search strategy in Scopus included ((TITLE-ABS-KEY(Orthopaedics OR Orthopaedics) AND AFFIL(India)) AND PUBYEAR > 2009 AND PUBYEAR < 2020) which resulted in 3270 articles on 02/11/2021. We analyzed the most publishing universities, city, state, specialty, authors, and anatomic location of these publications. We also mined the data to draw word clouds based on data obtained from the titles of articles, keywords and the affiliations of each of the articles published.ResultsTamil Nadu and New Delhi and their institutes appear to be the epicenter of publication activities in Orthopaedics in India. There has been a healthy trend of growth of articles in the orthopaedic specialty. Since there is a significant overlap of technology and engineering, it is not surprising to see engineering and technology institutes among the top 10 published institutes and even journals for the publications on orthopaedics.ConclusionThere has been a steady increase in the number of publications in the last decade. New Delhi and its Universities and Institutes appear to contribute the majority of citations and publications related to orthopaedics. Journal of Clinical Orthopaedics and Trauma was the most publishing journal for Indian authors on Orthopaedic related articles.     

中医药文献语义标注系统研究与开发

目的研究和开发支持中医和现代生物医学本体和术语集的语义标注系统。方法以MedPortal本体库和中医临床术语集等为术语资源库,设计语义标注系统工作流程和功能框架,并开发Web应用系统。结果构建了一个基于Web的中医药文献语义标注系统,支持语料库管理与维护、术语词典管理、语义标注和语义检索等功能,既可以为基于机器学习的信息抽取算法研究提供训练集,又能实现语义层面的多来源数据集成与知识融合。结论该中医药文献语义标注系统设计方案已经过实际项目验证,可为其他同类系统研发提供参考。