Prediction and Factor Extraction of Drug Function by Analyzing Medical Records in Developing Countries

摘要：

　　The World Health Organization has declared Bangladesh one of 58 countries facing acute Human Resources for Health (HRH) crisis. Artificial intelligence in healthcare has been shown to be successful for diagnostics. Using machine learning to predict pharmaceutical prescriptions may solve HRH crises. In this study, we investigate a predictive model by analyzing prescription data of 4,543 subjects in Bangladesh. We predict the function of prescribed drugs, comparing three machine-learning approaches. The approaches compare whether a subject shall be prescribed medicine from the 21 most frequently prescribed drug functions. Receiver Operating Characteristics (ROC) were selected as a way to evaluate and assess prediction models. The results show the drug function with the best prediction performance was oral hypoglycemic drugs, which has an average AUC of 0.962. To understand how the variables affect prediction, we conducted factor analysis based on tree-based algorithms and natural language processing techniques.

关键词： Data Mining Health Services Accessibility Medical Informatics

作者: Min Hu Yasunobu Nohara Masafumi Nakamura Naoki Nakashima

作者单位: Graduate School of Medical Sciences,Kyushu University,Fukuoka City,Fukuoka,Japan Medical Information Center,Kyushu University Hospital,Fukuoka City,Fukuoka,Japan

会议类型: 国际会议

会议名称: 第十六届世界医药健康信息学大会((MEDINFO2017)、第二届世界医药健康信息学华语论坛(WCHIS 2017)、第15届全国医药信息学大会(CMIA 2017)

会议地点: 苏州

会议语种:英文

页码: 403-407

在线出版日期: 2017-08-21（万方平台首次上网日期，不代表论文的发表时间）