@Article{info:doi/10.2196/11016，作者=“王志祥与林，培巨与程，青兰与台，舒华与高阳，叶慧与蒋重宪”，标题=“基于深度神经网络模型的潜在药物不良反应检测”，期刊=“J Med Internet Res”，年=“2019”，月=“Feb”，日=“06”，卷=“21”，号=“2”，页=“e11016”，关键词=“药物不良反应;深度神经网络;毒品表示;机器学习;背景:药物不良反应(adr)很常见，是每年造成100多万严重伤害和死亡的根本原因。检测adr最常见的方法是依靠自发报告。不幸的是，自发报告的低报告率严重限制了药物警戒。目的:探讨一种基于深度神经网络(DNN)的药物潜在不良反应自动检测方法。方法:我们设计了一个DNN模型，利用药物的化学、生物学和生物医学信息来检测adr。该模型旨在实现两个主要目的:识别药物的潜在不良反应和预测新药的可能不良反应。 For improving the detection performance, we distributed representations of the target drugs in a vector space to capture the drug relationships using the word-embedding approach to process substantial biomedical literature. Moreover, we built a mapping function to address new drugs that do not appear in the dataset. Results: Using the drug information and the ADRs reported up to 2009, we predicted the ADRs of drugs recorded up to 2012. There were 746 drugs and 232 new drugs, which were only recorded in 2012 with 1325 ADRs. The experimental results showed that the overall performance of our model with mean average precision at top-10 achieved is 0.523 and the rea under the receiver operating characteristic curve (AUC) score achieved is 0.844 for ADR prediction on the dataset. Conclusions: Our model is effective in identifying the potential ADRs of a drug and the possible ADRs of a new drug. Most importantly, it can detect potential ADRs irrespective of whether they have been reported in the past. ", issn="1438-8871", doi="10.2196/11016", url="//www.mybigtv.com/2019/2/e11016/", url="https://doi.org/10.2196/11016", url="http://www.ncbi.nlm.nih.gov/pubmed/30724742" }