Semi-supervised learning of the electronic health record for phenotype stratification

详细信息    查看全文

• 作者：Brett K. Beaulieu-Jones^a ; ^b ; ^{brettbe@med.upenn.edu} ; Casey S. Greene^b ; ^c ; ^d ; ^{csgreene@upenn.edu} ; the Pooled Resource Open-Access ALS Clinical Trials Consortium¹
• 关键词：Electronic health record ; Denoising autoencoder ; Unsupervised ; Electronic phenotyping ; Patient stratification ; Disease subtyping
• 刊名：Journal of Biomedical Informatics
• 出版年：2016
• 出版时间：December 2016
• 年：2016
• 卷：64
• 期：Complete
• 页码：168-178
• 全文大小：2865 K
• 卷排序：64

文摘

Denoising autoencoders (DAs) can model electronic health records. Semi-supervised learning with DAs improves ALS patient survival predictions. DAs improve patient cluster visualization through dimensionality reduction.