文献类型：期刊文献

英文题名：Representation learning for clinical time series prediction tasks in electronic health records

作者：Ruan, Tong[1];Lei, Liqi[1];Zhou, Yangming[1];Zhai, Jie[1];Zhang, Le[1];He, Ping[2];Gao, Ju[3]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, 130 Meilong Rd, Shanghai 200237, Peoples R China;[2]Shanghai Hosp Dev Ctr, 2 Kangding Rd, Shanghai 200000, Peoples R China;[3]Shanghai Univ Tradit Chinese Med, Shuguang Hosp, 528 Zhangheng Rd, Shanghai 201203, Peoples R China

年份：2019

卷号：19

外文期刊名：BMC MEDICAL INFORMATICS AND DECISION MAKING

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000509523600002)】；

基金：Publication costs were funded by the National Natural Science Foundation of China under Grant 61772201, the National Key R&D Program of China for "Precision Medical Research" under Grant 2018YFC0910500, the National Major Scientific and Technological Special Project for "Significant New Drugs Development" under Grant 2018ZX09201008, the Shanghai Sailing Program under Grant 19YF1412400, the Special Fund Project for "Shanghai Informatization Development in Big Data" under Grant 201901043, and the Network Teaching and Educational Research Project under Grant WJY2016012.

语种：英文

外文关键词：Electronic health records; Mortality prediction; Representation learning; Recurrent neural network

摘要：Background: Electronic health records (EHRs) provide possibilities to improve patient care and facilitate clinical research. However, there are many challenges faced by the applications of EHRs, such as temporality, high dimensionality, sparseness, noise, random error and systematic bias. In particular, temporal information is difficult to effectively use by traditional machine learning methods while the sequential information of EHRs is very useful. Method: In this paper, we propose a general-purpose patient representation learning approach to summarize sequential EHRs. Specifically, a recurrent neural network based denoising autoencoder (RNN-DAE) is employed to encode inhospital records of each patient into a low dimensional dense vector. Results: Based on EHR data collected from Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine, we experimentally evaluate our proposed RNN-DAE method on both mortality prediction task and comorbidity prediction task. Extensive experimental results show that our proposed RNN-DAE method outperforms existing methods. In addition, we apply the "Deep Feature" represented by our proposed RNN-DAE method to track similar patients with t-SNE, which also achieves some interesting observations. Conclusion: We propose an effective unsupervised RNN-DAEmethod to summarize patient sequential information in EHR data. Our proposed RNN-DAE method is useful on both mortality prediction task and comorbidity prediction task.