Deep EHR: A Survey of Recent Advances on Deep Learning Techniques for Electronic Health Record (EHR) Analysis

摘要

The past decade has seen an explosion in the amount of digital informationstored in electronic health records (EHR). While primarily designed forarchiving patient clinical information and administrative healthcare tasks,many researchers have found secondary use of these records for various clinicalinformatics tasks. Over the same period, the machine learning community hasseen widespread advances in deep learning techniques, which also have beensuccessfully applied to the vast amount of EHR data. In this paper, we reviewthese deep EHR systems, examining architectures, technical aspects, andclinical applications. We also identify shortcomings of current techniques anddiscuss avenues of future research for EHR-based deep learning.