Deep Learning for Electronic Health Records Analytics

• Published in: IEEE access Vol. 7; pp. 101245 - 101259
• Main Authors: Harerimana, Gaspard, Kim, Jong Wook, Yoo, Hoon, Jang, Beakcheol
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: adverse drug events; Algorithms; convolutional neural networks; Data mining; Deep learning; EHR raw features; Electronic health records; Electronic medical records; Hospitals; Laboratory tests; Machine learning; Physicians; recurrent neural networks; Statistical methods; Task analysis; Unstructured data
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2928363

Recent technological advancements have led to a deluge of medical data from various domains. However, the recorded data from divergent sources comes poorly annotated, noisy, and unstructured. Hence, the data is not fully leveraged to establish actionable insights that can be used in clinical applications. These data recorded in hospital's Electronic Health Records (EHR) consists of patient information, clinical notes, charted events, medications, procedures, laboratory test results, diagnosis codes, and so on. Traditional machine learning and statistical methods have failed to offer insights that can be used by physicians to treat patients as they need to obtain an expert opinion assisted features before building a benchmark task model. With the rise of deep learning methods, there is a need to understand how deep learning can save lives. The purpose of this study was to offer an intuitive explanation for possible use cases of deep learning with EHR. We reflect on techniques that can be applied by health informatics professionals by giving technical intuitions and blue prints on how each clinical task can be approached by a deep learning algorithm.