Using Deep Learning Based Natural Language Processing Techniques for Clinical Decision-Making with EHRs

TLDR: It is found that the distance to revolutionize the existing healthcare sector using deep learning methods still remains long, but the recent progress made by these proposed methods have already made a promising good start.

Abstract: Natural language processing (NLP) is an interdisciplinary domain of research that focuses on the interactions between human languages and computers. There has been a recent trend of solving the NLP problems using deep learning approach. The applications of deep learning in the healthcare sector are mostly considered to be related to canonical examples of applying image processing and computer vision techniques to medical scans for disease diagnoses. Electronic Health Record (EHR) is another source of data often being neglected, equally if not more important than medical scans, that can change the way we learn useful features and information from the medical records of patients. These text-based information stored within the EHR are data-rich by nature, but are often not well-understood due to its characteristics of high volume, variety, velocity and complexity. However, these specific characteristics fit right to the nature of deep learning. Therefore, we believe it is the right time to summarize the current status, to review and learn from the state-of-the-art medical-based NLP techniques. Different from the existing reviews, we examine and categorize the current deep learning-based NLP techniques in medical domain into three major purposes: representation learning, information extraction and clinical predictions. Meanwhile, we discuss whether the application of deep learning methods has tackled the problems differently and transformed these tasks revolutionarily. Based on the results, we find that the distance to revolutionize the existing healthcare sector using deep learning methods still remains long. However, the recent progress made by these proposed methods have already made a promising good start. Furthermore, we state some of the legal and ethical considerations, present the status quo of the healthcare industry applications, and provide several possible directions of future research.