Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review
It addresses the problem of automating EHR processing for healthcare delivery and research, but is incremental as it is a review paper summarizing existing methods.
This survey paper reviews neural natural language processing methods for processing unstructured text in electronic health records, summarizing current approaches across tasks like classification, extraction, and generation to address the challenge of tapping into over half of EHR data that is untapped for secondary use.
Electronic health records (EHRs), digital collections of patient healthcare events and observations, are ubiquitous in medicine and critical to healthcare delivery, operations, and research. Despite this central role, EHRs are notoriously difficult to process automatically. Well over half of the information stored within EHRs is in the form of unstructured text (e.g. provider notes, operation reports) and remains largely untapped for secondary use. Recently, however, newer neural network and deep learning approaches to Natural Language Processing (NLP) have made considerable advances, outperforming traditional statistical and rule-based systems on a variety of tasks. In this survey paper, we summarize current neural NLP methods for EHR applications. We focus on a broad scope of tasks, namely, classification and prediction, word embeddings, extraction, generation, and other topics such as question answering, phenotyping, knowledge graphs, medical dialogue, multilinguality, interpretability, etc.