Question answering

Big data

World Wide Web

Natural language

Process (computing)

Health care

Knowledge extraction

Variety (cybernetics)

Archaeology

Scope (computer science)

Operating system

Economics

Data mining

Computer science

Natural language processing

Health records

Natural (archaeology)

Data science

Artificial intelligence

Information extraction

Information retrieval

Programming language

Deep learning

Economic growth

Unstructured data

Artificial neural network

Interpretability

Recurrent neural network

History

Computer Science Review

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.

Neural Natural Language Processing for unstructured data in electronic health records: A review