Making Sense of Big Textual Data for Health Care: Findings from the Section on Clinical Natural Language Processing

Area of Science:

• Medical Informatics
• Computational Linguistics
• Artificial Intelligence in Medicine

Background:

• Clinical Natural Language Processing (NLP) is crucial for extracting information from unstructured clinical text.
• Advancements in NLP are essential for improving clinical decision-making and patient care.

Purpose of the Study:

• To identify and summarize the top clinical Natural Language Processing (NLP) research published in 2016.
• To highlight key contributions and emerging trends in the field of clinical NLP.

Main Methods:

• A comprehensive literature survey was conducted by IMIA Yearbook NLP section editors.
• Papers were selected based on relevance to clinical texts or outcomes, followed by automated ranking and manual review.
• A peer-review process by external experts finalized the selection of the best papers.

Main Results:

• Five outstanding clinical NLP papers from 2016 were identified, showcasing diverse contributions.
• Key advancements include frameworks for abbreviation disambiguation, coreference resolution, and classifying clinically relevant sentences.
• Research also addressed patient counseling analysis for mental health and the grounding of gradable adjectives in clinical contexts.

Conclusions:

• Clinical NLP demonstrated significant growth in 2016, with a notable shift towards practical applications.
• Fundamental research tackled complex issues like lexical semantics, coreference resolution, and discourse analysis.
• Many research outcomes have been translated into freely available tools, primarily for the English language.