Clinical information extraction applications: A literature review

Area of Science:

• Biomedical Informatics
• Health Informatics
• Clinical Data Science

Background:

• Electronic health records (EHRs) are increasingly adopted, necessitating methods to extract valuable information.
• Information Extraction (IE) is crucial for leveraging EHR data for clinical decision support and research.
• Automated extraction of clinical information from text is a key component for secondary data use.

Purpose of the Study:

• To review recent research on clinical information extraction (IE) applications.
• To identify trends, tools, methods, and applications in clinical IE.
• To understand and address the gap between EHR data utilization and clinical IE studies.

Main Methods:

• Conducted a literature search from January 2009 to September 2016.
• Utilized databases including Ovid MEDLINE, EMBASE, Scopus, Web of Science, and ACM Digital Library.
• Screened 1917 publications, selecting 263 for detailed review.

Main Results:

• The review covers publication venues, data sources, clinical IE tools, and methodologies.
• Applications discussed include disease- and drug-related studies and clinical workflow optimization.
• Identified 263 relevant articles focusing on clinical IE.

Conclusions:

• Clinical IE has diverse applications, but a significant gap exists with direct EHR data studies.
• This review provides insights into this gap and proposes potential solutions.
• Bridging the gap can enhance the secondary use of EHR data for research and clinical practice.