Extracting social determinants of health from electronic health records using natural language processing: a systematic review

• Published in: Journal of the American Medical Informatics Association : JAMIA 2021-11, Vol.28 (12), p.2716-2727
• Main Authors: Patra, Braja G, Sharma, Mohit M, Vekaria, Veer, Adekkanattu, Prakash, Patterson, Olga V, Glicksberg, Benjamin, Lepow, Lauren A, Ryu, Euijung, Biernacka, Joanna M, Furmanchuk, Al’ona, George, Thomas J, Hogan, William, Wu, Yonghui, Yang, Xi, Bian, Jiang, Weissman, Myrna, Wickramaratne, Priya, Mann, J John, Olfson, Mark, Campion, Thomas R, Weiner, Mark, Pathak, Jyotishman
• Format: Article
• Language: English
• Subjects: Data Management; Electronic Health Records; Humans; Machine Learning; Natural Language Processing; Reviews; Social Determinants of Health
• ISSN: 1527-974X; 1067-5027; 1527-974X
• DOI: 10.1093/jamia/ocab170

Abstract Objective Social determinants of health (SDoH) are nonclinical dispositions that impact patient health risks and clinical outcomes. Leveraging SDoH in clinical decision-making can potentially improve diagnosis, treatment planning, and patient outcomes. Despite increased interest in capturing SDoH in electronic health records (EHRs), such information is typically locked in unstructured clinical notes. Natural language processing (NLP) is the key technology to extract SDoH information from clinical text and expand its utility in patient care and research. This article presents a systematic review of the state-of-the-art NLP approaches and tools that focus on identifying and extracting SDoH data from unstructured clinical text in EHRs. Materials and Methods A broad literature search was conducted in February 2021 using 3 scholarly databases (ACL Anthology, PubMed, and Scopus) following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 6402 publications were initially identified, and after applying the study inclusion criteria, 82 publications were selected for the final review. Results Smoking status (n = 27), substance use (n = 21), homelessness (n = 20), and alcohol use (n = 15) are the most frequently studied SDoH categories. Homelessness (n = 7) and other less-studied SDoH (eg, education, financial problems, social isolation and support, family problems) are mostly identified using rule-based approaches. In contrast, machine learning approaches are popular for identifying smoking status (n = 13), substance use (n = 9), and alcohol use (n = 9). Conclusion NLP offers significant potential to extract SDoH data from narrative clinical notes, which in turn can aid in the development of screening tools, risk prediction models, and clinical decision support systems.