JMIR Publications

ABSTRACT

Background:

Social Determinants of Health (SDOH) are critical drivers of health disparities and patient outcomes. However, accessing and collecting patient level SDOH data can be operationally challenging in the emergency department clinical setting requiring innovative approaches. This scoping review examines the potential of artificial intelligence (AI) and data science for modeling, extraction, and incorporation of SDOH data specifically within emergency departments (ED), further identifying areas for advancement and investigation.

Objective:

This scoping review examines the potential of artificial intelligence (AI) and data science for modeling, extraction, and incorporation of SDOH data specifically within emergency departments (ED), further identifying areas for advancement and investigation.

Methods:

We conducted a standardized search across Medline (Ovid), Embase (Ovid), CINAHL, Web of Science, and ERIC databases for studies published between 2015-2022. We focused on identifying studies employing AI or data science related to SDOH within emergency care contexts or conditions. Two specialized reviewers in Emergency Medicine and clinical informatics independently assessed each article, resolving discrepancies through iterative reviews and discussion. We then extracted data covering study details, methodologies, patient demographics, care settings, and principal outcomes.

Results:

Of the 1,047 studies screened, 26 met the inclusion criteria. Notably, 9 out of 26 studies were solely concentrated on ED patients. Conditions studied spanned broad Emergency Medicine complaints and conditions including sepsis, acute myocardial infarction, and asthma. The majority (n=16) explored multiple SDOH domains, with homelessness/housing insecurity and neighborhood/built environment predominating. Machine learning (ML) techniques were utilized in 23 of the studies, natural language processing (NLP) being the most common approach used (n=11). Rule-based (n=5), deep learning (n=2), and pattern matching (n=4) were the most common NLP techniques used. NLP models in the reviewed studies displayed significant predictive performance with outcomes, With F1-scores ranging between 0.40 - 0.75 and specificities nearing 95.9%.

Conclusions:

Although in its infancy, the convergence of AI and data science techniques, especially ML and NLP, with SDOH in Emergency Medicine offers transformative possibilities for better usage and integration of social data into clinical care and research. With a significant focus on the ED and notable NLP model performance, there is an imperative to standardize SDOH data collection, refine algorithms for diverse patient groups, and champion interdisciplinary synergies. These efforts aim to harness SDOH data optimally, enhancing patient care and mitigating health disparities. Our research underscores the vital need for continued investigation in this domain.