Page 123 - AIH-1-2

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
Factors associated with social determinants

of health mentions in PubMed clinical case
reports from 1975 to 2022: A natural language

processing analysis

Julio Bonis*, Veysel Kocaman, and David Talby
John Snow Labs Inc., Delaware, United States of America

Abstract
Social determinants of health (SDoH) significantly influence health outcomes,
accounting for nearly 40% of such outcomes globally. These determinants, pivotal
in understanding health disparities, are insufficiently documented in clinical
settings and academic clinical narratives. To address this gap, we examined clinical
case reports from PubMed (1975–2022) to identify mentions of six specific SDoH,
employing a pre-trained named-entity recognition (NER) model from Spark natural
language processing (NLP). Multivariate logistic regression was utilized to investigate
associations between article characteristics and the documentation of SDoH.
From 463,546 reports, 4.4% mentioned SDoH, with race/ethnicity being the most
dominant mention. Race/ethnicity was often cited by sub-Saharan African authors
*Corresponding author:
Julio Bonis (adjusted odds ratio [AOR]: 4.47) and in general medicine (AOR: 2.18). Marital status
(julio@johnsnowlabs.com) mentions appeared predominantly in psychiatry (AOR: 2.60) and gynecology (AOR:
Citation: Bonis J, Kocaman V, 2.47). Sexual orientation mentions were correlated with infectious diseases (AOR:
Talby D. Factors associated with 25.00) and varied by authorship regions, with stronger associations observed in
social determinants of health South America (AOR: 4.04) and North America (AOR: 2.15), and comparatively weaker
mentions in PubMed clinical case
reports from 1975 to 2022: A natural associations noted in the Indian subcontinent and the Middle East (AOR: 0.16).
language processing analysis. Immigrant status mentions were closely related to infectious diseases (AOR: 4.51),
Artif Intell Health. 2024;1(2): 117-131. gynecology (AOR: 4.25), and certain geographies. Homelessness mentions were
doi: 10.36922/aih.2737
more prominent in forensic medicine (AOR: 14.92) and in both infections (AOR: 6.36)
Received: January 14, 2024 and mental disorders (AOR: 5.80). Spiritual belief mentions were more prominent
Accepted: March 18, 2024 with sub-Saharan authors (AOR: 9.17) and psychiatry (AOR: 7.61). SDoH mentions in
medical literature were also determined by the diagnosis, cultural background, and
Published Online: April 17, 2024
journal type. The limited SDoH registration emphasized their overlooked significance.
Copyright: © 2024 Author(s). Disproportionate emphasis on specific relationships, such as sexual orientation with
This is an Open-Access article infectious diseases, can perpetuate biases and stereotypes. Innovative tools such
distributed under the terms of the
Creative Commons Attribution as Spark NLP offer promise in advancing research using electronic health records
License, permitting distribution, (EHRs), but a standardized approach to SDoH reporting and vigilant AI training is
and reproduction in any medium, crucial for unbiased health-care analysis.
provided the original work is
properly cited.
Publisher’s Note: AccScience Keywords: Social determinants of health; Natural language processing; Clinical case
Publishing remains neutral with reports; Ethnicity; Marital status; Immigrant status; Homeless; Spiritual beliefs
regard to jurisdictional claims in
published maps and institutional
affiliations.

Volume 1 Issue 2 (2024) 117 doi: 10.36922/aih.2737