An Investigation of the Representation of Social Determinants of Health in the UMLS. Rawat, B. P. S., Keating, H., Goodwin, R., Druhl, E., & Yu, H. AMIA Annual Symposium Proceedings, 2022:912–921, April, 2023.
An Investigation of the Representation of Social Determinants of Health in the UMLS [link]Paper  abstract   bibtex   
Social Determinants of Health (SDOH) are the conditions in which people are born, live, work, and age. Unified Medical Language System (UMLS) incorporates SDOH concepts; but few have evaluated its coverage and quality. With 15,649 expert-annotated SDOH mentions from 3176 randomly selected electronic health record (EHR) notes, we found that 100% SDOH mentions can be mapped to at least one UMLS concept, indicating a good coverage of SDOH. However, we discovered a few challenges for the UMLS’s representation of SDOH. Next, we developed a multi-step framework to identify SDOH concepts from UMLS, and a clinical BERT-based classification algorithm to assign each identified SDOH concept to one of the six general categories. Our multi-step framework extracted a total of 198, 677 SDOH concepts from the UMLS and the SDOH category classification system attained an accuracy of 91%. We also built EASE: an open-source tool to Extract SDOH from EHRs.
@article{rawat_investigation_2023,
	title = {An {Investigation} of the {Representation} of {Social} {Determinants} of {Health} in the {UMLS}},
	volume = {2022},
	issn = {1942-597X},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10148271/},
	abstract = {Social Determinants of Health (SDOH) are the conditions in which people are born, live, work, and age. Unified Medical Language System (UMLS) incorporates SDOH concepts; but few have evaluated its coverage and quality. With 15,649 expert-annotated SDOH mentions from 3176 randomly selected electronic health record (EHR) notes, we found that 100\% SDOH mentions can be mapped to at least one UMLS concept, indicating a good coverage of SDOH. However, we discovered a few challenges for the UMLS’s representation of SDOH. Next, we developed a multi-step framework to identify SDOH concepts from UMLS, and a clinical BERT-based classification algorithm to assign each identified SDOH concept to one of the six general categories. Our multi-step framework extracted a total of 198, 677 SDOH concepts from the UMLS and the SDOH category classification system attained an accuracy of 91\%. We also built EASE: an open-source tool to Extract SDOH from EHRs.},
	urldate = {2024-04-10},
	journal = {AMIA Annual Symposium Proceedings},
	author = {Rawat, Bhanu Pratap Singh and Keating, Heather and Goodwin, Raelene and Druhl, Emily and Yu, Hong},
	month = apr,
	year = {2023},
	pmid = {37128364},
	pmcid = {PMC10148271},
	pages = {912--921},
}

Downloads: 0