Extracting social determinants of health from inpatient electronic medical records using natural language processing
Journal of Epidemiology and Population Health · 2024
DOI: 10.1016/j.jeph.2024.202791 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Epidemiology and Population Health, 2024. Verfasst von Elliot A Martin und 5 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Health Informatics, University of Calgary, Calgary, Canada; Health Research Methods and Analytics, Alberta Health Services, Calgary, Canad…. Hauptthemen laut MEDLINE: Natural Language Processing, Electronic Health Records, Social Determinants of Health, Inpatients. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Canadian Institutes of Health Research.
Abstract (Originalsprache)
BACKGROUND: Social determinants of health (SDOH) have been shown to be important predictors of health outcomes. Here we developed methods to extract them from inpatient electronic medical record (EMR) data using techniques compatible with current EMR systems. METHODS: Four social determinants were targeted: patient language barriers, employment status, education, and whether the patient lives alone. Inpatients aged 18 and older with records in the Calgary-wide EMR system were studied. Algorithms were developed on the January 2019 hospital admissions (n=8,999) and validated on the January 2018 hospital admissions (n=8,839). SDOH documented as structured data were compared against those extracted from unstructured free-text notes. RESULTS: More than twice as many patients had a note documenting a language barrier in EMR data than in structured data; 12 % of patients indicated by EMR notes to be living alone had a partner noted in their structured marital status. The Positive Predictive Value (PPV) of the elements extracted from notes was high, at 99 % (95 % CI 94.0 %-100.0 %) for language barriers, 98 % (95 % CI 92.6 %-99.9 %) for living alone, 96 % (95 % CI 89.8 %-98.8 %) for unemployment, and 88 % (95 % CI 80.0 %-93.1 %) for retirement. CONCLUSIONS: All SDOH elements were extracted with high PPV. SDOH documentation was largely missing in structured data and sometimes misleading.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Centre for Health Informatics, University of Calgary, Calgary, Canada; Health Research Methods and Analytics, Alberta Health Services, Calgary, Canada. Electronic address: eamartin@ucalgary.ca.
- Centre for Health Informatics, University of Calgary, Calgary, Canada; Health Research Methods and Analytics, Alberta Health Services, Calgary, Canada.
- Public Health Evidence and Innovation, Alberta Health Services, Calgary, Canada.
- Department of Community Health Science, University of Calgary, Calgary, Canada; Department of Medicine, University of Calgary, Calgary, Canada.
- Centre for Health Informatics, University of Calgary, Calgary, Canada; Department of Community Health Science, University of Calgary, Calgary, Canada.
Förderung
- Canadian Institutes of Health Research
Zitieren
APA
Martin, E. A., D'Souza, A. G., Saini, V., Tang, K., Quan, H., & Eastwood, C. A. (2024). Extracting social determinants of health from inpatient electronic medical records using natural language processing. Journal of Epidemiology and Population Health. https://doi.org/10.1016/j.jeph.2024.202791
Vancouver
Martin EA, D'Souza AG, Saini V, Tang K, Quan H, Eastwood CA. Extracting social determinants of health from inpatient electronic medical records using natural language processing. Journal of Epidemiology and Population Health. 2024. doi:10.1016/j.jeph.2024.202791
BibTeX
@article{Martin2024,
author = {Martin, Elliot A and D'Souza, Adam G and Saini, Vineet and Tang, Karen and Quan, Hude and Eastwood, Cathy A},
title = {Extracting social determinants of health from inpatient electronic medical records using natural language processing},
journal = {Journal of Epidemiology and Population Health},
year = {2024},
doi = {10.1016/j.jeph.2024.202791}
}
EUVIMED