Integrating structured and unstructured EHR data to characterize social and behavioral factors associated with frequent emergency department use among patients with cardiovascular disease
- 1Department of Foundational Medical Studies, Oakland University William Beaumont School of Medicine, Rochester, MI.
Abstract
ObjectiveThe goal was to integrate structured and unstructured data from the electronic health record (EHR) to identify social and behavioral determinants of health (SBDH) factors and evaluate their association with high emergency department (ED) utilization among cardiovascular disease (CVD) patients.
MethodsA custom natural language processing (NLP) algorithm was developed to extract 17 SBDH domains from clinical notes, combined with ICD-10 Z codes and screening questionnaires from the EHR. The study included patients aged 18-64 with a history of CVD. Multivariable logistic regression was used to identify associations between SBDH and high ED utilization ([≥] 5 visits) after adjusting for age, sex, race, insurance class, and chronic conditions.
ResultsUse of only ICD-10 codes and screening questionnaires identified patients in only a subset of the 17 SBDH domains, whereas extraction from clinical notes identified patients across all domains and increased prevalence estimates for every domain. Among 4,844 patients with CVD, 526 (10.9%) were frequent ED users. After adjustment, patients with inadequate support system (OR= 2.8), opioid abuse (OR=2.47), inadequate insurance (OR=2.42), alcohol abuse (OR=2.28), medication affordability concerns (OR=2.28), unreliable transportation (OR=1.82), financial strain (OR=1.69), and depression (OR=1.42) were significantly more likely to have frequent ED utilization.
ConclusionNLP can efficiently and more comprehensively identify socioeconomic risk factors from the EHR. Substance use, financial strain, inadequate social support, and other socioeconomic challenges may be linked to increased ED visits in patients with CVD.
Related
- Integrating epidemiology and genomic sequencing to characterize tuberculosis transmission
- Integrating emergency medical services and hospital surge capacity for mass-gathering preparedness: a structured narrative review
- A Reproducible Framework for Integrating Chronic Deep Brain Stimulation Sensing with Wearable Behavioral Monitoring
- Integrating structured sexual healthcare into a public gynaecological service: a single-centre retrospective implementation study
- Weight Loss and Long-Term Weight Trajectories After a Structured Nutritional and Behavioral Intervention: A Large Real-World Cohort Study
BibTeX
@misc{metzger2026integrating,
title = {{Integrating structured and unstructured EHR data to characterize social and behavioral factors associated with frequent emergency department use among patients with cardiovascular disease}},
author = {T. Metzger and S. Morrell and S. Roy and J. Neumann and L. Singh and P. Shah and B. Felice and D. Berger and R. Homayouni},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.11.26362813},
url = {https://www.medrxiv.org/content/10.64898/2026.09.11.26362813v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Integrating structured and unstructured EHR data to characterize social and behavioral factors associated with frequent emergency department use among patients with cardiovascular disease
AU - T. Metzger
AU - S. Morrell
AU - S. Roy
AU - J. Neumann
AU - L. Singh
AU - P. Shah
AU - B. Felice
AU - D. Berger
AU - R. Homayouni
PY - 2026
DA - 2026/09/11
PB - medRxiv
DO - 10.64898/2026.09.11.26362813
UR - https://www.medrxiv.org/content/10.64898/2026.09.11.26362813v1
AB - ObjectiveThe goal was to integrate structured and unstructured data from the electronic health record (EHR) to identify social and behavioral determinants of health (SBDH) factors and evaluate their association with high emergency department (ED) utilization among cardiovascular disease (CVD) patients. MethodsA custom natural language processing (NLP) algorithm was developed to extract 17 SBDH domains from clinical notes, combined with ICD-10 Z codes and screening questionnaires from the EHR. The study included patients aged 18-64 with a history of CVD. Multivariable logistic regression was used to identify associations between SBDH and high ED utilization ([≥] 5 visits) after adjusting for age, sex, race, insurance class, and chronic conditions. ResultsUse of only ICD-10 codes and screening questionnaires identified patients in only a subset of the 17 SBDH domains, whereas extraction from clinical notes identified patients across all domains and increased prevalence estimates for every domain. Among 4,844 patients with CVD, 526 (10.9%) were frequent ED users. After adjustment, patients with inadequate support system (OR= 2.8), opioid abuse (OR=2.47), inadequate insurance (OR=2.42), alcohol abuse (OR=2.28), medication affordability concerns (OR=2.28), unreliable transportation (OR=1.82), financial strain (OR=1.69), and depression (OR=1.42) were significantly more likely to have frequent ED utilization. ConclusionNLP can efficiently and more comprehensively identify socioeconomic risk factors from the EHR. Substance use, financial strain, inadequate social support, and other socioeconomic challenges may be linked to increased ED visits in patients with CVD.
ER -