Characterizing Emergency Department Care for Patients With Histories of Incarceration.

Abstract

Objectives: Patients with a history of incarceration experience bias from health care team members, barriers to privacy, and a multitude of health care disparities. We aimed to assess care processes delivered in emergency departments (EDs) for people with histories of incarceration.

Methods: We utilized a fine-tuned large language model to identify patient incarceration status from 480,374 notes from the ED setting. We compared socio-demographic characteristics, comorbidities, and care processes, including disposition, restraint use, and sedation, between individuals with and without a history of incarceration. We then conducted multivariable logistic regression to assess the independent correlation of incarceration history and management in the ED while adjusting for demographic characteristics, health behaviors, presentation, and past medical history.

Results: We found 1734 unique patient encounters with a history of incarceration from a total of 177,987 encounters. Patients with history of incarceration were more likely to be male, Black, Hispanic, or other race/ethnicity, currently unemployed or disabled, and had smoking and substance use histories, compared with those without. This cohort demonstrated higher odds of elopement (OR: 3.59 [95% CI: 2.41-5.12]), leaving against medical advice (OR: 2.39 [95% CI: 1.46-3.67]), and being subjected to sedation (OR: 3.89 [95% CI: 3.19-4.70]) and restraint use (OR: 3.76 [95% CI: 3.06-4.57]). After adjusting for covariates, the association between incarceration and elopement remained significant (adjusted odds ratio: 1.65 [95% CI: 1.08-2.43]), while associations with other dispositions, restraint use, and sedation did not persist.

Conclusion: This study identified differences in patient characteristics and care processes in the ED for patients with histories of incarceration and demonstrated the potential of using natural language processing in measuring care processes in populations that are largely hidden, but highly prevalent and subject to discrimination, in the health care system.