DISPARITIES IN ADVANCE CARE PLANNING: GAPS IN CLINICAL NOTES ON COMFORT VS. - LIFE-SUSTAINING TREATMENT PREFERENCES

Sep 29, 2026

Upload by moss~

Goal-concordant advance care planning remains essential, yet documented disparities persist. Using electronic health record free-text, a validated Priorities-BERT natural language processing model extracted care preferences from 3.6 million notes in 14,729 older adults with heart failure, cancer, or dementia. Preferences were categorized as comfort-only, life-sustaining treatment (LST)-only, mixed, or none. Logistic regression identified demographic and diagnosis-linked predictors, revealing significant cross-diagnosis gaps and lower LST documentation with increasing age. Targeted interventions are recommended to support equitable, timely ACP conversations.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages1

Reading Time3 min

AccessFree to download

Abstract

Background

Objective

Methods

Results

Conclusion

Innovation in Aging, 2025, Vol. 9, No. S2 1061 Abstract citation ID: igaf122.3571 DISPARITIES IN ADVANCE CARE PLANNING: GAPSIN CLINICAL NOTES ON COMFORT VS. LIFE-SUSTAINING TREATMENT PREFERENCES Yuwen Ji1, Alaa Albashayreh1, and Stephanie Gilbertson-White2, 1. University of Iowa, Iowa City, Iowa, United States, 2. University of Iowa, University of Iowa, Iowa, United States Background: Goal-concordant care is essential, yet disparities in advance care planning (ACP) persist. Electronic health record (EHRs) documentation of specific preferences, such as comfort and life-sustaining treatments (LST) and natural language processing (NLP) to extract free-text data, provides real-world information to explore patterns. Objective: To identify predictors associated with documentation of specific preferences in a cohort of older adults with chronic conditions. Methods: In a dataset of records from 14,729 older adults with heart failure, cancer, or dementia from a large academic medical center, we used a validated NLP model, Priorities-BERT (accuracy= 90.91%), to categorize documented care preferences from 3.6 million EHR notes into four groups: comfort-only, LST-only, mixed, or none. Logistic regression identified factors associated with each preference category (vs. no preference). Results: The mean age of the sample was 78.67 years (SD = 6.05) . Female patients (vs. male)(OR = 1. 11, 95% CI: 1.04–1. 19), heart failure (OR =1 .59, 95% CI: 1.34–1. 89), dementia (OR = 1 .33, 95%CI: 1.25-1.43), were associated with higher odds of having any priorities of care documented. Increasing age was associated with lower odds of LST (OR = 0 .94, 95%CI: 0.94-0.95) . Patients with heart failure (OR = 1 .50, 95%CI: 1.39-1.61) or dementia (OR = 1 .56, 95% CI: 1.42-1.71) were more likely to have comfort preferences documented. Conversely, cancer patients were more likely to have LST documented (OR = 1 . 12, 95%CI: 1.03-1.21) . Conclusion: Significant disparities existed across these three diagnoses in documentationACP preferences. Targeted clinical and health-system interventions are needed to promote equitable and timely ACP conversations for patients likely to benefit from this care.

FAQs

What was the main objective of the study?

To identify predictors associated with documentation of specific advance care planning preferences among older adults with chronic conditions.

How were patient preferences extracted from clinical records?

A validated NLP model, Priorities-BERT, categorized free-text EHR notes into comfort-only, LST-only, mixed, or no documented preference.

Which factors were associated with higher odds of having priorities of care documented?

Female sex and diagnoses of heart failure and dementia were associated with higher odds of documenting at least some care priorities.

What did the study conclude about disparities and interventions?

Significant disparities existed across diagnoses in documenting ACP preferences, and targeted clinical and health-system interventions are needed to promote equitable and timely ACP conversations.

Sep 29, 2026

Upload by moss~