JMIR Publications

ABSTRACT

Background:

Residents in persistent poverty areas experience higher cancer mortality due to social determinants of health (SDoH) that negatively affect multiple factors, including health behaviors.

Objective:

We describe SDoH and clinical electronic health record (EHR) data as an innovative and heretofore rarely used source of information needed when adapting health behavior interventions for cancer control in persistent poverty areas.

Methods:

EHR data from a large multi-specialty group practice were extracted for cancer patients residing in zip codes inclusive of persistent poverty areas targeted for a health behavior intervention, and receiving care between January 2018 and November 2023. Self-reported SDoH data were obtained using the Protocol for Responding to and Assessing Patient Assets, Risks, and Experience (PRAPARE) and through Natural Language Processing (NLP) of social histories from a social work visit.

Results:

We identified 2,642 unique cancer patients, of which roughly 22% had PRAPARE data and 60% had social history data available for analysis. The most common cancers among survivors (53.1% female; 48.6% Black; mean age 65.2 years) included breast (20.1%), prostate (15.0%), and lymphoid/hematopoietic (12.1%). Among survivors in persistent poverty areas (n=509; all with a high social vulnerability index), 34.1% were single, 55.4% had Medicare (with only 14.3% having private insurance), 36.5% had obesity, 63.9% had hypertension, and 31.2% had diabetes. Of survivors in persistent poverty areas with PRAPARE data, 15.8% lacked transportation, 4.2% lived in housing insecurity, and 6.7% felt unsafe where they live.

Conclusions:

Innovative EHR and NLP approaches identified several socioeconomic and safety related challenges along with opportunities for health behavior interventions to leverage Medicare coverage and target multiple comorbidities when adapting interventions for cancer survivors living in persistent poverty areas.