An Electronic Health Record-Based Tool to Identify Newly Diagnosed Breast Cancer Patients at Risk of Low Social Support

Goals of the project are to: 1) Identify terms from content in the EHR, based on theory and prior literature, and informed by clinical stakeholders in BC care, that measure structural and/or functional social support, have been associated with BC treatment and outcomes, and could be extracted through code or natural language processing (NLP); 2) Develop an EHR-based social support measure, EHR-SUPPORT, using data from structured, semi-structured, and unstructured (through NLP) sources that help identify patients at risk of low social support, overall and by race/ethnicity, and validate the measure against published social support measures; and 3) Evaluate associations of EHR-SUPPORT and its component variables with BC treatment outcomes (surgery delays, chemotherapy delays, nonadherence to hormonal therapy) and BC-specific and total mortality, overall and by race/ethnicity. In an exploratory aim, we propose to: Explore, with clinician stakeholders, workflow and information technology requirements to implementing EHR-SUPPORT.

0