April 29, 2025
The new publication by IMPACT Career Development Awardee, Erica Frechman, PhD, and IMPACT community members Jeff Williamson, MD, Nicholas Pajewski, PhD, and Jennifer Gabbard, MD, among others, examines the discrimination, calibration, and algorithmic fairness of the Epic End of Life Care Index (EOL-CI) as a prognostic model for predicting 1-year mortality.
Investigators assessed the EOL-CI’s performance, sensitivity, and predictive values in community-dwelling people 65 years and older within a single health system in the Southeastern United States.
Study findings reflect reasonable discrimination using the EOL-CI model, with the best performance for older adults and those with more health system contact. Local refinement and calibration of the EOL-CI to provide direct estimates of prognosis would optimize the model’s value for identifying patients who would benefit from targeted palliative care intervention and proactive care planning.
Read more here.