Supporting Acute Advance Care Planning with Precise, Timely Mortality Risk Predictions

Abstract

Patients with serious, life-limiting disease benefit from end-of-life conversations, goal setting, and palliative care. Hospitalized patients at high risk of near-term death are likely to benefit from such interventions. As NYU Langone Health expanded its institutional initiatives promoting patient-centered end-of-life care, leaders developed an artificial intelligence–based system that identifies patients at high risk of dying within 2 months. Upon opening a high-risk patient’s chart, attending physicians receive an interruptive alert stating the risk. If they agree, they are encouraged to conduct and document an advance care planning discussion. In the first year of operation running live across the health system, this platform has precisely identified high-risk patients within days of admission, producing high rates of provider agreement with risk and increased adoption of advance care planning. We are continuing to refine the system and to investigate how physicians interpret the risk estimates and integrate them into their decision-making.

Vincent J. Major

Assistant Professor

Vincent J. Major, PhD is an Assistant Professor at NYU Grossman School of Medicine working on applied machine learning for healthcare using electronic health record (EHR) data.