LAUSR

Key Points Question How do oncologists and a machine learning model compare in predicting 3-month mortality for patients with advanced solid tumors? Findings In this prognostic study, the machine learning model significantly outperformed 74 oncologists in predicting 3-month mortality for 2041 patients with metastatic solid tumors overall and in gastrointestinal and breast cancer subpopulations. Findings were not significant in genitourinary, lung, and rare cancer groups. Meaning The results of this study suggest the potential for a machine learning model trained with electronic health record data to support oncologists in prognostication and clinical decision-making to improve end-of-life care.