External Validation of a Clinically Validated Machine Learning Model to Identify and Prevent Acute Care During Cancer Radiotherapy and Chemoradiation

Poster Number: P180
Presentation Time: 05:00 PM - 06:30 PM

Abstract Keywords: Clinical Decision Support, Machine Learning, Precision Medicine, Chronic Care Management
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics

Patients with cancer undergoing radiation therapy (RT) often receive acute care during treatment. The SHIELD-RT algorithm uses structured electronic health record data to identify patients at high risk for acute events during RT and demonstrated high predictive performance in our previous randomized controlled trial. The objective of this study was to perform an external evaluation of algorithmic performance at a large academic medical center.

Speaker(s):
Marianna Elia, PhD
UCSF