Clinical Time Series

Longitudinal AI Models Predict Cancer Adverse Events
SPARC, a transformer-based foundation model trained on more than 100 million routinely collected longitudinal clinical measurements from 224,047 patients with cancer, predicts treatment-related adverse events and generalizes to external centers.
Chenlian Fu, Jennifer Yu, Ruian Shi, Michele Waters, Mitchell Pavlak, Andrea Arfe, Sohrab P. Shah, Alexis Battle, Kenneth L. Kehl, Brian M. Bot, US Cancer AI Alliance (CAIA), Nikolaus Schultz, Quaid Morris, Justin Jee
PDF Cite Code DOI