Mount Sinai Deploys PRISM AI to Match Cancer Patients to Trials Systemwide
The oncology-specific system scans EHR data to surface eligible cancer patients earlier.
Overview
- PRISM uses Triomics’ OncoLLM, an oncology-tuned large language model, to analyze patient records and extract eligibility signals from clinical notes, pathology reports, and biomarkers.
- The platform connects to Epic and Oracle Health through FHIR standards to flag potential matches in real time across Mount Sinai Queens, Brooklyn, South Nassau, Morningside, West, and other sites.
- Mount Sinai positions the rollout to replace manual protocol-to-chart reviews so clinicians can focus on patient conversations and identify trial opportunities more consistently.
- The institution says it is the first NCI-designated Comprehensive Cancer Center in New York City to deploy an oncology-focused AI trial-matching tool across its entire health system.
- Leaders plan to evaluate the impact on clinical trial enrollment and report findings at scientific meetings and in peer-reviewed publications, with outcome data still pending.