Oncoformer, AI Trial Matching & a $40M OpenAI Cancer Grant

This edition

Cancer prediction from a chest X-ray, AI trial matching at Mount Sinai, and a $40M OpenAI grant for cancer vaccines

Oncoformer cancer predictionAI trial matching$40M OpenAI × UNC grantAgentic AI in rad onc

Eric Topol@EricTopol on X

Cardiologist & physician-scientist — Scripps Research

Sep 21, 2026

Figure from a review of 31 legal cases involving medical AI tools: legal cases and harms concentrated in AI that touches clinical decision-making

View post on X ↗

Sep 20, 2026

Excerpt from the Oncoformer paper: a unimodal chest X-ray model predicts cancers outside the thoracic cavity — cervical cancer AUROC 0.905, colorectal 0.896 (Cell Press, open access)

View post on X ↗

Roupen Odabashian@RoupenMD on X

Oncologist — Karmanos; health-tech builder

Sep 17, 2026

Mount Sinai Health Systemi just deployed an AI platform, built on Triomics' oncology specific model, to match cancer patients to clinical trials systemwide, across seven sites including Mount Sinai Hospital, Brooklyn, Morningside, Queens, and South Nassau.

It became the first NCI designated comprehensive cancer center in New York City to do this at that scale.

I pay close attention to this specific problem because I have spent the last several months building a version of it myself. Matching a real patient to a real trial is not a keyword search.

It is reading a full chart, weighing inclusion and exclusion criteria that are often written ambiguously, and doing that fast enough that the patient is still eligible by the time anyone acts on it.

Most oncologists I know do this manually, or lean on a research coordinator who is already stretched across a dozen open protocols. The bottleneck was never a lack of interest in trials. It was time and staffing.

What I want to know now is not whether the model can find matches. Plenty of tools can find matches. Custom GPT today can match a patient to a trial

It is whether trial enrollment numbers actually move at Mount Sinai over the next year, or whether this becomes another well built tool that plateaus at the pilot stage because referral patterns and staffing did not change alongside it.

Mount Sinai press release: Mount Sinai launches AI-powered clinical trial-matching platform to expand access to cancer research

View post on X ↗

Ed ReznikAcademic scientist@EdReznik on X

Computational cancer researcher — MSK

Sep 18, 2026

MSK-Tox pipeline schematic: RAG retrieval plus LLM adverse-event calls over free-text oncology notes, N=55,406 patients, six toxicities

View post on X ↗

Free Access · KOL Pulse Intelligence

Track oncology’s top KOLs in your specialty

Create a free account, pick the tumor types you cover, and go beyond the tweet — the intelligence pharma teams use to map influence and prepare for engagement: