Announcing Independent Evaluations by Protege
Why we need a better test for healthcare AI — and what we hope better evidence will make possible
Blog –
Apply to Join Protege’s Next Live Event in SF: The State of Training Data, AI’s next bottleneck
The data constraint is the most important problem in scaling AI today.
On August 12th, we are convening leading AI researchers, frontier labs, investors and top technical talent to discuss the next bottleneck in AI:
The need for high-quality real-world data, dynamic evaluation, and the infrastructure needed to turn messy workflows into training signal.
Apply to join our next live Event in San Francisco on August 12:
Related articles
-
-
Protege Evaluation of A Disease Risk Prediction Model by Xlue AI
An Independent Evaluation of a Disease Risk Prediction Model Across 16 Clinical Tasks
Blog – -
Protege Double Blind Evaluation of Oncology Prediction Systems
Double-Blind Comparison of a Specialized Biomedical Model and Frontier Models on Breast and Lung Cancer Outcomes
Blog – -
Disease Odyssey
Healthcare is a journey, and the longer it takes, the less pleasant it becomes. Disease Odyssey evaluates pre-diagnostic reasoning on longitudinal clinical records: can AI shorten the journey by reaching the correct diagnosis faster?
Blog – -
Webinar Replay: Verifying AI in Medicine — Is Healthcare AI Actually Ready for Deployment?
Watch the replay: Isaac Kohane (NEJM AI, Harvard Medical School) and Protege co-founder Engy Ziedan, moderated by Second Opinion's Christina Farr, on verification, trust, and real-world readiness in medical AI.
Blog – -
Protege in the News: Healthcare AI Needs An Independent Referee
Two peer-reviewed journals, three weeks apart. Opposite answers on whether general or clinical AI performs better. Both contained flawed benchmarks...and there's no referee. This editorial…
Blog –
