Validating healthcare AI
How a decision-support system is evaluated: the EASY-1 trial
Claims about clinical AI should be settled by evidence, not enthusiasm. EASY Diabetes was evaluated in EASY-1 (NCT03258268), a registered randomized controlled trial that compared the system against standard of care.
A randomized design matters because it isolates the effect of the tool from everything else that changes in busy clinics. The trial compared the decision-support system against standard of care and looked at real outcomes and workflow, not just model metrics.
This is the bar I think clinical AI should meet: a pre-registered trial, real clinical endpoints, and an honest account of what improved. EASY Diabetes received the Medtech4Health Innovation Award.
This article is for general education and is not medical or professional advice. For guidance about your own health, talk with a qualified clinician.
Cite this article
Tojjar, D. (2025). How a decision-support system is evaluated: the EASY-1 trial. Dr. Damon Tojjar. https://readingtheevidence.org/articles/validating-easy1/
This article is part of Dr. Tojjar's guide to Validating healthcare AI.