Validating healthcare AI
Bringing AI decision support to diabetes care
Decision support earns its place in the clinic only when it is validated where care actually happens. EASY Diabetes, the type 2 diabetes decision-support system I co-developed and led as Head of Medical and Science, was evaluated in the EASY-1 randomized controlled trial (NCT03258268) against standard of care.
The result that matters is not a benchmark on a held-out dataset. It is whether clinicians make better decisions and patients do better. In EASY-1 (NCT03258268), a registered randomized controlled trial, the EASY Diabetes decision-support system was compared against standard of care. The work received the Medtech4Health Innovation Award.
The lesson generalizes. Useful clinical AI is clinically grounded, validated in real settings, transparent, and built to fit the way clinicians already work. Everything else is a demo.
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. (2023). Bringing AI decision support to diabetes care. Dr. Damon Tojjar. https://readingtheevidence.org/articles/ai-decision-support/
This article is part of Dr. Tojjar's guide to Validating healthcare AI.