Research3 min read

Apple launches health AI study with OpenEvidence for up to 200,000 users

Apple has opened a US research study that lets up to 200,000 iPhone users ask health questions of an AI built with OpenEvidence. It's one of the largest real-world tests yet of how people trust and act on conversational health AI.

AE
Aidose Editorial
Nov 16, 2026

Apple has launched the Apple Health AI Usage Study, a virtual research study run through a new iPhone app, Apple announced on November 15. The study looks at how people use conversational AI for health questions, and it is run with OpenEvidence, a clinical AI platform.

Up to 200,000 eligible participants can enroll. They must be 21 or older, live in the United States, and have an Apple Intelligence-enabled iPhone (iPhone 15 Pro or later) running iOS 26 or later. According to Apple, OpenEvidence's answers draw on sources including the New England Journal of Medicine, JAMA and Nature.

The study measures participants' trust in health AI, the quality of its responses, how well people understand them, and what health actions they take afterward. Participants can choose to share HealthKit data such as resting heart rate, sleep or lab results, and researchers will look at whether that data makes answers more relevant and easier to understand. They will also look at whether the tool helps people prepare for doctor visits.

Apple says study data will not be used to train AI models, and that participants decide whether to share HealthKit metrics or survey responses. The app has guardrails that flag certain concerning questions and suggest following up with a provider. Apple stresses that the app is not meant to diagnose or treat conditions.

"Health is deeply personal," said Sumbul Desai, M.D., Apple's vice president of Health and Fitness. Robert M. Wachter, M.D., chair of the Department of Medicine at UCSF, said that when patients and doctors use the same trustworthy tools, "patients arrive prepared, conversations improve, and next steps happen seamlessly."

For teams building health AI, the study is notable for its scale and for testing personal health data as context for answers. A study of up to 200,000 people could give Apple, and later the field, real evidence on whether grounding answers in someone's own health data makes them more useful and how far people trust AI health advice.

AE
Aidose Editorial
Nov 16, 2026 · 3 min read
Back to News