The ChatGPT Health controversy: what the viral Nature Medicine study missed with David Fraile Navarro

About this episode

The episode discusses the implications of a viral study on ChatGPT Health and its evaluation in medical triage.

Welcome to Pulse: Amplify, where we sit down with the leaders and changemakers shaping the future of health. A recent Nature Medicine study went viral after reporting that ChatGPT Health under-triaged more than half of emergency cases when tested using clinician-written scenarios. The finding raised serious concerns about whether consumer AI tools are safe for medical triage. But researchers from Macquarie University’s Australian Institute of Health Innovation took a closer look at the study design and suspected the results might reflect the evaluation format rather than the AI’s clinical capability . In this episode of Pulse Amplify, Louise and George speak with David Fraile Navarro about their follow-up study testing five frontier AI models across more than a thousand trials. Their research suggests that when AI systems are evaluated using more natural, patient-style interactions rather than exam-style prompts , triage performance improves significantly. The discussion explores why prompt structure, forced answer formats, and restrictions on clarifying questions can dramatically alter model behaviour, and why designing realistic evaluation methods is essential as millions of…

People in this episode

Hosts: Louise, George

Guest: David Fraile Navarro

Topics covered

• AI in healthcare
• medical triage
• evaluation methods
• patient interactions
• AI safety

Keywords

• ChatGPT Health
• AI tools
• emergency cases
• triage performance
• evaluation format

Mentioned in this episode

Organizations: Macquarie University, Australian Institute of Health Innovation

Books & works: Nature Medicine

More episodes of PULSE

• The Data Behind Europe's Quiet Digital Health Powerhouse, with Inma Rodríguez ACCIÓ · June 11, 2026 · 26 min
• AI, Patients, Prediction and the Foothills of the Singularity · June 4, 2026 · 39 min
• Your Fear of AI Is Prehistoric - with Dr Nick van Terheyden · May 28, 2026 · 32 min
• Westminster in Crisis, Wearables Get Clinical, and the Grown-Up Guide to AI · May 21, 2026 · 43 min
• Hold Fast: AI, Humanity and the Future of Aged Care with Donald Macaskill · May 14, 2026 · 30 min
• AI – now with Clinical Reasoning; the Paradox of Medical AI and OpenEvidence Pulls Out of Europe · May 7, 2026 · 43 min