The Breakdown In 18% of cases, Claude, GPT-5 and Gemini fabricated medical diagnoses, despite supporting images being omitted. The AI models used demographic-based clinical assumptions to invent these diagnoses. CMU research emphasizes the need for demographic sensitivity testing and verification before deploying AI tools in medical systems. * * * Siddharth Vohra is a [...] The post Healthcare Blind Spots: AI Models Prone To Fabricating Diagnoses appeared first on Robotics Institute Carnegie Mellon University .