Research on 21 large language models shows that AI does not yet have the ability to independently diagnose and treat clinical diseases

On April 14, despite the increasing application of artificial intelligence (AI) in the medical field, its ability to "think like a doctor" still has obvious shortcomings. A recent study conducted by the MESH incubator team at Massachusetts General Hospital found that generative AI is still insufficient in key aspects of clinical reasoning and does not yet have the ability to independently undertake clinical diagnosis and treatment tasks. Relevant results were published in the latest issue of "JAMANetworkOpen". The team selected 21 large-language models including ChatGPT, DeepSeek, Claude, Gemini and Grok, tested them in 29 published clinical cases, and simulated the real diagnosis and treatment process by gradually providing patient information (from basic symptoms to laboratory and imaging results). The results showed that when complete information was obtained, all models gave the correct final diagnosis in more than 90% of cases. (Science and Technology Daily)