Study Finds AI Medical Diagnosis Errors Exceed 80%
A new study suggests that generative AI has yet to develop the level of reasoning required for safe use in clinical settings. While recent systems show stronger performance when given detailed patient information, researchers found they still struggle with one of the most critical aspects of medical decision-making. The analysis, conducted by Mass General Brigham researchers, examined how large language models handle diagnostic tasks. Their findings, published in JAMA Network Open, indicate that these systems fall short when it comes to the complex thinking processes doctors rely on in real-world practice. According to co-author Marc Succi, current models are not suitable for independent clinical use. He pointed out that despite steady progress,…