Significant progress has been made in the application of artificial intelligence in healthcare, but a study reveals the limitations of general AI like ChatGPT in complex medical diagnoses. The research, led by medical educator Amrit Kirpalani from Western University in Ontario, Canada, found that ChatGPT made errors in 76 out of 150 complex medical cases, resulting in an error rate exceeding 50%. The case library used in this study is closer to real medical situations than the US Medical Licensing Examination, containing various complications and diagnostic challenges. The study points out that Ch
