In real-world test, an AI model did better than ER doctors at diagnosing patients

""This is the big conclusion for me - it works with the messy real-world data of the emergency department. It works for making diagnoses in the real world.""

""The AI model matched and often outperformed doctors and the earlier AI model, Chat GPT-4, in diagnosing patients and managing their care.""

A patient with a pulmonary embolism worsened despite treatment, leading to AI intervention. The AI identified a history of lupus as a potential cause. Researchers from Harvard Medical School and Beth Israel Deaconess Medical Center found that an AI model developed by OpenAI excelled in diagnosing patients and managing care, often outperforming doctors. The AI was tested on real-world cases and demonstrated effectiveness in the emergency department, providing accurate diagnoses using electronic health records and limited information.

Read at www.npr.org