Stay up to date with notifications from The IndependentNotifications can be managed in browser preferences.Jump to contentThank you for registeringPlease refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged inAllNewsSportCultureLifestyleA new study published in NEJM AI indicates that OpenAI’s o3 model can help diagnose previously unsolved medical mysteries. The AI model, released in April 2025, assisted in identifying new diagnoses for 18 children at Boston Children’s Hospital, including those with rare neurodevelopmental and neuromuscular disorders. Researchers analysed 376 genomes from undiagnosed patients, with the AI model successfully identifying nearly five per cent of new diagnoses, a result described as a “total game changer.”One patient, Kyra Benton, who had experienced undiagnosed symptoms since age nine, finally received a diagnosis of myofibrillar myopathy with the aid of the AI. The study highlights that the AI model functions as a diagnostic tool, processing patient data and doctors' notes, with human review essential for final diagnoses, and is not intended for self-diagnosis. In full18 children had illnesses so rare doctors were stumped. AI gave them answersThank you for registeringPlease refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in

Researchers from Boston Children’s Hospital identified 18 diagnoses for children with rare diseases using OpenAI’s o3 model.

An AI model is helping some patients get diagnoses after years of unexplained illness, according to a new study published Thursday.

OpenAI’s o3 model can help find answers to the unsolved mysteries in the medical field, according to a new study

Stay up to date with notifications from The IndependentNotifications can be managed in browser preferences.Jump to contentThank you for registeringPlease refresh the page or…