AI model helps some patients get diagnoses after years of uncertainty: Study
A study in the New England Journal of Medicine shows an AI model helped diagnose 18 children with rare diseases. The research involved Boston Children's Hospital and OpenAI. Human experts and certified clinical labs confirmed every result.
What changed
New details identify the specific AI model as OpenAI's o3 and the research location as Boston Children's Hospital.
Live updates
-
AI Model Identifies Rare Diseases in 18 Children
confidence 90%A study in the New England Journal of Medicine shows an AI model helped diagnose 18 children with rare diseases. The research involved Boston Children's Hospital and OpenAI. Human experts and certified clinical labs confirmed every result.
What's confirmed:
- An AI model helped diagnose 18 children with rare diseases that had previously stumped doctors.
- The study was published in the New England Journal of Medicine.
- Research was conducted by OpenAI and Boston Children's Hospital.
- Certified clinical labs and human experts confirmed all results.
Still unconfirmed:
- OpenAI's o3 model was the specific tool used to find these medical answers.
- The average diagnosis of a rare disease in the UK takes around 5.6 years.
- Rare diseases collectively affect around one in 10 people globally.
-
AI Model Identifies Rare Diseases in Pediatric Patients
confidence 90%A study published in the New England Journal of Medicine shows an AI model helped diagnose 18 children with rare diseases. These patients had previously stumped doctors for years. The tool focuses on identifying leads for rare genetic conditions.
What's confirmed:
- An AI model helped diagnose 18 children with rare diseases that had stumped doctors.
- The findings were published in a New England Journal of Medicine study.
- Over 30 million Americans, including half who are children, have a rare disease.
Still unconfirmed:
- OpenAI was the specific entity that found the 18 rare diseases.
- The patients were specifically based in Boston.