OpenAI and Harvard study: o3 Deep Research model aids diagnosis of rare pediatric diseases, yielding 4.8% additional diagnoses
Original title:Using AI to help physicians diagnose rare genetic diseases affecting children
AI summary
Boston Children's Hospital, Harvard University and OpenAI published a study in NEJM AI. The team used the OpenAI o3 Deep Research reasoning model to reanalyze 376 previously undiagnosed rare disease cases, producing evidence-based candidate explanations. After expert review, additional testing and clinical confirmation, doctors established diagnoses in 18 cases, an additional diagnostic rate of 4.8%. The study shows that AI-assisted workflows can help experts generate testable hypotheses in unsolved cases, making periodic reanalysis more scalable. The model does not diagnose directly or make clinical decisions, providing only evidence chains for expert review.
Key Takeaways
- Boston Children's Hospital,Harvard University and OpenAI published a study in NEJM AI.
- The team used the OpenAI o3 Deep Research reasoning model to reanalyze 376 previously undiagnosed…
- After expert review,additional testing and clinical confirmation,doctors established diagnoses in…
- The study shows that AI-assisted workflows can help experts generate testable hypotheses in…
- The model does not diagnose directly or make clinical decisions,providing only evidence chains for…
Quick Facts
- Published
- Updated
- Source
- OpenAI:官网动态(RSS · 排除企业/客户案例)
- Category
- Papers & Research
- AI score
- 72
这是AI辅助罕见病诊断的严肃实证,4.8%的新诊断率在专家反复分析过的病例里相当扎实。虽然离临床落地还很远,但证明推理模型能帮专家从旧数据里挖出新线索。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: OpenAI and Harvard study: o3 Deep Research model aids diagnosis of rare pediatric diseases, yielding 4.8% additional diagnoses. June 18, 2026. https://new.nat6.net/en/news/cmqjmtwvi04vqslmh55vbp7oh/