Digital Health & AI
A retrospective study in NEJM AI found that OpenAI's o3 Deep Research model produced candidate gene-phenotype hypotheses that, after expert review and CLIA-certified lab confirmation, yielded a 4.8% incremental diagnostic rate in cases that had already stumped specialists — the AI made no diagnoses on its own.
Owen Tanaka, Digital Health & AI Desk · 3 min read
For the families of children with rare genetic diseases, the path to a diagnosis can stretch across years, dozens of specialists, and still end without an answer. A study published June 18, 2026, in NEJM AI suggests that AI-assisted genomic reanalysis may open a narrow but meaningful door for some of those families — provided human geneticists remain firmly in the final seat.
Researchers at Boston Children’s Hospital’s Manton Center for Orphan Disease Research, Harvard University, and OpenAI applied the o3 Deep Research reasoning model to 376 de-identified pediatric cases that had previously undergone genetic testing and expert review without reaching a diagnosis. After the AI surfaced candidate gene-phenotype links and human clinical geneticists independently evaluated each output, 18 cases resulted in confirmed diagnoses — an incremental diagnostic yield of 4.8%.
Continue reading →