[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-openais-o1-model-trims-time-to-diagnose-rare-diseases":10},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":22,"tags":24,"sources":28,"feedback":32,"feedback_at":22,"cost_usd":32,"total_tokens":32},1138,"openais-o1-model-trims-time-to-diagnose-rare-diseases","OpenAI's o1 model trims time to diagnose rare diseases","A geneticist shows the new system can accelerate rare‑condition diagnostics, signaling another step for AI in clinical genomics.","OpenAI’s latest model, o1, helped a geneticist shave weeks off the diagnostic workflow for obscure medical cases. Catherine Brownstein demonstrated the tool on a handful of patients with undiagnosed rare diseases, using it to prioritize candidate gene variants and suggest likely pathogenicity. The pilot showed a noticeable speedup compared with the manual review process she typically follows.\n\nThe demo matters because rare‑disease diagnosis has long been a bottleneck in precision medicine. Faster variant triage could mean earlier treatment decisions and less costly “diagnostic odysseys” for families. While OpenAI touts o1 as a general‑purpose reasoning engine, its application to genomics hints that the same approach could be repurposed across other data‑intensive medical tasks.\n\nThe move follows a series of AI‑driven genetics milestones, from DeepMind’s AlphaFold protein‑structure predictions to large‑language‑model‑based variant annotation tools. Unlike those, o1 is marketed as a reasoning‑first system rather than a specialised predictor, which may let it adapt more quickly to new disease frames. Still, the demonstration was limited to a small cohort, and real‑world adoption will depend on regulatory clearance and integration with existing laboratory pipelines. The excitement will likely be tempered until peer‑reviewed results appear.","[\"ai\",\"genomics\",\"healthtech\"]","2024-09-12T00:00:00.000Z","2026-06-16T12:47:56.142Z","2026-06-16T12:47:59.193Z","published",null,[],[25,26,27],"ai","genomics","healthtech",[29],{"name":30,"url":31},"OpenAI","https:\u002F\u002Fopenai.com\u002Findex\u002Fo1-genetics",0]