[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-an-ai-that-decides-which-alzheimers-tests-you-actually-need":10,"sections":34},{"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":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},9519,"an-ai-that-decides-which-alzheimers-tests-you-actually-need","An AI That Decides Which Alzheimer's Tests You Actually Need","Researchers built an AI agent that picks its own Alzheimer's diagnostic tests, matching full testing accuracy at a fraction of the cost.","An AI agent can now decide which Alzheimer's tests you actually need, not just read the results.\n\nResearchers built a system called SCOPE-AD that treats Alzheimer's screening like a sequential decision problem instead of a one-shot prediction. The model tracks a patient's status along the continuum from cognitively normal to mild cognitive impairment to full Alzheimer's, choosing one diagnostic test at a time and updating its belief after each result. A teacher model trained on historical patient records estimates which tests are worth their cost, and those decisions get distilled into a smaller policy model built on Qwen. Tested on the ADNI dataset, the system hit 77.70% Macro-F1 accuracy while spending an average of $50.46 per patient on tests.\n\nThat cost number is the real story. Running every available test only nudged accuracy up by 1.89 points, but it cost 116.7 times more. For a disease where diagnostic workups already strain patients and health systems, an agent that knows when to stop testing is worth more than one that squeezes out another percentage point.\n\nDon't expect this in a clinic soon. ADNI is a curated research cohort, not the messy reality of a memory clinic waiting room, and a policy trained to minimize cost still needs validation on what it decides not to test for.","[\"ai\",\"healthcare\",\"alzheimers\",\"medical-ai\"]","2026-10-02T04:00:00.000Z","2026-10-02T22:55:49.746Z","2026-10-02T22:56:00.989Z","published",null,[],"ai",[24,26,27,28],"healthcare","alzheimers","medical-ai",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.01278",0,{"sections":35},[36,39,43,47,52,56,60,65,70,75,80,85,90,95],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",5886,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",835,{"name":44,"slug":45,"count":46,"latest_published_at":18},"Policy","policy",438,{"name":48,"slug":49,"count":50,"latest_published_at":51},"Deals","deals",317,"2026-10-01T22:00:00.000Z",{"name":53,"slug":54,"count":55,"latest_published_at":18},"Hardware","hardware",199,{"name":57,"slug":58,"count":59,"latest_published_at":18},"Science","science",171,{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",155,"2026-10-01T19:54:10.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Dev Tools","dev-tools",96,"2026-10-01T16:57:03.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",93,"2026-09-30T21:41:11.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Startups","startups",90,"2026-10-01T21:55:22.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]