[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-can-now-run-a-medical-literature-review-for-23":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},2549,"ai-can-now-run-a-medical-literature-review-for-23","AI Can Now Run a Medical Literature Review for $23","LUMEN automates systematic reviews end-to-end using 11 specialized agents, completing work that takes humans 67 weeks for under $30.","A new open-source pipeline puts a price tag on AI-assisted medical research — and it's surprisingly low.\n\nResearchers introduced LUMEN, a multi-agent system that automates six phases of a systematic review and meta-analysis using 11 specialized language models. Tested across seven datasets spanning psychiatry, surgery, cardiology, and other fields, the pipeline achieved 100% directional agreement with published meta-analyses, with effect sizes within 1% for homogeneous study designs. A complete review costs between $19 and $29, with a median of $22.65. Title-abstract screening and data extraction together account for most of that spend.\n\nThe cost transparency is the real contribution here. Prior work showed LLMs could handle individual pieces — screening at 96.7% sensitivity, extraction at 91.0% accuracy — but no one had published what a full pipeline actually costs or where the money goes. Knowing that changes how research teams can budget and prioritize automation. The finding that multi-agent design *hurts* screening but is essential for extraction (producing 5.7x more poolable analyses than single-model approaches) suggests blanket architectural choices are a mistake.\n\nThe authors also note that model rankings shift by domain, meaning a model that performs well on psychiatry reviews may underperform on cardiology — a quiet warning against assuming any one setup transfers cleanly to new territory.","[\"ai\",\"research\",\"healthcare\",\"open-source\"]","2026-06-30T04:00:00.000Z","2026-06-30T07:56:12.140Z","2026-06-30T07:56:15.096Z","published",null,[],"ai",[24,26,27,28],"research","healthcare","open-source",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.28362",0,{"sections":35},[36,40,45,50,55,60,65,70,75,80,85,89,94,99],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":86,"slug":87,"count":83,"latest_published_at":88},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]