A new open-source pipeline puts a price tag on AI-assisted medical research — and it's surprisingly low.
Researchers 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.
The 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.
The 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.