paper-with-me

홈 › Papers

LUMEN: Cost-Transparent Multi-Agent Pipeline for Automated Systematic Review and Meta-Analysis

2026-03-29 · Yen-Hsun Huang, Yu-Shiou Lin arxiv

Systematic reviews and meta-analyses (SR/MA) remain the gold standard for evidence synthesis, yet completing one typically requires 67 weeks and substantial expert effort. Recent large language model (LLM) systems have demonstrated strong performance on individual SR phases - screening (otto-SR: 96.7% sensitivity), extraction (Gartlehner et al.: 91.0% accuracy), and search (TrialMind: 0.83 recall) - but no study has reported what it actually costs to run an end-to-end pipeline, how cost distributes across phases, or how architectural choices affect the cost-quality trade-off. We present LUMEN, an open-source multi-agent pipeline that automates six SR/MA phases using 11 specialized LLM agents with deliberate model routing. We evaluate LUMEN on seven datasets: five self-conducted domain reviews (psychiatry, psychology, surgery, vaccinology, cardiology) and two SYNERGY screening benchmarks. Across 13 ground-truth-comparable outcomes, LUMEN achieves 100% directional agreement with published meta-analyses, with effect sizes within 1% for homogeneous study designs. The primary contribution is the first empirical cost and operational characterization of such a pipeline: a complete review costs 19 to 29 USD (median 22.65 USD), with title-abstract screening and data extraction together dominating expenditure. A three-arm extraction ablation reveals a phase-dependent architecture reversal: multi-agent design hurts screening but is essential for extraction, producing 5.7x more poolable analyses than single-model alternatives while eliminating clinically dangerous direction errors. A two-dataset screening benchmark demonstrates that model ranking is domain-dependent and not transferable across review topics. All code and cost logs are publicly available.

📄 PDF Abstract BibTeX arXiv:2606.28362

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SoftEnNet: Symbiotic Monocular Depth Estimation and Lumen Segmentation for Colonoscopy Endorobots

2023-01-19 · Alwyn Mathew, Ludovic Magerand, Emanuele Trucco, Luigi Manfredi

Colorectal cancer is the third most common cause of cancer death worldwide. Optical colonoscopy is the gold standard for detecting colorectal cancer; however, about 25 percent of polyps are missed during the procedure. A…

Depth EstimationMonocular Depth EstimationRobot NavigationSegmentation

A Deep Learning Approach to Automate High-Resolution Blood Vessel Reconstruction on Computerized Tomography Images With or Without the Use of Contrast Agent

2020-02-09 · Anirudh Chandrashekar, Ashok Handa, Natesh Shivakumar, Pierfrancesco Lapolla 외

Existing methods to reconstruct vascular structures from a computed tomography (CT) angiogram rely on injection of intravenous contrast to enhance the radio-density within the vessel lumen. However, pathological changes …

Computed Tomography (CT)Data AugmentationManagementMorphological Analysis

AortaDiff: A Unified Multitask Diffusion Framework For Contrast-Free AAA Imaging

2025-10-01 · Yuxuan Ou, Ning Bi, Jiazhen Pan, Jiancheng Yang 외 arxiv

While contrast-enhanced CT (CECT) is standard for assessing abdominal aortic aneurysms (AAA), the required iodinated contrast agents pose significant risks, including nephrotoxicity, patient allergies, and environmental …

Multi-Task Learning

CNN-based automatic segmentation of Lumen & Media boundaries in IVUS images using closed polygonal chains

2023-09-29 · Pavel Sinha, Ioannis Psaromiligkos, Zeljko Zilic

We propose an automatic segmentation method for lumen and media with irregular contours in IntraVascular ultra-sound (IVUS) images. In contrast to most approaches that broadly label each pixel as either lumen, media, or …

Decoder

Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute

2023-01-25 · Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Joshua Ainslie 외

Retrieval-augmented language models such as Fusion-in-Decoder are powerful, setting the state of the art on a variety of knowledge-intensive tasks. However, they are also expensive, due to the need to encode a large numb…

DecoderQuestion AnsweringRetrieval