arXiv Machine Learning

A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications

The paper evaluates the cost‑effectiveness of consensus‑based learning (CBL) versus federated learning (FL) across seven medical datasets, three tasks, and eight modalities involving 3 to 23 clients. CBL achieves accuracy comparable to FL while dramatically cutting training time (15‑fold) and communication cost (60‑fold). The study suggests that CBL offers a more sustainable and democratized approach to deploying collaborative AI in real‑world healthcare settings.

arXiv Machine Learning
5d ago

Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning

FL-Net is a federated learning framework designed for medical research that addresses five key requirements identified in the literature. It offers modular data harmonization, discovery, disclosure control, versioned tools, and containerized workflow execution, enabling reuse of harmonized data and workflows across studies. The framework was evaluated on MIMIC and US-130 datasets, supporting up to 50 concurrent clients and demonstrating reproducible, audited federated workflows.

By Simon S\"uwer, Julian Klemm, Elisa Acitelli, Mathieu Almeida, Lucia Altucci, Zsolt Bagyura, Michelangela Barbieri, Zsolt-Zolt\'an Bed\H{o}, Rosaria Benedetti, B\'ela Bihari, Csongor Csal\'oka, Lucia Dicunta, Stanislav Ehrlich, Bjoern M. Eskofier, S\'andor-J\'ozsef Fej\'er, Georg Fr\"owis, Walter H\"otzendorfer, Alexandra Kautzky-Willer, Jens Johann Georg Lohmann, Marianna Maranghi, Lorenzo Marconi, Rudolf Mayer, Wouter Leonard Megchelenbrink, Monika Moga, Adham Mottalib, Sanjeev Mehta, Madeleine M\"uller, Thomas Nystr\"om, Bal\'azs-Attila Orb\'an, Paul O'Toole, Giuseppe Paolisso, Paolo Parini, Matteo Pedrelli, Enrico Petrillo, Philipp Poindl, Niklas Probul, Anastasia Pustozerova, Tanja \v{S}ar\v{c}evi\'c, Lukas Weilguny, Jan Baumbach, Andreas Maier
arXiv Machine Learning
1d ago

A Federated Artificial Intelligence Framework for Optimizing Pancreatic Cancer Treatment - Strategy Update

arXiv:2609.24718v1 Announce Type: new Abstract: While a centralized approach involving patient consent to collect and analyze data centrally would theoretically offer the best data quality and predic...

By Anne-Christin Hauschild, Amirreza Aleyasin, Nils H. Beyer, Lisa Fricke, Jonas H\"ugel, Maryam Moradpour, Anh-Tien Nguyen, Youngjun Park, Sophia Rheinl\"ander, Tim Beissbarth, Elisabeth Hessmann, Martin Middeke, Matthias Lauth, Maximilian Reichert, Ulrich Sax
arXiv AI
Aug 25

MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM

The paper introduces MACD, a Multi-Agent Clinical Diagnosis framework that enables large language models to self‑learn clinical knowledge through a multi‑agent pipeline of summarization, refinement, and application. MACD is extended into a human‑AI collaborative workflow where multiple diagnostician agents consult iteratively, guided by a judge agent and human oversight. Evaluation on the MIMIC‑MACD cohort shows significant gains in diagnostic accuracy—an average 11.6 percentage‑point improvement over authoritative knowledge for open‑weight LLMs and an 18.3‑percentage‑point boost over physician‑only diagnosis in text‑only vignettes.

By Wenliang Li, Rui Yan, Xu Zhang, Li Chen, Hongji Zhu, Jing Zhao, Junjun Li, Mengru Li, Wei Cao, Zihang Jiang, Wei Wei, Kun Zhang, Shaohua Kevin Zhou