共识学习在现实医疗应用中的成本效益基准研究:优于联邦学习?
A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications
该文章在Scientific Reports发表,提出并评估了共识学习(CBL)作为联邦学习(FL)替代方案的可行性。在包含7个医疗数据集、3种任务、8种模态的基准测试中,CBL方法在精度上与FL相当,但训练时间减少15倍、通信成本降低131倍(p<0.05)。作者认为CBL是更具成本效益和可持续性的协作AI部署路径,有助于减轻对大规模计算资源的依赖。
- Article
- Open access
- Published: 01 October 2026
- Francesco Cremonesi1 na1,
- Lucia Innocenti1,2 na1,
- Vicky Goh2,
- Sebastien Ourselin2,
- Michela Antonelli2 na2 &
- …
- Marco Lorenzi1 na2
Scientific Reports (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Federated learning (FL) has gained wide popularity as a collaborative learning paradigm allowing collaborative Artificial Intelligence (AI) in sensitive healthcare applications. Nevertheless, the practical implementation of FL presents technical and organizational challenges, as it generally requires complex communication infrastructures. In this context, consensus-based learning (CBL) may represent a promising alternative for collaborative learning, allowing the combination of local knowledge into a federated decision system, while potentially reducing deployment overhead. Nevertheless, a comprehensive assessment of the viability of consensus-based learning as a cost-effective and sustainable alternative to federated learning has not yet been conducted. In this work we propose an extensive benchmark of the accuracy, cost-effectiveness, and sustainability of a panel of FL and CBL methods in a wide range of collaborative medical data analysis scenarios. The benchmark includes 7 different medical datasets, encompassing 3 machine learning tasks, 8 different data modalities, and multi-centric settings involving 3 to 23 clients. Our results reveal that CBL is a cost-effective and more sustainable alternative to FL. When compared across the panel of medical datasets in the considered benchmark, CBL methods provide equivalent accuracy to the one achieved by FL. Nonetheless, CBL significantly reduces training time and communication cost (resp. 15 fold and 131 fold decrease) (p-value< 0.05). This study opens a novel perspective on the deployment of collaborative AI in real-world applications, whereas the adoption of cost-effective methods is instrumental to achieve sustainability and democratization of AI by alleviating the need for extensive computational resources.
Similar content being viewed by others



Funding
LI and ML are supported by the 3IA Côte d’Azur Investments in the Future project managed by the National Research Agency (ref.n ANR-15-IDEX-01 and ANR-19-P3IA-0002). ML is funded by the grants (TRAIN ANR-22-FAI1-0003) and (Fed-BioMed ANR-19-CE45-0006). The other authors have no funding to report.
Author information
Author notes
These authors contributed equally to this work as joint first authors: Francesco Cremonesi and Lucia Innocenti.
These authors contributed equally to this work as joint last authors: Marco Lorenzi and Michela Antonelli.
Authors and Affiliations
Epione Research Group, Inria Center of Université Côte d’Azur, Nice , France
Francesco Cremonesi, Lucia Innocenti & Marco Lorenzi
King’s College London, London, UK
Lucia Innocenti, Vicky Goh, Sebastien Ourselin & Michela Antonelli
Authors
- Francesco Cremonesi
- Lucia Innocenti
- Vicky Goh
- Sebastien Ourselin
- Michela Antonelli
- Marco Lorenzi
Corresponding author
Correspondence to Marco Lorenzi.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Cremonesi, F., Innocenti, L., Goh, V. et al. A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications. Sci Rep (2026). https://doi.org/10.1038/s41598-026-70599-y
Received: 11 August 2025
Accepted: 03 September 2026
Published: 01 October 2026
DOI: https://doi.org/10.1038/s41598-026-70599-y
来源:Nature 健康护理主题 · nature.com