EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Asynchronous proximal federated aggregation for heterogeneous healthcare networks

Manakkattu Sreelakshmi, Radhakrishnan Delhibabu

Frontiers in Digital Health · 17.07.2026 · 8

DOI: 10.3389/fdgth.2026.1879670 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Digital Health, online erschienen am 17.07.2026. Verfasst von Manakkattu Sreelakshmi und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering (SCOPE) and the Department of Quantum AI, Vellore Institute of Technology (VIT), Vellore, Tamil Nadu, Indi…. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The deployment of Federated Learning (FL) across the Internet of Medical Things (IoMT) is severely hindered by computational asymmetry and statistical heterogeneity. Traditional synchronous aggregation protocols suffer from severe straggler effects when deployed across devices with varying computational capacities, such as hospital servers vs. ambulatory wearables.

Methods

In this study, we propose the Asynchronous Proximal Federated Aggregation (APFA) framework to address these dual bottlenecks. APFA integrates a local proximal regularizer with a server-side staleness dampening penalty, permitting continuous, uncoordinated model updates from edge devices.

Results

Evaluated on highly skewed partitions of the CheXpert and MIMIC-IV datasets, APFA reached an 80% diagnostic viability threshold in just 4.1 simulated hours, representing a 71% reduction in total wait time compared to standard synchronous baselines like FedProx.

Discussion

Our mathematical integration effectively mitigates weight divergence, indicating the robustness of asynchronous machine learning for scalable, privacy-preserving clinical diagnostics.

Schlagwörter

Stichwörter der Autor:innen

Internet of Medical Things (IoMT)asynchronous aggregationfederated learninghealthcare analyticsnon-IID dataprivacy-preserving machine learning

Autor:innen und Institutionen

  • School of Computer Science and Engineering (SCOPE) and the Department of Quantum AI, Vellore Institute of Technology (VIT), Vellore, Tamil Nadu, India.

Zitieren

APA

Sreelakshmi, M., & Delhibabu, R. (2026). Asynchronous proximal federated aggregation for heterogeneous healthcare networks. Frontiers in Digital Health, 8. https://doi.org/10.3389/fdgth.2026.1879670

Vancouver

Sreelakshmi M, Delhibabu R. Asynchronous proximal federated aggregation for heterogeneous healthcare networks. Frontiers in Digital Health. 2026;8. doi:10.3389/fdgth.2026.1879670

BibTeX
@article{Sreelakshmi2026,
  author = {Sreelakshmi, Manakkattu and Delhibabu, Radhakrishnan},
  title = {Asynchronous proximal federated aggregation for heterogeneous healthcare networks},
  journal = {Frontiers in Digital Health},
  year = {2026},
  volume = {8},
  doi = {10.3389/fdgth.2026.1879670}
}
Kostenlos starten →