A Federated Learning Platform as a Service for Advancing Stroke Management in European Clinical Centers

TL;DR

This paper presents a secure, PaaS-based federated learning platform utilizing MQTT protocol, designed to facilitate collaborative AI model training in healthcare, specifically for stroke management, while addressing data privacy and security concerns.

Contribution

It introduces a novel federated learning platform architecture tailored for clinical environments, emphasizing security, configurability, and operational management, tested with real datasets.

Findings

Platform successfully tested in operational environments

Enhanced data privacy through federated learning approach

Proven effectiveness with publicly available datasets

Abstract

The rapid evolution of artificial intelligence (AI) technologies holds transformative potential for the healthcare sector. In critical situations requiring immediate decision-making, healthcare professionals can leverage machine learning (ML) algorithms to prioritize and optimize treatment options, thereby reducing costs and improving patient outcomes. However, the sensitive nature of healthcare data presents significant challenges in terms of privacy and data ownership, hindering data availability and the development of robust algorithms. Federated Learning (FL) addresses these challenges by enabling collaborative training of ML models without the exchange of local data. This paper introduces a novel FL platform designed to support the configuration, monitoring, and management of FL processes. This platform operates on Platform-as-a-Service (PaaS) principles and utilizes the Message Queuing Telemetry Transport (MQTT) publish-subscribe protocol. Considering the production readiness and data sensitivity inherent in clinical environments, we emphasize the security of the proposed FL architecture, addressing potential threats and proposing mitigation strategies to enhance the platform's trustworthiness. The platform has been successfully tested in various operational environments using a publicly available dataset, highlighting its benefits and confirming its efficacy.