Enhancing Performance for Highly Imbalanced Medical Data via Data Regularization in a Federated Learning Setting

TL;DR

This paper introduces a data regularization method for federated learning that improves cardiovascular disease prediction accuracy on highly imbalanced, distributed medical datasets while preserving privacy and resource efficiency.

Contribution

It proposes a novel data regularization algorithm tailored for federated learning to address class imbalance in medical datasets, enhancing predictive performance.

Findings

Improved prediction accuracy across four cardiovascular datasets.

Robustness under various hyperparameter settings.

Effective adaptation to different resource scenarios.

Abstract

The increased availability of medical data has significantly impacted healthcare by enabling the application of machine / deep learning approaches in various instances. However, medical datasets are usually small and scattered across multiple providers, suffer from high class-imbalance, and are subject to stringent data privacy constraints. In this paper, the application of a data regularization algorithm, suitable for learning under high class-imbalance, in a federated learning setting is proposed. Specifically, the goal of the proposed method is to enhance model performance for cardiovascular disease prediction by tackling the class-imbalance that typically characterizes datasets used for this purpose, as well as by leveraging patient data available in different nodes of a federated ecosystem without compromising their privacy and enabling more resource sensitive allocation. The method is evaluated across four datasets for cardiovascular disease prediction, which are scattered across different clients, achieving improved performance. Meanwhile, its robustness under various hyperparameter settings, as well as its ability to adapt to different resource allocation scenarios, is verified.