Effective Non-IID Degree Estimation for Robust Federated Learning in Healthcare Datasets
Authors:
Open Access
- 22 March 2025
- journal article
- research article
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 9 (3) , 437-464
Abstract
Building unbiased and robust machine learning models using datasets from multiple healthcare systems is critical for addressing the needs of diverse patient populations. However, variations in patient demographics and healthcare protocols across systems often lead to significant differences in data distributions. Not Independent and Not Identically Distributed (non-IID) data presents a major challenge in developing effective federated learning (FL) frameworks. This study proposes a method to estimate the non-IID degree between datasets and introduces three metrics (variability, separability, and computational time) to evaluate and compare the performance of non-IID degree estimation methods. We developed a novel non-IID FL algorithm that incorporates the proposed non-IID degree estimation index as regularization into existing FL algorithms for acute kidney injury risk (AKI) prediction. Our results demonstrate that the proposed method for estimating non-IID degree outperforms previous approaches by effectively identifying differences in data distributions between datasets, consistently producing similar estimates of non-IID degree when evaluating different subsamples from the same dataset, requiring significantly less computational time, and providing better interpretability. Finally, we showed that the proposed non-IID FL algorithm achieves higher test accuracy than local learning, concurrent FL algorithms, and centralized learning for the AKI prediction task.Keywords
Funding Information
- National Science and Technology Council (MOST 111-2321-B-468-001, MOST 111-2321-B-468-001, MOST 111-2321-B-468-001, MOST 111-2321-B-468-001, MOST 111-2321-B-468-001)
- Shumaker Endowment for Biomedical Informatics
- National Institutes of Health (5T32LM012410)
This publication has 44 references indexed in Scilit:
- Low-Parameter Federated Learning with Large Language Models2024
- A comprehensive survey of federated transfer learning: challenges, methods and applicationsFrontiers of Computer Science, 2024
- A distribution information sharing federated learning approach for medical image dataComplex & Intelligent Systems, 2023
- Multi-center federated learning: clients clustering for better personalizationWorld Wide Web, 2022
- Beyond bias and discrimination: redefining the AI ethics principle of fairness in healthcare machine-learning algorithmsAI & SOCIETY, 2022
- A state-of-the-art survey on solving non-IID data in Federated LearningFuture Generation Computer Systems, 2022
- An overview of distance and similarity functions for structured dataArtificial Intelligence Review, 2020
- Addressing Bias in Artificial Intelligence in Health CareJAMA, 2019
- Multiple imputation using chained equations: Issues and guidance for practiceStatistics in Medicine, 2010
- Pattern Recognition and Density Estimation under the General i.i.d. Assumption2001