Federated Learning for Clinical Structured Data: A Benchmark Comparison of Engineering and Statistical Approaches

Abstract

Federated learning (FL) has shown promising potential in safeguarding data privacy in healthcare collaborations. While the term "FL" was originally coined by the engineering community, the statistical field has also explored similar privacy-preserving algorithms. Statistical FL algorithms, however, remain considerably less recognized than their engineering counterparts. Our goal was to bridge the gap by presenting the first comprehensive comparison of FL frameworks from both engineering and statistical domains. We evaluated five FL frameworks using both simulated and real-world data. The results indicate that statistical FL algorithms yield less biased point estimates for model coefficients and offer convenient confidence interval estimations. In contrast, engineering-based methods tend to generate more accurate predictions, sometimes surpassing central pooled and statistical FL models. This study underscores the relative strengths and weaknesses of both types of methods, emphasizing the need for increased awareness and their integration in future FL applications.

References in corpus (15)

• Federated Learning: Challenges, Methods, and Future Directions
• The European Union general data protection regulation: what it is and what it means
• Multitask learning and benchmarking with clinical time series data
• Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
• Fair Resource Allocation in Federated Learning
• A Field Guide to Federated Optimization
• Federated Tensor Factorization for Computational Phenotyping
• Benchmarking emergency department triage prediction models with machine learning and large public electronic health records
• A review of distributed statistical inference
• The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
• Federated and distributed learning applications for electronic health records and structured medical data: A scoping review
• FedEval: A Holistic Evaluation Framework for Federated Learning
• FedScore: A privacy-preserving framework for federated scoring system development
• A synthetic data integration framework to leverage external summary-level information from heterogeneous populations
• Augmented Transfer Regression Learning with Semi-non-parametric Nuisance Models

Cited by in corpus (2)

• FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction
• Developing Federated Time-to-Event Scores Using Heterogeneous Real-World Survival Data