Investigating privacy-preserving machine learning for healthcare data sharing through federated learning

Abstract

Privacy-Preserving Machine Learning (PPML) is a pivotal paradigm in healthcare research, offering innovative solutions to the challenges of data sharing and privacy preservation. In the context of Federated Learning, this paper investigates the implementation of PPML for healthcare data sharing, focusing on the dynamic nature of data collection, sample sizes, data modalities, patient demographics, and comorbidity indices. The results reveal substantial variations in sample sizes across substudies, underscoring the need to align data collection with research objectives and available resources. The distribution of measures demonstrates a balanced approach to healthcare data modalities, ensuring data fairness and equity. The interplay between average age and sample size highlights the significance of tailored privacy-preserving strategies. The comorbidity index distribution provides insights into the health status of the studied population and aids in personalized healthcare. Additionally, the fluctuation of sample sizes over substudies emphasizes the adaptability of privacy-preserving machine learning models in diverse healthcare research scenarios. Overall, this investigation contributes to the evolving landscape of healthcare data sharing by addressing the challenges of data heterogeneity, regulatory compliance, and collaborative model development. The findings empower researchers and healthcare professionals to strike a balance between data utility and privacy preservation, ultimately advancing the field of privacy-preserving machine learning in healthcare research.