Privacy-Preserving Federated Learning in Healthcare
Sunghwan Moon, Won Hee Lee
Abstract
Federated learning (FL) has received great attention in healthcare primarily due to its decentralized, collaborative nature of building a machine learning (ML) model. Over the years, the FL approach has been successfully applied for enhancing privacy preservation in medical ML applications. This study aims to review prevailing applications in healthcare for the future landing FL application. We identified the emerging applications of FL in key healthcare domains, including COVID-19, brain tumor segmentation, mammogram, sleep quality prediction, and smart healthcare system. Finally, we discuss privacy concerns in federated setting and provide current methods to increase the data privacy capabilities of FL.
Topics & Concepts
Health careComputer scienceKey (lock)Information privacyFederated learningCoronavirus disease 2019 (COVID-19)Healthcare systemQuality (philosophy)Data scienceArtificial intelligenceInternet privacyComputer securityMedicineEpistemologyPhilosophyEconomic growthDiseasePathologyInfectious disease (medical specialty)EconomicsPrivacy-Preserving Technologies in DataArtificial Intelligence in Healthcare and EducationRadiomics and Machine Learning in Medical Imaging