Federated Learning in Healthcare:A Benchmark Comparison of Engineering and Statistical Approaches for Structured Data Analysis  

作　　者：Siqi Li Di Miao Qiming Wu Chuan Hong Danny D’Agostino Xin Li Yilin Ning Yuqing Shang Ziwen Wang Molei Liu Huazhu Fu Marcus Eng Hock Ong Hamed Haddadi Nan Liu 

机构地区：[1]Centre for Quantitative Medicine,Duke-NUS Medical School,Singapore,Singapore [2]Department of Biostatistics and Bioinformatics,Duke University,Durham,NC,USA [3]Department of Biostatistics,Columbia University Mailman School of Public Health,New York,NY,USA [4]Institute of High Performance Computing,Agency for Science,Technology and Research,Singapore,Singapore [5]Programme in Health Services and Systems Research,Duke-NUS Medical School,Singapore,Singapore [6]Health Services Research Centre,Singapore Health Services,Singapore,Singapore [7]Department of Emergency Medicine,Singapore General Hospital,Singapore,Singapore [8]Department of Computing,Imperial College London,London,England,UK [9]Institute of Data Science,National University of Singapore,Singapore,Singapore

出　　处：《Health Data Science》2024年第1期45-57,共13页健康数据科学(英文)

基　　金：supported by the Duke/Duke-NUS Collaboration grant.

摘　　要：Background:Federated learning(FL)holds promise for safeguarding data privacy in healthcare collaborations.While the term“FL”was originally coined by the engineering community,the statistical field has also developed privacy-preserving algorithms,though these are less recognized.Our goal was to bridge this gap with the ffrst comprehensive comparison of FL frameworks from both domains.Methods:We assessed 7 FL frameworks,encompassing both engineering-based and statistical FL algorithms,and compared them against local and centralized modeling of logistic regression and least absolute shrinkage and selection operator(Lasso).Our evaluation utilized both simulated data and real-world emergency department data,focusing on comparing both estimated model coefffcients and the performance of model predictions.Results:The ffndings reveal that statistical FL algorithms produce much less biased estimates of model coefffcients.Conversely,engineering-based methods can yield models with slightly better prediction performance,occasionally outperforming both centralized and statistical FL models.Conclusion:This study underscores the relative strengths and weaknesses of both types of methods,providing recommendations for their selection based on distinct study characteristics.Furthermore,we emphasize the critical need to raise awareness of and integrate these methods into future applications of FL within the healthcare domain.

关 键 词：holds utilized slightly 

分 类 号：P20[天文地球—测绘科学与技术]