作者: Nicola Rieke , Jonny Hancox , Wenqi Li , Fausto Milletarì , Holger R. Roth
DOI: 10.1038/S41746-020-00323-1
关键词: Clinical Practice 、 Data science 、 Healthcare system 、 Statistical model 、 Key factors 、 Federated learning 、 Digital health 、 Computer science
摘要: Data-driven Machine Learning has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems. Existing data not fully exploited ML primarily because it sits silos privacy concerns restrict access to this data. However, without sufficient will be prevented reaching its full potential and, ultimately, making the transition research clinical practice. This paper considers key factors contributing issue, explores how Federated (FL) may provide solution future of digital health highlights challenges considerations that need addressed.