• Jyoti Bangare
• Nilofer Kittad

Data-driven machine learning (ML) has become a potential strategy for generating accurate, robust statistics models from medical data, gathered in huge amounts by modern healthcare systems, with the rapid development of computer software and hardware technologies. A large amount of healthcare data from clinicians, patients, insurance companies, the pharmaceutical industry, and others are openly accessible. This abundance of data and sophisticated access to it offered data science technology an unparalleled chance to obtain data-driven insights and improve the quality of healthcare provision. Existing medical data are not properly used by ML models, mainly because it is contained in data silos. However, ML will not be able to achieve its full potential and ultimately migrate from research to medical care systems without access to complete data. This study reviews federated learning (FL), especially in the health care systems. We summarise in particular the broad solutions to federated learning's statistical challenges, system impediments, and privacy issues and identify the consequences and potentials for health care systems.

Machine Learning, Healthcare, Federated Learning, Privacy

"A REVIEW: FEDERATED LEARNING FOR HEALTH CARE APPLICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 8, page no.f295-f302, August-2021, Available :http://www.jetir.org/papers/JETIR2108637.pdf

"A REVIEW: FEDERATED LEARNING FOR HEALTH CARE APPLICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 8, page no. ppf295-f302, August-2021, Available at : http://www.jetir.org/papers/JETIR2108637.pdf