Federated Learning in a Medical Context: A Systematic Literature Review

Data privacy is a very important issue. Especially in fields like medicine, it paramount to abide by the existing regulations preserve patients’ anonymity. However, data required for research and training machine learning models that could help gain insight into complex correlations or personalised treatments may otherwise stay undiscovered. Those generally scale with amount of available, but current situation often prohibits building large databases across sites. So would be beneficial able combine similar related from different sites all over world while still preserving privacy. Federated has been proposed as solution this, because relies on sharing models, instead raw itself. That means private never leaves site device was collected on. an emerging area, many domains have identified application those methods. This systematic literature review provides extensive look at concept federated its applicability confidential healthcare datasets.