Aim:

Today, data banks contain unpredictable data. Together with the advances in data science, large data offer the potential to better understand the causes of diseases. This potential results from the processing, analysis or modeling of machine learning algorithms. Various data sets stored in different institutions are not always shared directly due to privacy and legal concerns. This problem limits the full use of large data in health research. Federated learning is aimed at developing artificial intelligence systems based on both high accuracy and data privacy.

Materials and Methods:

In this study, a federated learning approach was proposed in order to access any data and develop machine learning applications without sharing personal information within the scope of data privacy. Firstly, the structure of the Federated learner has been studied. It was then determined how federated learning should be used in machine learning models in different health applications.

Results:

In federated learning, the model is trained on local computers and its updates are transferred to a central server. The updated model is then transferred to local models. In this way, the central model is trained without seeing the data.

Conclusion:

It is necessary to make machine learning models in which confidentiality is applied with data obtained from health. For this, federated learning must be integrated into traditional machine learning applications. Thus, high performance is envisaged to be achieved with big data where data confidentiality is adopted.

Keywords: Privacy, federated learning, personal data, machine learning, healthcare