Federated learning: a novel approach for analyzing data that are spread across different parties. Its main idea is that parties run computations on their local data, yielding either aggregated parameters or encrypted values. These are then shared to generate a global (statistical) model. In other words, instead of bringing the data to the algorithms, federated learning brings the algorithms to the data. This way, patient-sensitive information is not disclosed. Federated learning is some times known as distributed learning. However, we try to avoid this term, since it can be confused with distributed computing, where different computers share their processing power to solve very complex calculations.