The Personal Health Train (PHT) is a platform that utilises distributed analytics (DA) methods to enable analyses of sensitive patient data while also complying with data protection regulations. The main principle of the PHT is that the analysis tasks are brought to the data provider while the data instances remain in their original location. Training of the data models is based on distributed data and for their training we use Federated Learning (FL) protocols.

The PHT originates from an analogy from the real world: the infrastructure reminds of a railway system including trains, stations, and train depots. The train uses the network to visit different stations to transport, e.g., several goods. Adapting this concept to the PHT ecosystem, we draw similarities such as: the Train encapsulates an analytical task, which is represented by the good in the analogy. The data provider takes over the role of a reachable Station that can be accessed by the Train. Further, the Station executes the task, which processes the available data, etc.

Here you can find some links to research publications on our work regarding the Personal Health Train.