The term Personal Health Train (PHT) is used for technologies and agreements that enable decentralised analysis of health-related data. Although originally invented and developed for scientific research purposes, the Personal Health Train concept (PHT) quickly spread outside the research domain. Various organizations have now joined the PHT network to learn from each other’s experiences and solutions.
People and organizations interested in applying the Personal Health Train concept or distributed learning techniques to health-related topics are invited to join the Personal Health Train network.
For more information about the Personal Health Train concept, please check out the website of the Personal Health Train network.
Realizing decentral data-analysis. It's a community effort!
Modern health care and research generates and requires vast amounts of data captured and stored at different locations. Managing these data in a centralized database is neither desirable nor feasible. Central data processing raises all kinds of issues, on agreements for data-accessibility, data standardization and privacy. The Personal Health Train can give controlled access to data, while ensuring privacy protection and optimal engagement of individual patients and citizens.
The PHT concept makes use of distributed learning. It is a technique for developing artificial intelligence (AI) algorithms in an automated way. It ‘trains’ AI algorithms on a vast range of data located at different sites. It eliminates the need to pool and store data into a single location. Instead, the model is trained in multiple iterations at different sites. To train models to meet the level of expertise of medical experts, the AI algorithms need to be fed a large number of cases. And these examples need to sufficiently represent the clinical environment in which they will be used.
Mode of operation
Within the Personal Health Train network, different working groups work on specific questions relevant to the PHT concept. These are: