TADPOLE-SHARE

Dementia is a complex syndrome with Alzheimer’s disease as its most common form. Currently, no curative treatment for Alzheimer’s disease is available. Therefore, it is crucial to establish an accurate prediction of the disease progression in the early stage of the disease in individual patients. This would enable clinical trials to include the patients in which the treatment is expected to be most effective. In this project, we built a platform for sharing prediction algorithms for Alzheimer’s disease with the scientific community: the TADPOLE-SHARE platform (https://tadpole-share.github.io/). The platform enables further development and improvement of these prediction methods as well as their further validation on other datasets of patients with Alzheimer’s disease. To collaborate with international researchers, we organized a virtual hackathon on July 23-24. The goal of the hackathon, in which five teams participated, was to implement more algorithms in the prediction platform. Currently 5 algorithms are implemented in the platform. Collaborators are about to add three more algorithms in the next months. We are currently using the TADPOLE-SHARE platform in a validation study on the TAPDOLE challenge and on a dataset of patients visiting multiple memory clinics in the Netherlands.