TADPOLE Challenge: Prediction of Longitudinal Evolution in Alzheimer’s Disease
Author: Razvan V. Marinescu, Neil P. Oxtoby, Alexandra L. Young, Esther E. Bron, Arthur W. Toga, Michael W. Weiner, Frederik Barkhof, Nick C. Fox, Stefan Klein, Daniel C. Alexander
The Alzheimer’s Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge compares the performance of algorithms atpredicting future evolution of individuals at risk of Alzheimer’s disease. TADPOLE Challenge participants train their models andalgorithms on historical data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study or any other datasets to whichthey have access. Participants are then required to make monthly forecasts over a period of 5 years from January 2018, of threekey outcomes for ADNI-3 rollover participants: clinical diagnosis, Alzheimer’s Disease Assessment Scale Cognitive Subdomain(ADAS-Cog13), and total volume of the ventricles. These individual forecasts are later compared with the corresponding futuremeasurements in ADNI-3 (obtained after the TADPOLE submission deadline). The ?rst submission phase of TADPOLE was openfor prize-eligible submissions between 15 June and 15 November 2017. The submission system remains open via the website:https://tadpole.grand-challenge.org, although since 15 November 2017 submissions are not eligible for the ?rst round ofprizes. This paper describes the design of the TADPOLE Challenge.