The Alzheimer's Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge: Results after 1 Year Follow-up

Catégorie

Journal Article

Auteurs

Marinescu, R. V., Oxtoby, N. P., Young, A. L., Bron, E. E., Toga, A. W., Weiner, M. W., Barkhof, F., Fox, N. C., Eshaghi, A., Toni, T., Salaterski, M., Lunina, V., Ansart, M., Durrleman, S., Lu, P., Iddi, S., Li, D., Thompson, W. K., Donohue, M. C., Nahon, A., Levy, Y., Halbersberg, D., Cohen, M., Liao, H., Li, T., Yu, K., Zhu, H., Tamez-Pena, J. G., Ismail, A., Wood, T., Bravo, H. C., Nguyen, M., Sun, N., Feng, J., Yeo, B. T. T., Chen, G., Qi, K., Chen, S., Qiu, D., Buciuman, I., Kelner, A., Pop, R., Rimocea, D., Ghazi, M. M., Nielsen, M., Ourselin, S., Sorensen, L., Venkatraghavan, V., Liu, K., Rabe, C., Manser, P., Hill, S. M., Howlett, J., Huang, Z., Kiddle, S., Mukherjee, S., Rouanet, A., Taschler, B., Tom, B. D. M., White, S. R., Faux, N., Sedai, S., Oriol, J. de V., Clemente, E. E. V., Estrada, K., Aksman, L., Altmann, A., Stonnington, C. M., Wang, Y., Wu, J., Devadas, V., Fourrier, C., Raket, L. L., Sotiras, A., Erus, G., Doshi, J., Davatzikos, C., Vogel, J., Doyle, A., Tam, A., Diaz-Papkovich, A., Jammeh, E., Koval, I., Moore, P., Lyons, T. J., Gallacher, J., Tohka, J., Ciszek, R., Jedynak, B., Pandya, K., Bilgel, M., Engels, W., Cole, J., Golland, P., Klein, S., Alexander, D. C.

Année

2020

Titre

The Alzheimer's Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge: Results after 1 Year Follow-up

Journal / Livre / Conférence

arXiv:2002.03419 [q-bio, stat]

Résumé

We present the findings of "The Alzheimer's Disease Prediction Of Longitudinal Evolution" (TADPOLE) Challenge, which compared the performance of 92 algorithms from 33 international teams at predicting the future trajectory of 219 individuals at risk of Alzheimer's disease. Challenge participants were required to make a prediction, for each month of a 5-year future time period, of three key outcomes: clinical diagnosis, Alzheimer's Disease Assessment Scale Cognitive Subdomain (ADAS-Cog13), and total volume of the ventricles. No single submission was best at predicting all three outcomes. For clinical diagnosis and ventricle volume prediction, the best algorithms strongly outperform simple baselines in predictive ability. However, for ADAS-Cog13 no single submitted prediction method was significantly better than random guessing. Two ensemble methods based on taking the mean and median over all predictions, obtained top scores on almost all tasks. Better than average performance at diagnosis prediction was generally associated with the additional inclusion of features from cerebrospinal fluid (CSF) samples and diffusion tensor imaging (DTI). On the other hand, better performance at ventricle volume prediction was associated with inclusion of summary statistics, such as patient-specific biomarker trends. The submission system remains open via the website https://tadpole.grand-challenge.org, while code for submissions is being collated by TADPOLE SHARE: https://tadpole-share.github.io/. Our work suggests that current prediction algorithms are accurate for biomarkers related to clinical diagnosis and ventricle volume, opening up the possibility of cohort refinement in clinical trials for Alzheimer's disease.

Mots-clés

Quantitative Biology - Populations and Evolution, Statistics - Applications

‹ Retour à la page précédente