A Bayesian mixed-effects model to learn trajectories of changes from repeated manifold-valued observations

Abstract : We propose a generic Bayesian mixed-effects model to estimate the temporal progression of a biological phenomenon from observations obtained at multiple time points for a group of individuals. The progression is modeled by continuous trajectories in the space of measurements. Individual trajectories of progression result from spatiotemporal transformations of an average trajectory. These transformations allow to quantify the changes in direction and pace at which the trajectories are followed. The framework of Rieman-nian geometry allows the model to be used with any kind of measurements with smooth constraints. A stochastic version of the Expectation-Maximization algorithm is used to produce produce maximum a posteriori estimates of the parameters. We evaluate our method using series of neuropsychological test scores from patients with mild cognitive impairments later diagnosed with Alzheimer's disease, and simulated evolutions of symmetric positive definite matrices. The data-driven model of the impairment of cognitive functions shows the variability in the ordering and timing of the decline of these functions in the population. We show also that the estimated spatiotemporal transformations effectively put into correspondence significant events in the progression of individuals.
Type de document :
Article dans une revue
The Journal of Machine Learning Research, 2017, 18, pp.1-33
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01540367
Contributeur : Olivier Colliot <>
Soumis le : mercredi 31 octobre 2018 - 19:58:49
Dernière modification le : vendredi 16 novembre 2018 - 02:04:44

Fichier

schiratti17_JMLR_publishedOpen...
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01540367, version 3

Citation

Jean-Baptiste Schiratti, Stéphanie Allassonniere, Olivier Colliot, Stanley Durrleman. A Bayesian mixed-effects model to learn trajectories of changes from repeated manifold-valued observations. The Journal of Machine Learning Research, 2017, 18, pp.1-33. 〈hal-01540367v3〉

Partager