Learning disease progression models with longitudinal data and missing values

Raphäel Couronné (1, 2) , Marie Vidailhet (2) , Jean-Christophe Corvol (2) , Stéphane Lehéricy (2, 3) , Stanley Durrleman (1, 2)

1 ARAMIS - Algorithms, models and methods for images and signals of the human brain = Algorithmes, modèles et méthodes pour les images et les signaux du cerveau humain [ICM Paris]
2 ICM - Institut du Cerveau = Paris Brain Institute
3 CENIR - Plateforme de neuroimagerie CENIR = Center for NeuroImaging Research-Human MRI Neuroimaging core facility for clinical research [ICM Paris]

Statistical methods have been developed for the analysis of longitudinal data in neurodegenerative diseases. To cope with the lack of temporal markers-i.e. to account for subject-specific disease progression in regard to age-a common strategy consists in realigning the individual sequence data in time. Patient's specific trajectories can indeed be seen as spatiotemporal perturbations of the same normative disease trajectory. However, these models do not easily allow one to account for multimodal data, which more than often include missing values. Indeed, it is rare that imaging and clinical examinations for instance are performed at the same frequency in clinical protocols. Multimodal models also need to allow a different profile of progression for data with different structure and representation. We propose to use a generative mixed effect model that considers the progression trajectories as curves on a Rieman-nian Manifold. We use the concept of product manifold to handle multimodal data, and leverage the generative aspect of our model to handle missing values. We assess the robuste-ness of our methods toward missing values frequency on both synthetic and real data. Finally we apply our model on a real-world dataset to model Parkinson's disease progression from data derived from clinical examination and imaging.

Mots clés: Non- Linear Mixed Effect Model; Multimodal; Disease modeling; Longitudinal; Riemmanian Geometry; Missing values; Mixed Effect Model

Domaines: Machine Learning [stat.ML]; Bio-informatique [q-bio.QM]; Statistiques [math.ST]

Raphäel Couronné, Marie Vidailhet, Jean-Christophe Corvol, Stéphane Lehéricy, Stanley Durrleman. Learning disease progression models with longitudinal data and missing values. ISBI 2019 - International Symposium on Biomedical Imaging, Apr 2019, Venice, Italy. ⟨hal-02091571v2⟩