Journal Article

Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference

Young, Alexandra L, Masellis, Mario, Graff, Caroline, Warren, Jason D, Fox, Nick C, Bocchetta, Martina, Schott, Jonathan M, Tartaglia, Maria Carmela, Ourselin, Sebastien, Thomas, David L, Cardoso, Jorge, Yong, Keir, Laforce, Robert, Galimberti, Daniela, Sorbi, Sandro, de Mendonça, Alexandre, Crutch, Sebastian, Marinescu, Razvan V, Finger, Elizabeth, Firth, Nicholas C, Tagliavini, Fabrizio, Oxtoby, Neil P, Cash, David M, Dick, Katrina M, Rohrer, Jonathan D, Borroni, Barbara, Rowe, James B, van Swieten, John, Alexander, Daniel C, Frisoni, Giovanni B

2018

Overview

The heterogeneity of neurodegenerative diseases is a key confound to disease understanding and treatment development, as study cohorts typically include multiple phenotypes on distinct disease trajectories. Here we introduce a machine-learning technique—Subtype and Stage Inference (SuStaIn)—able to uncover data-driven disease phenotypes with distinct temporal progression patterns, from widely available cross-sectional patient studies. Results from imaging studies in two neurodegenerative diseases reveal subgroups and their distinct trajectories of regional neurodegeneration. In genetic frontotemporal dementia, SuStaIn identifies genotypes from imaging alone, validating its ability to identify subtypes; further the technique reveals within-genotype heterogeneity. In Alzheimer’s disease, SuStaIn uncovers three subtypes, uniquely characterising their temporal complexity. SuStaIn provides fine-grained patient stratification, which substantially enhances the ability to predict conversion between diagnostic categories over standard models that ignore subtype ( p  = 7.18 × 10 −4 ) or temporal stage ( p  = 3.96 × 10 −5 ). SuStaIn offers new promise for enabling disease subtype discovery and precision medicine. Progressive diseases tend to be heterogeneous in their underlying aetiology mechanism, disease manifestation, and disease time course. Here, Young and colleagues devise a computational method to account for both phenotypic heterogeneity and temporal heterogeneity, and demonstrate it using two neurodegenerative disease cohorts.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 59/57 / 639/705/117 / 692/699/375/365 / Alzheimer Disease - genetics / Alzheimer Disease - pathology / Complexity / Dementia disorders / Diagnostic systems / Disease / Frontotemporal dementia / Frontotemporal Dementia - genetics / Frontotemporal Dementia - pathology / Genotype / Genotypes / Heterogeneity / Humanities and Social Sciences / Humans / Inference / Learning algorithms / Machine learning / Medical imaging / Models, Neurological / multidisciplinary / Neurodegeneration / Neurodegenerative diseases / Neurodegenerative Diseases - classification / Neurodegenerative Diseases - pathology / Neurological diseases / Patients / Phenotype / Phenotypes / Precision medicine / Reproducibility of Results / Science / Science (multidisciplinary) / Subgroups / Time Factors / Trajectories