Discovering Subtypes of Neurodegenerative Progression with a Scalable Connectome-Constrained Dynamic Model
Abstract
Parkinson's disease is clinically and biologically heterogeneous, yet its spatiotemporal progression remains poorly characterized. We present a connectome-constrained disease progression model that jointly estimates subject-specific disease time and data-driven subtypes from longitudinal morphometry. Applied to 85 imaging and clinical biomarkers from the Parkinson's Progressive Markers Initiative (PPMI) cohort, the model recovers four morphologically distinct progression subtypes. We validate the model on a hold-out cross-sectional dataset and benchmark it against SuStaIn under a matched training and validation protocol. Only our method recovers subtypes that correspond significantly to clinical motor subtypes and genetic variants of Parkinson's Disease.
Related
- Identifying Neurophysiological Subtypes in Clinical High Risk for Psychosis Using Functional Connectome Profiling
- Discovering Prognostic Risk Strata and Heterogeneous Progression Routes from Cross-Sectional Survival Data
- ApproxBrain: Certified Sufficiency Frontiers in Connectome-Constrained Neural Systems
- FlyHack: Stress-Testing Mechanistic Claims in a Connectome-Constrained Visual Model
- The (Butter)fly Dream: Linear Separability of World-Model Rollouts in a Connectome-Constrained Visual Model
BibTeX
@misc{semchin2026discovering,
title = {{Discovering Subtypes of Neurodegenerative Progression with a Scalable Connectome-Constrained Dynamic Model}},
author = {Daniel Semchin and Emile d'Angremont and Hao Ding and Alan Antar and Marco Lorenzi and Konstantinos Arfanakis and Ysbrand van der Werf and Paul Thompson and Boris Gutman},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.10890},
eprint = {2609.10890},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.10890},
}
RIS
TY - UNPB
TI - Discovering Subtypes of Neurodegenerative Progression with a Scalable Connectome-Constrained Dynamic Model
AU - Daniel Semchin
AU - Emile d'Angremont
AU - Hao Ding
AU - Alan Antar
AU - Marco Lorenzi
AU - Konstantinos Arfanakis
AU - Ysbrand van der Werf
AU - Paul Thompson
AU - Boris Gutman
PY - 2026
DA - 2026/09/09
PB - arXiv
DO - 10.48550/arxiv.2609.10890
UR - https://arxiv.org/abs/2609.10890
AB - Parkinson's disease is clinically and biologically heterogeneous, yet its spatiotemporal progression remains poorly characterized. We present a connectome-constrained disease progression model that jointly estimates subject-specific disease time and data-driven subtypes from longitudinal morphometry. Applied to 85 imaging and clinical biomarkers from the Parkinson's Progressive Markers Initiative (PPMI) cohort, the model recovers four morphologically distinct progression subtypes. We validate the model on a hold-out cross-sectional dataset and benchmark it against SuStaIn under a matched training and validation protocol. Only our method recovers subtypes that correspond significantly to clinical motor subtypes and genetic variants of Parkinson's Disease.
ER -