Multi-Parametric Subtype and Stage Inference improves spatiotemporal subtyping of Alzheimer's Disease

Motivation: Subtype and Stage Inference (SuStaIn) model is widely used to reveal spatiotemporal heterogeneity in cross-sectional datasets. But SuStaIn does not account for correlations between biomarkers. Goal(s): We attempt to modify SuStaIn model to utilize highly correlated biomarkers in the analysis of neurodegenerative diseases' heterogeneity. Approach: We propose Multi-Parametric SuStaIn (MP-SuStaIn), an alternative SuStaIn model that incorporates biomarker correlations into spatiotemporal analysis. We apply MP-SuStaIn to analyze Alzheimer's disease (AD) based on multiple morphological features using the ADNI dataset. Results: MP-SuStaIn identified three subtypes of AD, each with distinct progression patterns, morphological characteristics, clinical symptoms, and prognostic results. Impact: We identified three subtypes of Alzheimer's disease with distinct progression patterns and morphological characteristics by using multiple brain morphologic biomarkers and a modified Subtype and Stage Inference model, which can analyze the spatiotemporal heterogeneity of neurodegenerative diseases.