A Novel Multi-view Mixture Model Framework for Longitudinal Clustering with Application to ANCA-Associated Vasculitis

TL;DR

This paper introduces a two-view mixture model using Neural ODEs for longitudinal data clustering, applied to vasculitis patient data to identify subgroups with different disease progression patterns.

Contribution

It presents a novel probabilistic framework combining static and dynamic data with Neural ODEs and an EM algorithm for interpretable disease subgroup discovery.

Findings

Identified subgroups with distinct serum creatinine trajectories.

Revealed heterogeneity in end-stage kidney disease outcomes.

Demonstrated effective modeling of irregular longitudinal data.

Abstract

Effectively modeling irregularly sampled longitudinal data is essential for understanding disease progression and improving risk prediction. We propose a two-view mixture model that integrates static baseline covariates and longitudinal biomarker trajectories within a unified probabilistic clustering framework. Temporal patterns are modeled using Neural Ordinary Differential Equations. Model training uses an EM algorithm with a sparsity-inducing log-penalty for interpretable subgroup discovery. Application of the model to an Irish cohort of ANCA-associated vasculitis patients reveals subgroups with heterogeneous serum creatinine trajectories and variation in end-stage kidney disease outcomes.