Joint Progression Modeling (JPM): A Probabilistic Framework for Mixed-Pathology Progression

TL;DR

This paper introduces the Joint Progression Model (JPM), a probabilistic framework for modeling disease progression with mixed pathologies, demonstrating improved accuracy over existing models and consistency with known disease progression patterns.

Contribution

The paper proposes JPM, a novel probabilistic framework that models joint disease progression as partial rankings, extending event-based models to handle mixed pathologies.

Findings

JPM improves ordering accuracy by approximately 21% over baseline models.

All JPM variants are well-calibrated and achieve near-perfect separation.

The Mallows variant aligns well with prior literature on mixed neurodegenerative pathologies.

Abstract

Event-based models (EBMs) infer disease progression from cross-sectional data, and standard EBMs assume a single underlying disease per individual. In contrast, mixed pathologies are common in neurodegeneration. We introduce the Joint Progression Model (JPM), a probabilistic framework that treats single-disease trajectories as partial rankings and builds a prior over joint progressions. We study several JPM variants (Pairwise, Bradley-Terry, Plackett-Luce, and Mallows) and analyze three properties: (i) calibration -- whether lower model energy predicts smaller distance to the ground truth ordering; (ii) separation -- the degree to which sampled rankings are distinguishable from random permutations; and (iii) sharpness -- the stability of sampled aggregate rankings. All variants are calibrated, and all achieve near-perfect separation; sharpness varies by variant and is well-predicted by simple features of the input partial rankings (number and length of rankings, conflict, and overlap). In synthetic experiments, JPM improves ordering accuracy by roughly 21 percent over a strong EBM baseline (SA-EBM) that treats the joint disease as a single condition. Finally, using NACC, we find that the Mallows variant of JPM and the baseline model (SA-EBM) have results that are more consistent with prior literature on the possible disease progression of the mixed pathology of AD and VaD.