Bayesian Event-Based Model for Disease Subtype and Stage Inference

TL;DR

This paper introduces a Bayesian variant of the Event-Based Model, BEBMS, which outperforms the existing SuStaIn model in synthetic and real Alzheimer's data, improving disease subtype and stage inference.

Contribution

The paper develops BEBMS, a Bayesian subtype model, and demonstrates its superior performance over SuStaIn in various experiments and real-world data analysis.

Findings

BEBMS significantly outperforms SuStaIn in synthetic data tasks.

BEBMS produces more scientifically consistent results in Alzheimer's disease progression.

BEBMS is more robust to model misspecification.

Abstract

Chronic diseases often progress differently across patients. Rather than randomly varying, there are typically a small number of subtypes for how a disease progresses across patients. To capture this structured heterogeneity, the Subtype and Stage Inference Event-Based Model (SuStaIn) estimates the number of subtypes, the order of disease progression for each subtype, and assigns each patient to a subtype from primarily cross-sectional data. It has been widely applied to uncover the subtypes of many diseases and inform our understanding of them. But how robust is its performance? In this paper, we develop a principled Bayesian subtype variant of the event-based model (BEBMS) and compare its performance to SuStaIn in a variety of synthetic data experiments with varied levels of model misspecification. BEBMS substantially outperforms SuStaIn across ordering, staging, and subtype assignment tasks. Further, we apply BEBMS and SuStaIn to a real-world Alzheimer's data set. We find BEBMS has results that are more consistent with the scientific consensus of Alzheimer's disease progression than SuStaIn.