Multi-Channel Stochastic Variational Inference for the Joint Analysis of Heterogeneous Biomedical Data in Alzheimer's Disease

TL;DR

This paper introduces a multi-channel stochastic generative model for joint analysis of heterogeneous biomedical data in Alzheimer's Disease, enabling better data reconstruction, patient stratification, and interpretability.

Contribution

It proposes a novel multi-channel stochastic variational inference method that effectively models heterogeneous data sources in AD research, improving data fusion and interpretability.

Findings

Superior data reconstruction compared to single-channel models

Effective unsupervised patient stratification

Potential for general application in data fusion

Abstract

The joint analysis of biomedical data in Alzheimer's Disease (AD) is important for better clinical diagnosis and to understand the relationship between biomarkers. However, jointly accounting for heterogeneous measures poses important challenges related to the modeling of the variability and the interpretability of the results. These issues are here addressed by proposing a novel multi-channel stochastic generative model. We assume that a latent variable generates the data observed through different channels (e.g., clinical scores, imaging, ...) and describe an efficient way to estimate jointly the distribution of both latent variable and data generative process. Experiments on synthetic data show that the multi-channel formulation allows superior data reconstruction as opposed to the single channel one. Moreover, the derived lower bound of the model evidence represents a promising model selection criterion. Experiments on AD data show that the model parameters can be used for unsupervised patient stratification and for the joint interpretation of the heterogeneous observations. Because of its general and flexible formulation, we believe that the proposed method can find important applications as a general data fusion technique.