Unified Bayesian representation for high-dimensional multi-modal biomedical data for small-sample classification

TL;DR

BALDUR is a Bayesian method that effectively integrates multi-modal biomedical data in high-dimensional, small-sample scenarios, providing explainable classification and biomarker identification.

Contribution

It introduces a unified Bayesian framework combining multi-modal data views into a latent space with dual kernels, enhancing small-sample classification and interpretability.

Findings

Outperforms state-of-the-art models on neurodegeneration datasets

Identifies biomarkers consistent with existing scientific literature

Provides explainable results suitable for clinical biomarker discovery

Abstract

We present BALDUR, a novel Bayesian algorithm designed to deal with multi-modal datasets and small sample sizes in high-dimensional settings while providing explainable solutions. To do so, the proposed model combines within a common latent space the different data views to extract the relevant information to solve the classification task and prune out the irrelevant/redundant features/data views. Furthermore, to provide generalizable solutions in small sample size scenarios, BALDUR efficiently integrates dual kernels over the views with a small sample-to-feature ratio. Finally, its linear nature ensures the explainability of the model outcomes, allowing its use for biomarker identification. This model was tested over two different neurodegeneration datasets, outperforming the state-of-the-art models and detecting features aligned with markers already described in the scientific literature.