CoPoE: Multimodal Fusion via Decomposable Disease-Coordinate Product-of-Experts for Missing-Modality Alzheimer's Diagnosis

2026-10-08

AI Summary

This study addresses the artifacts and poor interpretability introduced by conventional fusion methods when handling missing data in multimodal Alzheimer’s disease diagnosis. To this end, we propose CoPoE, a framework that constructs a factorized disease-coordinate latent space by integrating diagonal Gaussian experts with a masked Product-of-Experts architecture. This design enables interpolation-free, robust fusion over arbitrary non-empty modality subsets without synthesizing missing inputs. Evaluated on the ADNI dataset, CoPoE achieves state-of-the-art full-modality performance and the highest average AUROC, while significantly improving calibration metrics including expected calibration error, Brier score, and negative log-likelihood. Furthermore, the framework demonstrates evidence enrichment along pathological axes, effectively enhancing both model interpretability and probabilistic calibration.

Abstract

Multimodal Alzheimer's disease (AD) diagnosis benefits from integrating heterogeneous clinical, imaging, genomic, and biomarker evidence, but clinical cohorts frequently suffer from irregular modality missingness. Existing fusion methods often synthesize absent inputs, risking the introduction of artificial surrogates, or pool available signals into uninterpretable latent spaces. We present CoPoE (Disease-Coordinate Product-of-Experts), a disease-coordinate framework that maps multimodal evidence into a structured latent space partitioned into four distinct biological and clinical axes: genetic Risk, molecular Pathology, Neurodegeneration, and clinical Stage (R/P/N/S). Each observed modality parameterizes a diagonal Gaussian expert over the full RPNS vector, and a masked Product-of-Experts architecture fuses only the available modalities. Consequently, absent modalities add no factor to the fusion path, allowing the network to preserve a robust, decomposable posterior for any non-empty modality subset without synthetic imputation in the RPNS path. Through extensive missing-modality experiments on the ADNI dataset, CoPoE achieves the best all-modality performance and the highest mean AUROC across all 15 observed-subset evaluations among standardized missing-modality fusion baselines under a shared non-PET ADNI embedding benchmark, while substantially improving raw-probability ECE, Brier score, and NLL. Furthermore, PET-supervised probing shows evidence enrichment within the pathology (P) block under full modalities, with tau-related signal retained even when direct fluid biospecimen inputs are withheld. Our code is available at https://github.com/labhai/CoPoE.

Problem

• Alzheimer's disease diagnosis
• multimodal fusion
• missing modality
• interpretability

Innovation

• Product-of-Experts
• Missing-Modality Fusion
• Multimodal Alzheimer's Diagnosis
• Decomposable Latent Space
• Uncertainty Calibration