Conditional Evidence Reconstruction and Decomposition for Interpretable Multimodal Diagnosis

TL;DR

This paper introduces CERD, a novel framework for interpretable multimodal diagnosis that reconstructs missing data and decomposes evidence, improving robustness and interpretability in incomplete modality scenarios.

Contribution

CERD is the first method to reconstruct missing modalities conditioned on observed data and decompose evidence into shared and modality-specific cues for better interpretability.

Findings

CERD outperforms baselines in incomplete-modality settings on ADNI data.

CERD provides structured, clinically aligned evidence attributions.

CERD enhances trustworthiness of multimodal diagnosis models.

Abstract

Neurobiological and neurodegenerative diseases are inherently multifactorial, arising from coupled influences spanning genetic susceptibility, brain alterations, and environmental and behavioral factors. Multimodal modeling has therefore been increasingly adopted for disease diagnosis by integrating complementary evidence across data sources. However, in both large-scale cohorts and real-world clinical workflows, modality coverage is often incomplete, making many multimodal models brittle when one or more modalities are unavailable. Existing approaches to incomplete multimodal diagnosis typically rely on group-wise or static priors, which may fail to capture subject-specific cross-modal dependencies; moreover, many models provide limited interpretability into which evidence sources drive the final decision. To address these limitations, we propose Conditional Evidence Reconstruction and Decomposition (CERD), a framework for interpretable multimodal diagnosis with incomplete modalities. CERD first reconstructs missing modality representations conditioned on each subject's observed inputs, then decomposes diagnostic evidence into shared cross-modal corroboration and modality-specific cues via logit-level attribution. Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) demonstrate that CERD outperforms competitive baselines under incomplete-modality settings while producing structured and clinically aligned evidence attributions for trustworthy decision support.