Multi-channel causal variational autoencoder for multimodal biomedical causal disentanglement

The multimodal nature of clinical assessment and decision-making, and the high rate of healthcare data generation, motivate the need to develop approaches specifically tailored to the analysis of these complex and potentially high-dimensional multimodal datasets. In this work, we propose Multi-Channel Causal VAE (MC2VAE), a novel causal disentanglement approach for multi-channel data, whose objective is to jointly learn modality-specific latent representations from a multi-channel dataset, and identify a causal structure between the latent channels. Each channel is projected into its own latent space, where a causal discovery step is integrated to learn the hidden causal graph. Finally, the decoder takes into account the discovered graph to predict the data. Covariate of interest can be integrated as well when available, and accounted in the causal graph structure. Extensive experiments on synthetically generated multi-channel datasets demonstrate the ability of MC2VAE in effectively uncovering the underlying latent causal structures across multiple channels, hence making it a strong candidate for real-world multi-channel causal disentanglement. Application to multi-channel data on neurodegeneration extracted from the Alzheimer’s Disease Neuroimaging Initiative highlights the existence of a biologically meaningful latent causal structure, whose pertinence is supported by multiple previous experimental and modeling work, and provides actionable insight for disease progression.

Download paper here

Recommended citation: Al-Ali S., Balelli I. (2026). “Multi-channel causal variational autoencoder for multimodal biomedical causal disentanglement.” Journal of Biomedical Informatics. 104995.