English

Dynamic causal discovery in Alzheimer's disease through latent pseudotime modelling

Applications 2025-11-07 v1 Computational Engineering, Finance, and Science Machine Learning

Abstract

The application of causal discovery to diseases like Alzheimer's (AD) is limited by the static graph assumptions of most methods; such models cannot account for an evolving pathophysiology, modulated by a latent disease pseudotime. We propose to apply an existing latent variable model to real-world AD data, inferring a pseudotime that orders patients along a data-driven disease trajectory independent of chronological age, then learning how causal relationships evolve. Pseudotime outperformed age in predicting diagnosis (AUC 0.82 vs 0.59). Incorporating minimal, disease-agnostic background knowledge substantially improved graph accuracy and orientation. Our framework reveals dynamic interactions between novel (NfL, GFAP) and established AD markers, enabling practical causal discovery despite violated assumptions.

Keywords

Cite

@article{arxiv.2511.04619,
  title  = {Dynamic causal discovery in Alzheimer's disease through latent pseudotime modelling},
  author = {Natalia Glazman and Jyoti Mangal and Pedro Borges and Sebastien Ourselin and M. Jorge Cardoso},
  journal= {arXiv preprint arXiv:2511.04619},
  year   = {2025}
}

Comments

Accepted to the NeurIPS 2025 Workshop on CauScien: Uncovering Causality in Science