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

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 use a latent trajectory model on 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—constraining only demographic and cognitive variables—substantially improved graph accuracy and orientation. Our framework reveals dynamic interactions between emerging (NfL, GFAP) and established AD markers, enabling practical causal discovery despite violated model assumptions.