A Bayesian framework for longitudinal EHR and genetic discovery

Electronic health records (EHRs) provide rich longitudinal disease histories, but existing methods for analysing these data typically treat diseases in isolation1 and rarely integrate germline genetics. Here we present ALADYNOULLI, a Bayesian generative framework that jointly models longitudinal EHR diagnoses, age and polygenic risk to recover latent time-varying disease signatures and patient-specific signature loadings; the model is formulated as a mixture of probabilities rather than a probability of a mixture2, correctly accommodating simultaneous and chronic conditions. Applied to three independent biobanks (UK Biobank3, Mass General Brigham4 and All of Us; total n > 683,000) spanning up to 52 years of follow-up and 348 diseases, the model recovers 21 replicable signatures with high cross-cohort composition preservation (median of 80%) and reveals biological subtypes within diagnostic categories (Cohen’s d up to 4.25; P ≤ 1 × 10−8 for 95% of comparisons). Signatures are concordant with established disease biology: carriers of familial hypercholesterolaemia5 enrich in the cardiovascular signature; carriers of clonal haematopoiesis of indeterminate potential6 in the inflammation signature; and a rare variant burden in LDLR, TTN and BRCA2 (refs. 7,8) aligns with disease specificities. A signature-based genome-wide association study identifies 151 genome-wide significant loci including cardiovascular associations missed by single-trait analyses. An explicit likelihood enables inverse probability weighting for selection bias9 while preserving biological signal. For disease prediction, ALADYNOULLI outperforms Pooled Cohort Equation (PCE), PREVENT and Gail at 1-year and 10-year horizons; disease-level (PheCode) predictions complement code-level foundation models such as Delphi-2M (ref. 10). A Bayesian generative framework that integrates longitudinal electronic health records with genetic data to identify latent disease signatures is presented.