Personalised normative cardiac phenotyping reveals clinically relevant heterogeneity in cardiac shape and outcome risk

Standard cardiac biomarkers such as ejection fraction, ventricular volumes, and strain compress complex three-dimensional heart dynamics into a small set of predefined measurements, leaving clinically important heterogeneity unrecognised. Here we propose a personalised normative cardiac frame-work in which each individual is compared to a digital twin representing expected healthy cardiac function given their age, sex, and body habitus. We show that structured patterns of deviation from these normative twins, discovered through systematic exploration of a generative cardiac dynamics space, constitute novel dynamic phenotypes that are not captured by conventional biomarkers. Applied independently to two UK Biobank cardiac cohorts with distinct shape representation, a 128-dimensional four-chamber statistical shape descriptor (HeartSSM, n = 52,365) and a 64-dimensional deep generative latent space from a conditional variational mesh autoencoder (MeshHeart cVAE, n = up to 39,376), we identify reproducible, continuous deviation-from-normative-twin scores (three discrete deviation phenotypes in the HeartSSM cohort) that improve cardiovascular risk stratification beyond ejection fraction, ventricular volumes, myocardial mass, and strain. The strongest effect was seen for incident atrial fibrillation among individuals with preserved ejection fraction (≥50%): incremental C-index Δ C = +0.068 (5-fold cross-validated Δ C = +0.063; likelihood-ratio P = 3.3 × 10 −8 ), with a separate, smaller effect for incident stroke in the same preserved-EF subgroup in the independent MeshHeart cVAE representation (which showed no signal for atrial fibrillation) (Δ C = +0.024, P = 2.6 × 10 −4 ). Both effects were checked against placebo controls in which the deviation scores were replaced by Gaussian noise. To test whether the normative twin generalises beyond UK Biobank’s specific scanning and processing pipeline, we applied the MeshHeart cVAE normative twin, unmodified, to an independent external cohort of healthy volunteers imaged at a different hospital (Gen-Scan/Hammersmith, n = 315): deviation scores in this cohort were of comparable magnitude to the UK Biobank healthy reference (ratio of means = 1.09; Mann–Whitney P = 1.4 × 10 −5 ), indicating that the normative twin captures cross-site-transferable structure rather than a scanner- or pipeline-specific artefact. Our findings suggest that cardiac phenotyping can move beyond predefined measurements toward data-driven dynamic phenotypes that better capture the heterogeneity underlying cardiovascular disease risk, even among individuals whose ejection fraction appears normal.