AI Insight
Researchers developed HealthFlux, an AI model that integrates 5,647 health features from eleven data types (clinical records, blood tests, genetics, imaging, and molecular profiles) in over 502,000 UK Biobank participants to create a continuously updated representation of overall health status. The model predicts 195 diseases and mortality risk over five years with significantly higher accuracy (mean AUROC 0.816) than previous state-of-the-art models (0.715), and maintains predictive power up to a decade after the last measurement. Notably, HealthFlux successfully predicts diseases it was never trained on (mean AUROC 0.769), suggesting it has learned fundamental patterns of health deterioration rather than disease-specific signatures.
Why it matters
This approach could enable earlier disease detection and intervention by identifying at-risk individuals years before clinical diagnosis, particularly those missed by single-modality assessments. The ability to predict diseases the model was never trained on suggests potential for anticipating emerging or rare conditions, fundamentally changing how preventive healthcare could be delivered.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Human health is a single underlying state that no measurement observes directly: diagnoses, blood tests, molecular profiles and images each capture one facet at separate times. Inferring health from such evidence requires a representation that integrates every modality and is carried forward and revised as observations arrive, which is the defining task of a world model. Here we introduce HealthFlux, a pan-modal world model that learns the latent dynamics of health from 5,647 features across eleven data domains, spanning clinical records, blood tests, genetics, proteomics, metabolomics and MRI, in 502,166 UK Biobank participants. Its hybrid state-space architecture combines ODE-based evolution between observations with continuous-time recurrent updates when new measurements arrive. In held-out participants, HealthFlux predicts 195 diseases and death over five years with a mean AUROC of 0.816, compared with 0.715 for the previous state-of-the-art model. These results remain true when validated in three independent cohorts, and HealthFlux also outperforms specialized clinical risk scores for disease and mortality. Simulated forward without further observations, the state continues to predict disease accurately up to a decade after the last measurement. HealthFlux predicts diseases excluded entirely from training, with a mean AUROC of 0.769, evidence that it has learned health itself rather than the diseases it was trained on. Each modality contributes information the others lack, and integrating them identifies individuals at risk whom single-modality models miss. HealthFlux thus makes health itself the object of prediction: one continuously updated state, informed by any measurement, from which the risk of any disease can be read years before diagnosis.
Source: A world model simulates the latent dynamics of human health