Navigating a new era in cardiovascular disease epidemiology: big data, artificial intelligence and the imperative of disability inclusion.

Cardiovascular disease (CVD) remains the leading cause of premature global mortality and one of the largest contributors to disability-adjusted life years lost. Over the past decade, the field has been transformed by the convergence of population biobanks, deep learning applied to imaging and electrocardiography, polygenic risk scores, wearable biosensors, and methodological advances in causal inference and target trial emulation. These innovations are reshaping precision public health for the general population. Yet the gains have not been equitably distributed. People with disability (PwD), comprising approximately 16 per cent of the global population and recognised by the United States National Institute on Minority Health and Health Disparities as a population experiencing health disparities are systematically under-represented in clinical trials, biobanks, electronic health records and the artificial-intelligence (AI) models trained upon them. Their cardiovascular health is therefore both worse and less precisely characterised than that of the general population. This article maps the key methodological vectors of change in CVD epidemiology, explains why each has so far failed to reach PwD, and presents a layered, defendable framework for disability-inclusive big-data and AI-enabled CVD research. It argues that disability inclusion is not a peripheral equity concern but a stress-test for the validity, generalisability and ethical legitimacy of the entire precision-cardiovascular enterprise.