Researchers from King's College London, Imperial College London and The Alan Turing Institute created over 3,800 anatomically accurate digital hearts to investigate how age, sex and lifestyle factors influence heart disease and electrical function. The large-scale cardiac digital twin study represents the first research of this magnitude, helping scientists discover that age and obesity cause changes in the heart's electrical properties, potentially explaining why these factors link to higher heart disease risk.
The results, published in Nature Cardiovascular Research, demonstrate opportunities that cardiac digital twins at scale offer to better understand lifestyle impact on heart health and function across different populations. Using cardiac digital twins, researchers found that differences in electrocardiogram readings between men and women are primarily due to heart size differences, not electrical signal conduction variations.
The insights could help clinicians refine treatments through tailored heart device settings for men and women or identifying new drug targets for specific groups. The deeper understanding of heart function across different groups could lead to more personalised care and treatment for heart condition patients.
Professor Steven Niederer, Mission Director for Cardiac Digital Twins at the Alan Turing Institute, stated: "Our research shows that the potential of cardiac digital twins goes beyond diagnostics. By replicating the hearts of people across the population, we have shown that digital twins can offer us deeper insights into the people at risk of heart disease. It also shows how lifestyle and gender can affect heart function."
The cardiac digital twins were created using real patient data and ECG readings from UK Biobank and a cohort of patients with heart disease, working as digital replicas of patients' hearts to explore functions difficult to measure directly. Recent advances in machine learning and AI helped researchers create this digital twin volume, reducing manual tasks and enabling quicker construction.
Professor Pablo Lamata, report author and professor of biomedical engineering at King's College London, stated: "These insights will help refine treatments and identify new drug targets. By developing this technology at scale, this research paves the way for their use in large population studies. This could lead to personalised treatments and better prevention strategies, ultimately transforming how we understand and treat heart diseases."
Digital twins are computer models simulating objects or processes in the physical world, potentially costly and time-intensive but offering new insights into physical system behaviour. In healthcare applications, digital twins could predict patient disease development and treatment response patterns.
Organisations can leverage digital twin technology for healthcare applications enabling predictive patient care and treatment optimisation through large-scale simulation capabilities. The research demonstrates scalable digital twin implementation supporting population health studies while advancing personalised medicine approaches across healthcare systems.
The 3,800-scale cardiac digital twin study validates healthcare digital twin deployment potential while demonstrating AI and machine learning's role in accelerating medical simulation development. Healthcare organisations can apply digital twin insights for personalised treatment protocols and drug target identification supporting improved patient outcomes. The research methodology supports healthcare enterprises implementing digital twin technologies for population health analysis and treatment optimisation. Organisations benefit from evidence-based digital twin applications enabling predictive healthcare delivery and personalised treatment strategies.