A new AI model has been developed to identify female patients at higher risk of heart disease based on their electrocardiogram (ECG).
The researchers believe that this algorithm, designed specifically for women, could help doctors detect high-risk individuals earlier, leading to better treatment and care. The details of the study are published in Lancet Digital Health.
The study, funded by the British Heart Foundation, analysed over one million ECGs from 180,000 patients, including 98,000 women.
The researchers created a scoring system that compares an individual’s ECG with typical patterns for both men and women, identifying a range of risks for each sex. Women whose ECGs resembled the typical “male” pattern—characterised by an increased size of the electrical signal—were found to have larger heart chambers and more muscle mass. These women also had a significantly higher risk of cardiovascular disease, future heart failure, and heart attacks compared to those whose ECGs more closely resembled the “typical female” pattern.
Previous research has shown that men are generally considered to be at higher risk for cardiovascular disease, possibly due to hormonal and lifestyle differences. As a result, both healthcare professionals and the public have historically believed that women are at lower risk. This assumption persists despite the fact that women are twice as likely to die from coronary heart disease—the leading cause of heart attacks—than from breast cancer. A recent consensus statement labelled cardiovascular disease as the “number one killer” of women, calling for better diagnosis, treatment, and more female representation in clinical trials.
Cardiovascular disease in women is far more complex than previously understood. While tests like ECGs give a snapshot of the heart’s condition, they often group patients by sex without accounting for individual physiology. AI-enhanced ECGs provide a more nuanced understanding of female heart health, and this could help improve outcomes for women at risk of heart disease.
Many of the women identified by this model were at an even higher risk than the ‘average’ man. If used widely, this AI model could reduce gender disparities in cardiac care and improve outcomes for women at risk of heart disease.
The research group recently published another paper on a related AI-ECG risk estimation model, called AIRE, which can predict the risk of disease development and progression based on an ECG. Trials of AIRE within the NHS are planned for late 2025 and will assess its effectiveness with real patients from hospitals across Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust.
Too often, women are misdiagnosed or dismissed by healthcare professionals due to the misconception that heart disease is ‘only a male’ issue. Even when women receive the correct diagnosis, evidence shows they are less likely than men to receive the recommended treatments. This study applies powerful AI technology to ECGs. Harnessing this type of research could help identify those at the highest risk of future heart problems, reducing the gender gap in heart care outcomes. However, a single test will not solve the problem. Achieving equitable heart care for everyone requires systemic change in every part of the healthcare system.
Source: Imperial College London
Image Credit: iStock
References:
Sau A et al. (2025) Artificial intelligence-enhanced electrocardiography for the identification of a sex-related cardiovascular risk continuum: a retrospective cohort study. The Lancet Digital Health. 7(3):E184-E194.
