Research
Study suggests AI model can identify women at higher risk of heart disease from ECGs
Published:
25 February 2025
Published:
25 February 2025
An artificial intelligence (AI) model can identify women at higher risk of heart disease based on electrocardiogram (ECG) readings, according to new research we funded at Imperial College London.
The researchers say that the algorithm, designed specifically for female patients, could allow doctors to identify women at high-risk of heart disease at an earlier stage, allowing for better treatment and care.
Electrical activity of the heart
An ECG is one of the most common medical tests and records the electrical activity of the heart. In their study, the researchers used AI to analyse over one million ECGs from 180,000 patients, over half of whom were female.
In the study, published in the journal Lancet Digital Health, researchers developed a score that measured how closely an individual's ECG matches ‘typical’ patterns of ECGs for men and women. They found that women whose ECGs more closely matched the typical ‘male’ pattern – such as having an increased size of the electrical signal – tended to have larger heart chambers and more muscle mass.
These women were also found to have a significantly higher risk of cardiovascular disease, future heart failure, and heart attacks, compared to women with ECGs more closely matching the ‘typical female’ ECG.
'Reduce the gender gap'
Last year, the researchers published a study suggesting that an AI-ECG risk estimation model – known as AIRE – can predict patients’ risk of developing and worsening heart disease from an ECG. They’re currently planning trials of AIRE at two NHS Trusts in London, to begin later this year. This latest model, to identify women at higher risk of heart disease, will be trialed in conjunction with AIRE.
Dr Sonya Babu-Narayan, our Clinical Director, said: “Far too often, women are misdiagnosed or even dismissed by healthcare professionals, thanks to the myth that heart disease is 'only a male’ issue. Even if they do receive the right diagnosis, evidence shows that women are less likely than men to receive recommended treatments.”
“This study has applied powerful AI technology to ECGs, a routine, cheap and widely available heart test. Harnessing the potential of this type of research could help better identify those patients at highest risk of future heart problems and reduce the gender gap in heart care outcomes. However, one test alone will not level the playing field. Ensuring every person gets the right heart care they need when they need it will require change in every part of our healthcare system.”