New AI tool detects increased risk of heart disease in women with ECG

New AI tool detects increased risk of heart disease in women with ECG

A new AI model can flag female patients who are at higher risk of heart disease based on an electrocardiogram (ECG).

The researchers say the algorithm, designed specifically for female patients, could allow doctors to identify high-risk women earlier and provide better treatment and care. Details will be published todayLancet Digital Health.

An EKG reports the heart's electrical activity and is one of the most common medical tests in the world. In their study, funded by the British Heart Foundation, researchers used artificial intelligence to analyze over a million ECGs from 180,000 patients, 98,000 of whom were female.

In the most recent study, researchers developed a score that measures how closely an individual's EKG matches the typical 'patterns of EKGs for men and women' and showed risk for each gender. Women whose ECGs more closely matched the typical “male” pattern – such as

Crucially, it was also found that these women have a significantly higher risk of cardiovascular disease, future heart failure and heart attacks than women with ECGs that more closely match the "typical female" ECG.

Previous evidence has shown that men tend to have a higher risk of heart disease - more specifically called cardiovascular disease - which may be due to differences in hormonal profiles and lifestyle factors. For this reason, medical professionals and the public believe that women's risk of cardiovascular disease is low. Although this the risk for women is also high, with women twice as likely to die from coronary heart disease, the leading cause of heart attacks, than from breast cancer in the UK. A recent consensus statement called cardiovascular disease the “number one killer” of women. The statement called for better diagnosis and treatment of women, as well as better female representation in clinical trials.

Dr. Arunashis Sau, academic clinical lecturer at the National Heart and Lung Institute, Imperial College London and cardiology registrar at Imperial College Healthcare NHS Trust, led the research. He said:

"Our work has highlighted that cardiovascular disease in women is far more complex than previously thought. In the clinic we use tests such as ECGs to provide a snapshot of this, but as a result this can involve grouping patients by sex in a way that does not take into account their individual physiology.

Dr. Fu Siong Ng, reader in cardiac electrophysiology at the National Heart & Lung Institute at Imperial College London and consultant cardiologist at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust, was the senior author of the study. He said: "Many of the women identified were actually at even higher risk than the 'average' man. If widely adopted, the AI ​​model may, over time, reduce gender disparities in cardiac care and improve outcomes for women with heart disease."

The research group recently published another paper on the associated AI-ECG risk estimation model, known as AIRE, which can predict patients' risk of developing and worsening disease from an ECG. The AIRE trials in the NHS are already planned for the end of 2025. These will evaluate the benefits of implementing the model with real patients from hospitals in the College Healthcare NHS Foundation Trust and Chelsea and Westminster Hospital in the Imperial College. This model is being tested in conjunction with AIRE.

Far too often, women are misdiagnosed or even dismissed by medical professionals, thanks to the myth that heart disease is “just a male” problem. Even when they receive the correct diagnosis, evidence shows that women are less likely than men to receive recommended treatments. “

Dr. Sonya Babu-Narayan, clinical director at the British Heart Foundation

"This study applied powerful AI technology to EKGs, a routine, cheap and widely used heart test. Harnessing the potential of this type of research could help better identify those patients at highest risk for future heart problems and narrow the gender gap in heart care. One test. One test alone will not level the playing field. Ensuring that every person needs the right heart care.

The research was funded by the British Heart Foundation, through a BHF Clinical Research Training Fellowship to Dr. Sau, a BHF program grant to Dr. Fu Siong NG and the BHF Center of Research Excellence at Imperial. Researchers also received funding from the NIHR Imperial Biomedical Research Centre, a translational research partnership between Imperial College Healthcare NHS Trust, and Imperial College London, which received £95m in 2022 to further develop new experimental treatments and diagnostics for patients.

Sources: