Researchers at Imperial College London have developed an algorithm specifically for female patients. The study, published in Lancet Digital Health, aims to help physicians identify high-risk women earlier for improved care and treatment.
Image Credit: Imperial College London/Thomas Angus
One of the most widely used medical tests worldwide is an electrocardiogram (ECG), which records the heart's electrical activity. In their British Heart Foundation-funded study, the researchers used artificial intelligence to analyze more than one million ECGs from 180,000 patients, 98% of whom were female.
In the most recent study, the researchers created a score that indicates the degree to which a person's ECG resembles “typical” patterns for both men and women, indicating a range of risk for each sex. Women with larger heart chambers and more muscle mass tended to have ECGs resembling the typical “male” pattern, such as having a larger electrical signal.
Importantly, compared to women whose ECGs more closely resembled the “typical female” ECG, these women were also found to have a significantly higher risk of cardiovascular disease, future heart failure, and heart attacks.
According to earlier research, men are more likely than women to develop heart disease, or more precisely, cardiovascular disease. This could be because of variations in hormone profiles and lifestyle choices.
As a result, the public and medical professionals think that women have a low risk of cardiovascular disease. This is even though women are also at high risk; in the UK, they are twice as likely to die from coronary heart disease, which is the primary cause of heart attacks, as from breast cancer.
Cardiovascular disease is the “number one killer” of women, according to a recent consensus statement. Better female representation in clinical trials and improved diagnosis and treatment for women were demanded in the statement.
The study was directed by Dr. Arunashis Sau, a Cardiology Registrar at Imperial College Healthcare NHS Trust and an Academic Clinical Lecturer at Imperial College London's National Heart and Lung Institute.
Our work has underlined that cardiovascular disease in females is far more complex than previously thought. In the clinic, we use tests like ECGs to provide a snapshot of what is going on but as a result, this may involve grouping patients by sex in a way that does not take into account their individual physiology. The AI-enhanced ECGs give us a more nuanced understanding of female heart health and we believe this could be used to improve outcomes for women at risk of heart disease.
Dr. Arunashis Sau, Cardiology Registrar, Imperial College
The Study's Senior Author was Dr. Fu Siong Ng, a Consultant Cardiologist at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust, as well as a Reader in Cardiac Electrophysiology at the National Heart & Lung Institute at Imperial College London.
Many of the women identified were in fact at even higher risk than the ‘average’ man. If it becomes used widely, over time the AI model may reduce gender differences in cardiac care, and improve outcomes for women at risk of heart disease.
Dr. Fu Siong Ng, Consultant Cardiologist, Imperial College
AIRE, a related AI-ECG risk estimation model that can forecast a patient's risk of developing and exacerbating disease based on an ECG, was the subject of a recent study by the research team. AIRE trials in the NHS are already scheduled for the end of 2025.
These will assess the model's effectiveness using actual patients from hospitals in the Chelsea and Westminster Hospital NHS Foundation Trust and Imperial College Healthcare NHS Trust. Together with AIRE, this model will be tested.
Dr. Sonya Babu-Narayan, Clinical Director at the British Heart Foundation, 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 the 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.
Dr. Sonya Babu-Narayan, Clinical Director, British Heart Foundation
The British Heart Foundation provided funding for the study through the BHF Clinical Research Training Fellowship to Dr. Sau, the BHF Program Grant to Dr. Fu Siong Ng, and the BHF Centre of Research Excellence at Imperial.
The NIHR Imperial Biomedical Research Centre, a translational research collaboration between Imperial College Healthcare NHS Trust and Imperial College London, also provided support to the researchers. In 2022, the center was granted £95 million to continue creating novel experimental patient treatments and diagnostics.
Journal Reference:
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. doi.org/10.1016/j.landig.2024.12.003.