Such technology promises to enable doctors to identify high-risk women earlier, thus leading to potentially better treatment and care for those patients.

To develop the model, the team used AI to analyze more than one million ECGs from 180,000 patients — 98,000 of whom were female.

Based on this data, the team created a score that measures how closely an individual's ECG matches standard patterns of ECGs for men and women. This score showed a typical range of risk for each sex. For instance, the team noted that women with ECGs that more closely matched the standard ‘male’ pattern — demonstrating an increased size of the electrical signal — typically had larger heart chambers as well as more muscle mass.

Further, these female patients also tended to have significantly higher risk of cardiovascular disease, future heart failure and heart attacks, when compared to women with ECG results that more closely matched the standard female ECG.

The researchers explained: "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’s going on, but as a result this may involve grouping patients by sex in a way that doesn’t 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.”

The study, “Artificial intelligence-enhanced electrocardiography for the identification of a sex-related cardiovascular risk continuum: a retrospective cohort study," appears in the journal The Lancet Digital Health.