AI model could detect hidden heart disease from routine ECGs

Artificial intelligence (AI) could identify signs of heart failure and heart valve disease in a routine electrocardiogram (ECG), according to research led by a team at Imperial’s National Heart and Lung Institute (NHLI) recently presented at the European Society of Cardiology Congress in Munich.

Around a billion ECGs are performed worldwide each year. The test measures the electrical activity of the heart and is routinely used to diagnose a range of cardiac conditions.

Researchers from NHLI, led by NHLI Clinical Research Fellow Dr Ahmed El-Medany, trained an AI model on ECGs from millions of patients to learn the connection between the patterns in the ECG results and specific heart conditions. Researchers tested whether the AI could identify reduced left ventricular ejection fraction – a measure of how effectively the heart’s main pumping chamber squeezes blood out with each beat – as well as thickening of the heart muscle, and heart valve disease of moderate severity or higher.

The technology has so far been tested on the ECGs of a small group of 5,442 patients and of a larger group of 61,520 patients, all in the US, whose echocardiogram results could be compared with the AI analysis.

The AI performed particularly well at detecting reduced heart pumping function, which is a type of heart failure – a condition affecting more than a million people in the UK.
The model was able to identify up to 81% of patients who had heart failure – detecting reduced pumping function of the heart's main chamber – and identified up to 90% of patients with a common form of heart valve disease.

Heart valve disease is when one or more of the heart's valves do not work as they should to control the direction of blood flow. Aortic stenosis is one of the most common types and means the valve does not open fully, which can block or restrict the flow of blood.
The AI was able to identify several forms of heart valve disease, although its performance varied depending on which valve was affected.

The results presented by NHLI researchers at the European Society of Cardiology Congress are built on a statistical analysis called 'area under the receiver operating characteristic curve'. A score of 1.0 means the AI is always right, and 0.5 means it performs as well as someone guessing at random.

For reduced heart pumping function, the AI achieved a score of 0.86 when tested on the smaller group of around 5,000 patients, and 0.9 for the larger group of over 60,000. For aortic stenosis, it achieved scores of 0.85 and 0.73, respectively.

The technology cannot be used on its own to definitively diagnose or rule out heart failure or heart valve disease, but can identify those who are at higher risk. If integrated into clinical practice, this could improve rates of early diagnosis of these cardiac conditions.

Dr Ahmed El-Medany said, “These results suggest there is potentially far more information hidden within a routine ECG than we can recognise by looking at it ourselves."

"It is particularly encouraging that this superhuman AI performed well across separate groups of patients. The important next questions are how it performs in NHS patients and whether the same information can be captured using much simpler portable ECG devices.”

Professor Fu Siong Ng, Professor of Cardiology at NHLI and senior investigator on this project, said, “Patients can often wait several months for a heart ultrasound scan […] [It is] exciting that our technology could identify patients most at risk of heart failure and heart valve disease, so they could be prioritised for scans faster and more urgently.”

The AI is now being tested on ECGs from 590 NHS patients across London and Bristol, and the team say the AI ECG technology could be two years away from being used routinely by clinicians.

This article is based on the BHF press release (2 September 2026).