Prevention AI can spot hidden heart valve problems from a simple ECG

A study, published in The European Heart Journal, funded by the British Heart Foundation, National Institute for Health and Care Research, and the Medical Research Council, found that an AI algorithm can predict serious heart conditions years in advance using only ECG data

Researchers found that their AI could spot very early changes in the heart’s structure from an ECG, a common test which shows the heart’s electrical activity. The advanced algorithm could detect issues in the heart’s valves, which keep blood flowing in the correct direction through the heart’s chambers, even before the appearance of symptoms or physical changes that can be detected by ultrasound scans.

The AI could accurately predict who would go on to develop significant leaks in the heart’s mitral, tricuspid, or aortic valves – conditions known as regurgitant valvular heart diseases. It was able to correctly identify the risk of a leaky heart valve in the years following the ECG (from high to low) in around 69-79% of cases.

People flagged as ‘high-risk’ by the algorithm were up to 10 times more likely to develop these diseases than those classed as lower risk.

According to the team from Imperial College London and Imperial College Healthcare NHS Trust, their AI-enhanced predictions could potentially transform doctors’ approach to treating heart valve disease.

It’s estimated that 41 million people worldwide, including 1.5 million people in the UK, live with these heart valve diseases, which can lead to heart failure, hospital admissions and death. Early diagnosis is key for successful treatment. But the symptoms, which can include shortness of breath, dizziness, feeling tired and having heart palpitations, can be easily confused with other causes, while some patients don’t show any symptoms until the disease is advanced.

Earlier detection

Dr Arunashis Sau, one of the study leads, Academic Clinical Lecturer at Imperial College London’s National Heart and Lung Institute, and cardiology registrar at Imperial College Healthcare NHS Trust said: “Our hearts are incredibly complex and hard-working organs, but we rarely give them much consideration unless something goes wrong. By the time symptoms and structural changes appear in the heart, it may be too late to do much about it. Our work is harnessing AI to detect subtle changes at the earliest stage from a simple and common test, and we think this could be really transformative for doctors and patients. Rather than waiting for symptoms or relying only on expensive and time-consuming imaging tests, we could use AI-enhanced ECGs to spot those most at risk earlier than ever before. This means that many more people could get the care they need before their hidden condition affects their quality of life or becomes life-threatening.”

The study was part of an international collaboration led by researchers Drs Sau and Dr Fu Siong Ng and involving researchers in China, based at Shanghai’s Zhongshan Hospital. AI models were trained using nearly one million ECG and heart ultrasound (echocardiogram) records from over 400,000 patients in China. The technology was then tested on a separate group of more than 34,000 patients in the United States, showing that it works well across ethnically diverse populations and healthcare systems.

Issues with heart valves may first appear as very small changes to the heart’s electrical activity which are not apparent to doctors. These electrical changes become larger, but by this point, symptoms have often started to develop. The AI system can detect these subtle electrical patterns much earlier, hopefully before symptoms develop at all.

Dr Ng, the senior author, Reader in Cardiac Electrophysiology at the National Heart & Lung Institute at Imperial College London and a consultant cardiologist at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust, said:

“AI has enormous potential for improving healthcare around the world, but it requires huge amounts of data to train and test these algorithms. Our work is an example of the benefits of international collaboration in this fast-growing area. By training the model in an almost exclusively Chinese population and then testing in a US cohort, we can show that our AI tool has the potential to be applied in various countries and settings around the world. This ultimately means it has the potential to help even more patients.”

Continued work

The research builds upon the team’s development of the related AI-ECG risk estimation model, known as AIRE, which can predict patients’ risk of developing and worsening disease based on an ECG. Other AI models from this project have been trained to analyse ECGs to predict problems such as female heart disease risk, health risks including early death, high blood pressure and type 2 diabetes.

Trials of AIRE in the NHS are already planned for late 2025. These will evaluate the benefits of implementing the model with real patients from hospitals across Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust.