AI accurately predicts deadly heart rhythm problems

Credit: Unsplash+.

In a groundbreaking study from Leicester, researchers have turned to artificial intelligence (AI) to tackle one of the most pressing challenges in heart health: predicting dangerous heart rhythms before they strike.

Dr. Joseph Barker and Professor Andre Ng, a leading heart expert from the University of Leicester and the University Hospitals of Leicester NHS Trust, have shared promising results from their latest project in the European Heart Journal—Digital Health.

The heart condition in question, known as ventricular arrhythmia (VA), is a serious issue where the heart’s lower chambers beat unusually fast.

This can cause blood pressure to drop suddenly, leading to loss of consciousness and, in severe cases, sudden death if not promptly treated.

The team’s focus was on improving how doctors can tell which patients are most at risk of this frightening condition.

Dr. Barker spearheaded this study at the National Institute for Health and Care Research (NIHR) Leicester Biomedical Research Center, collaborating with Dr. Xin Li, a specialist in Biomedical Engineering.

They developed an AI tool that analyzed heart rhythm data (ECGs) from 270 adults who wore Holter monitors.

These portable devices tracked the heart’s activity during everyday routines at home, collecting data that was later examined by the team.

These participants, part of NHS care from 2014 to 2022, were chosen because their health outcomes were already known. Sadly, 159 of them had suffered from lethal ventricular arrhythmias, usually around 1.6 years after their ECG was taken.

The AI tool, named VA-ResNet-50, was tasked with reviewing these ECGs to predict the heart’s capability to develop lethal arrhythmias based on “normal for patient” heart rhythms.

The results were impressive. The AI tool correctly identified the condition 80% of the time, offering a much-needed improvement over current medical guidelines, which often fall short.

According to Professor Ng, these guidelines don’t accurately pinpoint patients at high risk of ventricular arrhythmia, resulting in many preventable deaths.

The AI’s performance means that if it identifies someone as at risk, their chance of experiencing a lethal event is three times higher than that of the average adult.

This finding is a significant leap forward, showing that AI can offer a new perspective on assessing heart risk, potentially guiding doctors in recommending life-saving treatments like implantable cardioverter defibrillators.

This study stands out not just for its innovative use of AI in heart care but also for its collaborative spirit.

The success, according to Professor Ng, is a testament to the hard work and dedication of Dr. Barker and Dr. Xin Li, who believed in the potential of AI to unlock insights from data that was previously overlooked.

By leveraging AI, this Leicester team is paving the way for more precise, timely, and effective heart care, offering hope that in the future, fewer lives will be lost to sudden and unpredictable heart rhythms.

If you care about heart disease, please read studies that herbal supplements could harm your heart rhythm, and how eating eggs can help reduce heart disease risk.

For more information about heart health, please see recent studies that apple juice could benefit your heart health, and results showing yogurt may help lower the death risks in heart disease.

The research findings can be found in European Heart Journal—Digital Health.

Copyright © 2024 Knowridge Science Report. All rights reserved.