In a groundbreaking study conducted in Leicester, researchers have found that artificial intelligence (AI) can be used to predict whether a person is at risk of a fatal heart rhythm with an impressive 80% accuracy rate.

Led by Dr. Joseph Barker in collaboration with Professor Andre Ng, the study focused on ventricular arrhythmia (VA), a serious heart rhythm disturbance that can lead to sudden death if not promptly treated. VA originates from the bottom chambers of the heart, causing a rapid drop in blood pressure and potentially resulting in loss of consciousness.

The findings of this study, published in the European Heart Journal—Digital Health, shed light on the potential of AI in identifying individuals at risk of VA. Dr. Barker, an NIHR Academic Clinical Fellow, spearheaded the multicentre study at the National Institute for Health and Care Research (NIHR) Leicester Biomedical Research Centre.

Together with Dr. Xin Li, a lecturer in biomedical engineering, Dr. Barker co-developed an AI tool named VA-ResNet-50. This tool analysed Holter electrocardiograms (ECGs) of 270 adults obtained during their normal daily routines at home. The participants had undergone Holter ECGs as part of their NHS care between 2014 and 2022, and outcomes were recorded. Unfortunately, 159 individuals had experienced lethal ventricular arrhythmias for an average of 1.6 years following the ECG.

Commenting on the findings, Professor Ng said, “Current clinical guidelines that help us to decide which patients are most at risk of going on to experience ventricular arrhythmia, and who would most benefit from the life-saving treatment with an implantable cardioverter defibrillator are insufficiently accurate, leading to a significant number of deaths from the condition.

“Ventricular arrhythmia is rare relative to the population it can affect, and in this study we collated the largest Holter ECG dataset associated with longer term VA outcomes. 

“We found the AI tool performed well compared with current medical guidelines, and correctly predicted which patient’s heart was capable of ventricular arrhythmia in 4 out of every 5 cases.

“If the tool said a person was at risk, the risk of a lethal event was three times higher than that of normal adults.

“These findings suggest that using artificial intelligence to look at patients’ electrocardiograms while in normal cardiac rhythm offers a novel lens through which we can determine their risk and suggest appropriate treatment, ultimately saving lives.”

He added: “This is important work, which wouldn’t have been possible without an exceptional team in Dr. Barker and Dr. Xin Li and their belief and dedication to novel methods of analysis of historically disregarded data.”

The AI tool, VA-ResNet-50, demonstrated remarkable performance compared to existing medical guidelines, accurately predicting VA in 4 out of 5 cases. According to Professor Ng, individuals identified as at risk by the AI tool had a threefold higher risk of experiencing a lethal event.

The implications of these findings are profound, suggesting that AI analysis of patients' electrocardiograms during normal cardiac rhythm could revolutionise risk assessment and treatment decisions, potentially saving lives.

Dr. Barker's outstanding contributions to this research have earned recognition, including a van Geest Foundation Award and a Heart Rhythm Society Scholarship. Further research is planned to advance this groundbreaking work and its potential applications in clinical practice.