Researchers at the UK’s University of Birmingham have used AI to develop a new way to identify patients with heart failure who will benefit from treatment with beta-blockers.

In their study, published at The Lancet, the team noted that while advances in therapeutics have substantially improved the prognosis of patients with heart failure, mortality remains unacceptably high; indeed, greater than most cancers.

“With prevalence of atrial fibrillation (AF) expected to double in the coming decades,” they wrote, “better identification of patient subgroups that could benefit from therapy is critical to address this unsustainable burden on health-care services. Conversely, the ability to identify individuals who are unlikely to receive therapeutic benefit could allow for a more personalised medicine approach, by stratifying the use of additional management strategies available in clinical practice.”

For the study, which involved 15,669 patients with heart failure and reduced left ventricular ejection fraction (low function of the heart's main pumping chamber),” the researchers used a series of AI techniques to “deeply interrogate” data from clinical trials. The research showed that the AI approach could take account of different underlying health conditions for each patient as well as the interactions of these conditions, to isolate response to beta-blocker therapy. 

Of the patients studies, 12,823 of which were in normal heart rhythm and 2,837 of which had AF, a heart rhythm condition commonly associated with heart failure that leads to worse outcomes.

The research was led by the cardAIc group, a multi-disciplinary team of clinical and data scientists at the University of Birmingham and the University Hospitals Birmingham NHS Foundation Trust, aiming to integrate AI techniques to improve the care of cardiovascular patients. The study used individual patient data from nine landmark trials in heart failure that randomly assigned patients to either beta-blockers or a placebo.The AI-based approach combined neural network-based variational autoencoders and hierarchical clustering within an objective framework, and with detailed assessment of robustness and validation across all the trials.

“Although tested in our research in trials of beta-blockers,” noted Georgios Gkoutos, Study Corresponding Author and Professor of Clinical Bioinformatics at the University of Birmingham,  “these novel AI approaches have clear potential across the spectrum of therapies in heart failure, and across other cardiovascular and non-cardiovascular conditions."

On a similar note, Corresponding author Dipak Kotecha, Professor and Consultant in Cardiology at the University of Birmingham, international lead for the Beta-blockers in Heart Failure Collaborative Group, and co-lead for the cardAIc group, said, "Development of these new AI approaches is vital to improving the care we can give to our patients; in the future this could lead to personalised treatment for each individual patient, taking account of their particular health circumstances to improve their well-being."

Photo by Devrimb/Getty Images