At the University of Birmingham, scientists have designed a new method to identify patients with heart failure, who will potentially benefit from treatment with beta-blockers.
The participants of the study included 15,669 patients with heart failure and decreased left ventricular ejection fraction (low function of the heart’s main pumping chamber). Of all the cases, 12,823 cases were in normal heart rhythm and 2,837 cases had atrial fibrillation (AF), which is a heart rhythm condition generally linked to heart failure that results in worse effects.
Heart failure is considered one of the most common heart conditions, with a significant impact on patient quality of life, and a major cause of hospitalization and healthcare cost.
The study, which was published in the journal The Lancet on August 30th, 2021, involved an array of artificial intelligence (AI) methods to keenly understand the data obtained from clinical trials. The study revealed the potential of the AI approach in considering different underlying health conditions of the patients and also the correlation of these conditions. This enabled the isolation of the response to beta-blocker therapy.
This was found to work in patients having normal heart rhythm, where the doctors would usually expect the beta-blockers to decrease the risk of death, including patients with AF where the previously employed method is found to be ineffective.
A cluster of patients having normal heart rhythm (who had a combination of older age, less severe symptoms and lower heart rate than average) was found to have reduced benefit from beta-blockers.
On the other hand, in patients with AF, the study observed a group of young patients with lower rates of prior heart attack. However, they had a heart function similar to the average AF patient who had a significant reduction in death with beta-blockers ranging from 15% to 9%.
The study was guided 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, focusing to combine AI techniques to enhance the care of cardiovascular patients.
The research was performed based on the data recorded and harmonized by the Beta-blockers in Heart Failure Collaborative Group, a global consortium dedicated to improving treatment for patients with heart failure.
The study utilized individual patient data from nine landmark trials in heart failure that randomly assigned patients to either a placebo or beta-blockers. The average age of the participants was around 65 years, and out of the total, 24% were women. The AI-based method integrated neural network-based differential autoencoders and hierarchical clustering within a target framework, and also with a detailed verification of robustness and validation throughout all the trials.
Although tested in our research in trials of beta-blockers, these novel AI approaches have clear potential across the spectrum of therapies in heart failure, and across other cardiovascular and non-cardiovascular conditions.
Georgios Gkoutos, Study Corresponding Author and Professor of Clinical Bioinformatics, University of Birmingham
Georgios Gkoutos is also the associate director of Health Data Research Midlands and co-lead for the cardAIc group.
“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 personalized treatment for each individual patient, taking account of their particular health circumstances to improve their well-being.”
Dipak Kotecha, Study Corresponding Author, Professor and Consultant in Cardiology, University of Birmingham
Dipak Kotecha is the international lead for the Beta-blockers in the Heart Failure Collaborative Group, and co-lead for the cardAIc group.
We hope these important research findings will be used to shape healthcare policy and improve treatment and outcomes for patients with heart failure.
Dr. Andreas Karwath, Study First Author and Rutherford Research Fellow, University of Birmingham
The study was recently presented at the ESC Congress 2021, on August 30th, 2021, hosted by the European Society of Cardiology — a non-profit knowledge-based professional association that simplifies the enhancement and harmonization of standards of diagnosis and treatment of cardiovascular diseases.
Karwath, A., et al. (2021) Redefining β-blocker response in heart failure patients with sinus rhythm and atrial fibrillation: a machine learning cluster analysis. The Lancet. doi.org/10.1016/S0140-6736(21)01638-X.