Date: February 1, 2024
In a revolutionary stride towards personalized heart failure treatment, a recent study co-authored by Dr. Matthew Segar, a third-year cardiovascular disease fellow at The Texas Heart Institute, and led by Dr. Ambarish Pandey from the University of Texas Southwestern Medical Center, introduces the BAN-ADHF score—a machine learning-based prediction tool for diuretic responsiveness. Published in the esteemed Journal of American College Cardiology Heart Failure (JACC Heart Failure), the study leverages decades of clinical and registry datasets funded by the National Institutes of Health and the American Heart Association.
Heart failure affects millions globally, and diuretics are a common therapy for managing fluid retention in patients with acute decompensated heart failure (ADHF). The effectiveness of diuretic therapy can vary, posing challenges for tailored treatment plans. Dr. Segar and Dr. Pandey’s study addresses this by employing machine learning algorithms to develop the BAN-ADHF score, demonstrating promising results in accurately predicting diuretic response.
The BAN-ADHF score has the potential to transform the management of ADHF by providing a personalized strategy for effectively handling congestion in hospitalized patients. Dr. Segar highlights the importance of early identification of individuals with low diuretic efficiency, stating, “Inefficient diuretic response in hospitalized patients can hinder treatment progress and increase the risk of post-discharge rehospitalization and mortality.”
The lack of consensus among experts on the most effective approach to diuretic resistance in stable heart failure patients adds complexity to treatment decisions. The study emphasizes the significance of tailoring decongestion strategies based on the BAN-ADHF score, potentially improving clinical outcomes and reducing healthcare costs associated with ADHF.
Dr. Joseph G. Rogers, President and CEO of The Texas Heart Institute, emphasizes the need for a more personalized approach, stating, “Because of the heterogeneity of ADHF patients, a more personalized approach to predicting optimal dosing strategies is needed.”
The study utilized machine learning algorithms on diverse datasets from clinical trials and registries, developing a diuretic efficiency phenomapping approach for ADHF patients. This approach identifies subgroups based on diuretic responsiveness, allowing for a more nuanced understanding of patient needs. The BAN-ADHF score was subsequently developed and validated, showing promise in predicting diuretic resistance probability.
The groundbreaking work by Dr. Segar and Dr. Pandey gained recognition from the National Institutes of Health’s National Heart, Lung, and Blood Institute (NHLBI) as a winning solution to the NHLBI Big Data Analysis Challenge. Dr. Segar was also honored with the American Heart Association’s Samuel A. Levine Early Career Clinical Investigator Award for his role in developing the phenomapping tool and the diuretic resistance clinical risk score.
The study’s collaborators included researchers from esteemed institutions such as Duke University School of Medicine, Cleveland Clinic, Houston Methodist DeBakey Heart and Vascular Center, and University of Colorado, among others.
As the medical community continues to embrace the potential of artificial intelligence, studies like these pave the way for more precise and individualized approaches to heart failure management, offering hope for improved patient outcomes and a significant step forward in the realm of cardiovascular care.