Can a machine learning algorithm successfully select a patient who will respond to a costly, invasive surgical procedure in which outcome is extremely uncertain? Patients with ventricular dyssynchrony experience a condition in which the chambers of their hearts no longer contract at the same time. As a consequence, these patients develop heart failure (HF) which can be fatal. Fortunately, cardiac resynchronization therapy (CRT) offers life-saving benefits to these patients by using pacemakers to resynchronize ventricular contraction while reversing HF [1]. However, an alarming 30-50% of patients selected to receive the costly and invasive CRT procedure under current guidelines set by physicians at the American Heart Association (AHA) fail to respond to the treatment [2]. Outcomes after CRT are influenced by complex interactions between the physical, electrical, and mechanical properties of the heart, but machine learning may be capable of uncovering patterns between these interactions and patient response. Therefore, the objective of this study is to use machine learning to predict if a patient will respond to CRT as well as to identify clinical features important in such classification.
PhD Candidate, Department of Biomedical Engineering, University of Virginia
Derek is a third-year PhD candidate in the Department of Biomedical Engineering at the University of Virginia. As a member of the Cardiac Biomechanics Group, he develops computer models to study heart growth and remodeling in response to both disease and therapy. Derek utilizes machine... Read More →
