Dr. Ramsey Wehbe MD, MSAI
Ramsey Wehbe, MD MSAI is a heart failure cardiologist and an assistant professor of medicine at MUSC, with dual appointments in the Division of Cardiology and the Biomedical Informatics Center. He is a physician scientist with expertise and formal training in artificial intelligence, and his clinical interests include cardiac imaging in the diagnosis of heart failure subtypes.
Dr. Wehbe completed his undergraduate studies at Duke University and medical school at the University of North Carolina at Chapel Hill. Prior to medical school, he spent a year at the National Institutes of Health (NIH) as a clinical research fellow. He then completed his residency in internal medicine and fellowship in cardiovascular disease, both at Northwestern, followed by an innovative fellowship in Artificial Intelligence at the Northwestern Bluhm Cardiovascular Institute, which culminated in a Master of Science in Artificial Intelligence degree from the Northwestern McCormick School of Engineering. Following this program, Dr. Wehbe completed a fellowship in advanced heart failure at Northwestern.
Dr. Wehbe has published extensively on the clinical application of artificial intelligence, particularly deep learning, to unstructured data sources (including imaging and free text from clinical notes) and holds several research awards/grants in this field. He sees great value in these technologies to help more deeply phenotype the heart failure syndrome and improve outcomes for patients living with heart failure.
Dr. Wehbe is the primary investigator of the Heart AI Lab (HEAL). HEAL is a team of researchers in the Division of Cardiology and Biomedical Informatics Center (BMIC) at the Medical University of South Carolina (MUSC) dedicated to using artificial intelligence to improve the health of patients living with cardiovascular disease, with a particular focus on heart failure. HEAL boasts an expanding program of both collaborative and internal research. Using innovative approaches to develop and apply cutting-edge deep learning methodologies, we analyze multi-modal unstructured data—such as cardiac imaging, electronic health records, and sensor data—to uncover new pathophysiologic insights, improve diagnostics, and enhance patient care. HEAL strives to bridge the gap between artificial intelligence and cardiovascular medicine, driving impactful research with real-world applications.