Overview
My current research interest is in understanding the mechanisms of cardiovascular disease among patients with chronic kidney disease, with a particular focus on the epidemic of sudden cardiac death. The ultimate goal is to reduce the impact of sudden death through improved risk stratification and novel risk mitigation therapies. Current investigations are focused on identifying novel genetic and biomarker risk factors among CKD patients, understanding the interplay of hemodialysis-specific exposures in the development of arrhythmias, and examining the risks and benefits of implantable cardioverter defibrillators among CKD patients using clinical trial and registry data.
Current Appointments & Affiliations
Associate Professor of Medicine
·
2020 - Present
Medicine, Nephrology,
Medicine
Member in the Duke Clinical Research Institute
·
2015 - Present
Duke Clinical Research Institute,
Institutes and Centers
Recent Publications
Advanced artificial intelligence vs simpler models for 1-year death prediction among patients receiving hemodialysis.
Journal Article JAMIA Open · April 2026 OBJECTIVES: We evaluated the data requirement for modern AI tools to outperform simpler models in predicting short-term mortality in over 500 000 patients with hemodialysis-dependent kidney failure. MATERIALS AND METHODS: We compared logistic regression, b ... Full text Link to item CiteChronic Pain Locations, Characteristics, and Associations With Other Symptoms in Adults Receiving Maintenance Hemodialysis: Findings From the HOPE Consortium Trial.
Journal Article Am J Kidney Dis · February 2026 RATIONALE & OBJECTIVE: Adults receiving maintenance hemodialysis (HD) frequently report pain, yet detailed descriptions of pain in this population are lacking. This study examines pain locations, characteristics, and associations with other symptoms in adu ... Full text Link to item CiteDiscrete Time Neural Network Models to Address Time-Varying Predictor Importance: An Illustration in Predicting Mortality Over Different Time Horizons.
Journal Article IEEE J Biomed Health Inform · January 2026 Clinical predictive models (CPMs) are crucial for forecasting patient outcomes using available electronic health record (EHR) data. Traditional time-to-event (TTE) models, like the Cox proportional hazards model, assume that hazard ratios remain constant o ... Full text Link to item CiteRecent Grants
TRIO NRSA Training Core-Post Doc Trainee
Inst. Training Prgm or CMEMentor · Awarded by University of North Carolina - Chapel Hill · 2023 - 2028QT prolonging medications and sudden cardiac death among individuals on hemodialysis
ResearchPrincipal Investigator · Awarded by University of North Carolina - Chapel Hill · 2020 - 2025Association Between ECG data obtained via the Medtronic Reveal LINQ device and Real-Time Blood Chemistry Values: RADAR Ancillary Study Proposal
Clinical TrialPrincipal Investigator · Awarded by New York University School of Medicine · 2018 - 2025View All Grants
Education
Vanderbilt University ·
2001
M.D.