As a Rhodes Scholar (Christ Church & Virginia, 2018) at the University of Oxford’s Computational Health Informatics (CHI) Lab and Nuffield Department of Population Heatlh, my doctoral research focused on the utilization of machine learning approaches for assessing stroke risk in the China Kadoorie Biobank — a contemporary cohort of 0.5 million Chinese adults. During my time at Oxford, I developed novel risk prediction models for China’s unique stroke epidemic and improved upon traditional epidemiological techniques with modern machine learning approaches. I also studied differences in risk prediction for ischemic and hemorrhagic stroke pathological types, utilizing these findings to optimize the use of statin therapy for primary prevention of cardiovascular disease in China. My thesis further explored the use of machine learning for subtyping of ischemic strokes including large artery atherosclerotic events, cardioembolic strokes, and small artery occlusions.
In April 2020, in response to the global rise of COVID-19, I was recruited as an analyst for the UK’s national DECOVID consortium, tasked with generating insights on the coronavirus pandemic using multicenter NHS data. In the early stages of this endeavor, I contributed to ethics discussions, workflow planning, and initial testing of the secure research environment.
My Oxford Engineering Science bio can be found here.
Research Publications
Chun et al. Utility of single versus sequential measurements of risk factors for prediction of stroke in Chinese adults. Sci Rep.
Chun et al. Improved stroke risk prediction using machine learning: a prospective cohort study of 0.5 million Chinese adults. J Am Med Inform Assoc.
Chun et al. Development, validation and comparison of multivariable risk scores for prediction of total stroke and stroke types in Chinese adults: a prospective study of 0.5 million adults. Stroke Vasc Neurol.