I’m a PhD student in Biostatistics at the University at Albany, SUNY. My research lies at the intersection of biostatistics, epidemiology, artificial intelligence, and environmental health. I develop quantitative methods that explain how environmental and social conditions shape population health and healthcare utilization.
My doctoral research examines environmental exposures, extreme weather, healthcare utilization, and population vulnerability. I analyze large-scale health, environmental, and socioeconomic data with statistical modeling, time-series methods, distributed lag models, and machine learning.
Published work in this direction includes a study of environmental health disparities among older adults in New York State and my first-author analysis of seasonal and periodic patterns of ischemic heart disease in New York. Related collaborative studies have examined socioeconomic and environmental correlates of glaucoma and disparities in the use of ophthalmic care.
I develop artificial intelligence methods for health research across large language models, foundation models, model compression, and medical image analysis.
I contributed to LLM-MedQA, a case-based approach to medical question answering presented at the International Joint Conference on Neural Networks, and to post-training quantization for medical image segmentation foundation models, published in Medical Image Analysis.
I am first author of a study of weight group-wise post-training quantization for medical foundation models, and of a quality-controlled framework for multi-structure left atrial segmentation on cardiac CT. I have also contributed to uncertainty-aware deep learning for cardiovascular image segmentation. I design these methods to remain interpretable in health research.
Before my doctoral studies, I worked as a biostatistician on clinical trials and observational studies, principally in ophthalmology, with investigators at the University of Pennsylvania and collaborating institutions.
I am first author of a latent profile analysis of tear cytokines and dry eye severity in the Dry Eye Assessment and Management (DREAM) Study, published in Scientific Reports, and a coauthor on the study’s longitudinal work linking tear biomarkers, clinical signs, symptoms, and quality of life.
My glaucoma research includes the Primary Open-Angle African American Glaucoma Genetics (POAAGG) Study, covering structural and functional progression, socioeconomic and environmental factors, and clinically defined ocular phenotypes.
I have also contributed to clinical studies published in JAMA Ophthalmology and The Lancet Global Health, including analyses of endophthalmitis after intraocular procedures and the FLAME trial of surgery for trachomatous trichiasis.
These studies required methods for longitudinal and correlated data, including generalized estimating equations, mixed-effects models, and survival analysis.
I am now building interpretable approaches to population health vulnerability and uncertainty-aware prediction, integrating statistical modeling with machine learning and artificial intelligence.
