Hello

I'm a clinical data scientist and NIH Fellow with a PhD in Biomedical Informatics (UCSF, August 2025), focused on translating real-world evidence into actionable insights. My work integrates machine learning, epidemiology, and clinical informatics to model disease progression, identify patient subgroups, and uncover the drivers of health outcomes. 

​

I’m well-versed in statistical and ML methods for tabular, imaging, and text data, from classical models (Naïve Bayes, logistic regression, random forests, SVMs) to neural networks for imaging/tabular data and transformer-based architectures for clinical notes.

​

I specialize in building interpretable, end-to-end ML pipelines using longitudinal EHR and claims data, incorporating health system variables such as ICD codes, vitals, labs, and unstructured clinical text. I’ve designed workflows that span study design, temporal modeling, quality assurance, and model validation, ensuring outputs are clinically relevant, reproducible, and scalable for deployment.​

​

I thrive in interdisciplinary environments where scientific rigor meets product thinking. Whether collaborating with engineers to optimize data pipelines or working with clinicians to refine model outputs, I’m driven by a mission to create trustworthy, equitable, and impactful data-driven tools for real-world healthcare challenges.