Student Name: Katherine Tan Katherine Tan
Advisor: Patrick Heagerty
Degree Program: PhD, Biostatistics
Campus Address: Box 357232, University of Washington, Seattle, WA 98195-7232
Email Address: wlktan [at] uw [dot] edu
CV/Resume: CV/Resume (pdf)

Broad Interests: I am interested in creative ways to analyze large-scale biomedical data drawn from heterogeneous sources.

Methodological/Theoretical interests: My methodological interests involve sampling designs that are valid and resource efficient to collect labels from large-scale, heterogeneous data such as Electronic Health Records (EHR). Labels are tags associated with unstructured datas, for example medical abstraction of clinical notes. The methods I develop borrow results from machine learning, epidemiology, and experimental designs.

Applied Interests Projects: I have worked on Phase II and pragmatic clinical trials in with collaborators in neonatology, radiology, informatics, physical medicine and health services. I recently completed a project on designing, implementing, and evaluating a Natural Language Processing system to classify radiology report text, using tools in Python, Java and R.