Novel Epidemiological Risk Models, with Application to Screening - Dr. Cheung

Biostatistics Branch Seminar Series

April 20, 2020 | 10:30 AM – 11:30 AM

Webex only

Add to Outlook Calendar

Speaker

Li Cheung, Ph.D., Staff Scientist
Biostatistics Branch, Division of Cancer Epidemiology and Genetics,
National Cancer Institute

Abstract

My research interest focuses on the development of statistical methods for analyzing electronic health record data, using these methods to model the natural history of intervening stages in the carcinogenic process, and the development of evidence-based cancer screening guidelines. I will discuss some of the critical statistical challenges involved in analyzing such data, and why standard tools for absolute and relative risk estimation are biased. I will introduce new statistical models that can be used to produce unbiased estimates in cohort studies with multiple time point data and biospecimen collection. These models are used to develop new risk-based management guidelines for cervical cancer. I will also discuss risk models and benefit models for oral cancer and lung cancer screening.  

Join Via WebEx
Meeting number: 470 540 547
Password: BBsem04.20

Join by phone
1-650-479-3207 Call-in toll number (US/Canada)
Access code: 470 540 547