Predicting lung cancer from clinical data and evaluating simulated screening programs
Principal Investigator
Name
Adam Yala
Degrees
Ph.D.
Institution
The Regents of the University of California, on behalf of its Berkeley campus
Position Title
Assistant Professor
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-1316
Initial CDAS Request Approval
Sep 5, 2023
Title
Predicting lung cancer from clinical data and evaluating simulated screening programs
Summary
For multiple diseases, early detection significantly improves patient outcomes. For instance, two large randomized controlled trials have established the efficacy of lung cancer screening (LCS) using low- dose computed tomography (LDCT) in cigarette smokers, with 20% and 24% decreases in lung cancer mortality in the National Lung Screening Trial (NLST) and the NELSON trial, respectively. This motivates considerable investments in population-wide screening programs, such as mammography for breast cancer and low-dose CT for lung cancer. To be effective and economically viable, these programs must find the right balance between early detection and overscreening. In this class project, we will develop machine learning tools to predict lung cancer risk from PLCO questionnaires, develop screening guideline simulations, and compare the cost-effectiveness of these proposed guidelines against current NLST criteria. This project will act as an invaluable teaching tool in a new UC Berkeley course.
Aims
- Develop machine learning models to predict lung cancer risk from PLCO questionares
- Simulate lung cancer screening guidelines based on new risk predictors
- Compare the simulated cost effectiveness of novel guidelines against NLST criteria
Collaborators
Adam Yala, UC Berkeley