Study
NLST
(Learn more about this study)
Project ID
NLST-1050
Initial CDAS Request Approval
Apr 19, 2023
Title
Developing an Accurate and Interpretable Risk-Based Model for Lung Cancer Screening
Summary
Lung cancer is the third most common cancer in both men and women, but it is the leading cause of cancer death in the United States. In 2021, the US Preventive Services Task Force (USPSTF) recommended an annual screening for lung cancer with low dose computed tomography (LDCT) in adults aged 50 to 80 years who have at least a 20 pack per year smoking history and who currently smoke or have quit within the past 15 years. Although smoking and age are the most important risk factors for detecting lung cancer, there are several other important risk factors that were not included in the current screening guideline. Therefore, there is a larger proportion of lung cancer incidence and mortality in individuals who were not included in the screening guideline (e.g., non-smokers). A more accurate and interpretable risk-based model for lung cancer screening would benefit high-risk individuals in getting screened and might help reduce lung cancer mortality.
Aims
1. To integrate patients' sociodemographic information, smoking behaviors, socioeconomic statuses, healthcare factors, and clinical studies in the PLCO and NLST datasets and separate these patients into a training dataset and a testing dataset
2. To develop an accurate and interpretable risk-based model to predict the risk of a patient's lung cancer incidence by using Bayesian network approach based on the training dataset.
3. To test the developed risk-based model based on the testing dataset and compare its predictive performance and interpretability with existing models (e.g., PLCOm2012, PLCOall2014) and USPSTF recommendation
Collaborators
Margaret Byrne PhD, Moffitt Cancer Center
Lee Green PhD, Moffitt Cancer Center