Developing an Accurate and Interpretable Risk-Based Model for Lung Cancer Screening
• 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 and a testing dataset
• 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.
• 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
Margaret Byrne PhD, Moffitt Cancer Center
Lee Green PhD, Moffitt Cancer Center
-
EEC-GIFT: a fairness-aware machine learning framework for lung cancer screening eligibility using real-world data.
Conahan P, Robinson LA, Le T, Valdes G, Schabath MB, Byrne MM, Green L, El Naqa I, Luo Y
JNCI Cancer Spectr. 2025 Mar 20 PUBMED