Radiomic and clinical predictors of epidermal growth factor receptor mutation in stage IA non-small cell lung cancer.
Computed tomography radiomics model predicted epidermal growth factor receptor mutation status with only moderate accuracy
Radiomic and clinical predictors of epidermal growth factor receptor mutation in stage IA non-small cell lung cancer.
Epidermal growth factor receptor (epidermal growth factor receptor) mutation status plays a critical role in guiding targeted therapy for non-small cell lung cancer (non-small cell lung cancer).
This study aimed to develop a computed tomography (computed tomography) radiomics based model integrating clinical variables for non-invasive prediction of epidermal growth factor receptor mutation status in stage IA non-small cell lung cancer patients.
A total of 375 patients with stage IA non-small cell lung cancer who underwent pre-treatment chest computed tomography and epidermal growth factor receptor mutation testing were retrospectively enrolled.
Predictive performance varied across feature selection strategies and machine learning algorithms.
These findings support the value of integrating radiomic and clinical features for non-invasive epidermal growth factor receptor mutation prediction in early-stage non-small cell lung cancer.
A computed tomography radiomics based model demonstrated only moderate performance for the non-invasive prediction of epidermal growth factor receptor mutation status in patients with stage IA non-small cell lung cancer.
When clinical variables were incorporated, predictive performance improved, suggesting that clinical features provide complementary information beyond radiomics alone.