CT radiomics plus clinical data predict EGFR mutation in early-stage lung cancer

A CT radiomics-based model achieved a test-set AUC of 0.745 for predicting EGFR mutation in stage IA non-small cell lung cancer; incorporating clinical variables modestly improved performance.

• Best-performing model (Linear Regression with LASSO-30 features) achieved test-set AUC 0.745.
• Clinical variables provided complementary information, modestly enhancing predictive performance beyond radiomics alone.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.