Abstract
Objective: The aim of this study was to develop a nomogram model for predicting epidermal growth factor receptor (EGFR) mutations and their common subtypes in non-small cell lung cancer (NSCLC) patients.
Methods: We conducted this study using data from NSCLC patients at the First Affiliated Hospital of Chongqing Medical University in China, including a total of 557 NSCLC patients. We identified independent risk factors for predicting EGFR mutations and their common subtypes through logistic univariable and multivariable analyses. These factors were then integrated to construct a nomogram, which underwent internal validation. We assessed the nomogram's predictive performance using receiver operating characteristic (ROC) curves and calibration plots. We randomly divided the dataset into training (n = 390) and validation (n = 167) cohorts in a 7:3 ratio. Following univariate and multivariate analyses, the nomogram for predicting EGFR mutations included four independent risk factors: age, pathological pattern (adenocarcinoma, ADC), smoking status, and squamous cell carcinoma antigen (SCC) levels. The nomogram for predicting EGFR exon 19 deletion mutation (19-Del) incorporated four independent risk factors: pathological pattern, smoking status, the presence of cytokeratin 21 fragment (CYFRA21.1), and tumor node metastasis (TNM). The nomogram for predicting EGFR exon 21-L858R mutation (21-L858R) included five independent risk factors: age, tumor location, pathological pattern, smoking status, and TNM.
Results: In the nomogram for predicting EGFR mutations, the C-index of the nomogram model was 0.769 in the training cohort and 0.757 in the validation cohort. In the nomogram for predicting EGFR exon 19 deletion mutation, the C-index of the nomogram model was 0.673 in the training cohort and 0.743 in the validation cohort. In the nomogram for predicting EGFR exon 21-L858R mutation (21-L858R), the C-index of 0.745 in the training cohort and 0.641 in the validation cohort. The calibration plot of the nomogram shows a good agreement between the predicted probability and the actual probability.
Conclusion: We have successfully developed and validated a novel nomogram for predicting EGFR mutation subtypes in NSCLC patients. This nomogram accurately estimates the EGFR mutation subtype and can help identify patients who may benefit from specific, individualized therapies.