Construction and validation of a nomogram for predicting overall survival in stage IV non-small cell lung cancer treated with epidermal growth factor receptor tyrosine kinase inhibitors.

Background: Despite the widespread adoption of epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) as the primary therapeutic strategy for EGFR mutated non-small cell lung cancer (NSCLC), the general survival probabilities for patients in stage IV are still limited. The objective of this research was to create a nomogram that forecasts overall survival (OS) in patients with advanced NSCLC undergoing EGFR-TKI treatment. Methods: A group of 461 patients with advanced EGFR-mutant NSCLC was recruited and randomly divided into training and validation sets in a ratio of 7:3. The predictive nomogram was constructed after identifying independent prognostic factors within the training group by applying the Cox regression analysis. The nomogram was evaluated by R software, with assessments including decision curve analyses, receiver operating characteristic curves, and calibration curves. Results: Multivariate Cox regression identified brain metastasis, neuron-specific enolase (NSE), cytokeratin fragment 19 (CYFRA 21-1), EGFR-TKIs, radiotherapy, and chemotherapy as independent prognostic factors. The nomogram was constructed based on these prognostic factors. The C-index was 0.713 in both the training and validation cohorts, with calibration curves demonstrating strong concordance between predicted and actual outcomes. The area under the receiver operating characteristic curve demonstrated robust predictive accuracy, with values of 0.771, 0.772, and 0.768 at 1, 3, and 5 years in the training cohort, and 0.802, 0.761, and 0.722 in the validation cohort. Decision curve analysis (DCA) confirmed the strong clinical applicability of the nomogram. Based on the nomogram scores, patients were stratified into high- and low-risk groups, with OS markedly increased in the latter group over the former (P<0.001). Conclusions: The nomogram was created using clinical features to forecast OS in stage IV NSCLC patients with EGFR mutations undergoing EGFR-TKI therapy.