Development and validation of a survival prediction model for patients with advanced non-small cell lung cancer based on LASSO regression

Abstract

Introduction: Lung cancer remains a significant global health burden, with non-small cell lung cancer (NSCLC) being the predominant subtype. Despite advancements in treatment, the prognosis for patients with advanced NSCLC remains unsatisfactory, underscoring the imperative for precise prognostic assessment models. This study aimed to develop and validate a survival prediction model specifically tailored for patients diagnosed with NSCLC. Methods: A total of 523 patients were randomly divided into a training dataset (n=313) and a validation dataset (n=210). We conducted initial variable selection using three analytical methods: univariate Cox regression, LASSO regression, and random survival forest (RSF) analysis. Multivariate Cox regression was then performed on the variables selected by each method to construct the final predictive models. The optimal model was selected based on the highest bootstrap C-index observed in the validation dataset. Additionally, the predictive performance of the model was evaluated using time-dependent receiver operating characteristic (Time-ROC) curves, calibration plots, and decision curve analysis (DCA). Results: The LASSO regression model, which included N stage, neutrophil-lymphocyte ratio (NLR), D-dimer, neuron-specific enolase (NSE), squamous cell carcinoma antigen (SCC), driver alterations, and first-line treatment, achieved a bootstrap C-index of 0.668 (95% CI: 0.626-0.722) in the validation dataset, the highest among the three models tested. The model demonstrated good discrimination in the validation dataset, with area under the ROC curve (AUC) values of 0.707 (95% CI: 0.633-0.781) for 1-year survival, 0.691 (95% CI: 0.616-0.765) for 2-year survival, and 0.696 (95% CI: 0.611-0.781) for 3-year survival predictions, respectively. Calibration plots indicated good agreement between predicted and observed survival probabilities. Decision curve analysis demonstrated that the model provides clinical benefit at a range of decision thresholds. Conclusion: The LASSO regression model exhibited robust performance in the validation dataset, predicting survival outcomes for patients with advanced NSCLC effectively. This model can assist clinicians in making more informed treatment decisions and provide a valuable tool for patient risk stratification and personalized management.