Establishment and validation of a survival prediction model for stage IV non-small cell lung cancer: a real-world study.

Abstract

Objective: The aim of this study is to develop and validate a predictive model for predicting survival in individual advanced non-small cell lung cancer patients by integrating basic patient information and clinical data.

Methods: A total of 462 patients with advanced non-small cell lung cancer collected from Shanxi Cancer Hospital were randomly assigned (in a 7:3 ratio) to a training cohort and an internal validation cohort. Independent factors affecting patients' 3-year survival were screened and predictive models were created by using a single-factor followed by multifactor Cox regression analysis. Evaluate the performance of the model using the consistency index (C-index), calibration curves, receiver operating characteristic curves (ROC) and decision curve analysis (DCA). The collected patients who received chemotherapy alone and those who received chemotherapy combined with immunotherapy were statistically paired using propensity score matching between the two groups, and subgroup analyses were performed among the screened variables.

Results: A better prognostic model was created and a nomogram chart visualizing the model was drawn. Based on the median risk score of the training cohort, all individuals were categorized into high- and low-risk groups, with the high-risk group having worse OS in both cohorts (P<0.05). The results of subgroup analysis showed that chemotherapy alone versus chemotherapy combined with immunotherapy in patients with advanced NSCLC affected OS.

Conclusion: A clinical predictive model was developed to predict 3-year survival in patients with advanced non-small cell lung cancer. The study demonstrated that chemotherapy combined with immunotherapy is superior to chemotherapy alone.