Establishment and Validation of a Survival Benefit Prediction Model for Non-small Cell Lung Cancer after Immunotherapy.

Abstract

Objective: This study aimed to analyze the prognosis of patients with non-small cell lung cancer (NSCLC) after receiving immunotherapy and construct a prediction model to evaluate the overall survival rate of patients.

Methods: This study was a retrospective study that collected data from 493 NSCLC patients who received immunotherapy for the first time. Survival data were analyzed using Cox regression models and the Kaplan-Meier method. The average age of patients was 56 years, and the data collection process included regular outpatient follow-up and observation of overall survival (OS) in the last 36 months.

Results: Multivariate analysis identified significant risk factors such as smoking history, age, T stage, and M stage on survival and disease progression. The model's performance indicators (C-index and AUC) and calibration curve verified the model's accuracy and predictive ability. In the training set, the AUCs of 3-year and 5-year survival were 0.761 and 0.763, respectively, and in the validation set, they were 0.739 and 0.761.

Conclusion: This study developed a prediction model for evaluating the survival of NSCLC patients after immunotherapy that integrates multiple influencing factors. This predictive model can be used as a tool to assess individual risks in NSCLC patients after immunotherapy, helping clinicians to develop more precise treatment and follow-up plans, potentially improving patient outcomes.