Related Experiment Video
Updated: Jan 10, 2026
Establishing a Competing Risk Regression Nomogram Model for Survival Data
Published on: October 23, 2020
Development and validation of a novel nomogram for predicting outcomes in advanced lung cancer patients treated
Tianwei Luo1, Haiyun Geng2, Genwang Wang3
1Department of Oncology, Nanjing Drum Tower Hospital, Nanjing Drum Tower Hospital Clinical College, Nanjing University of Chinese Medicine, Nanjing, China.
Background:
Standardized management of lung cancer (LC) progressing post-immunotherapy remains challenging, with debated clinical benefits of treatment beyond progression (TBP). We evaluated the efficacy of continued immune checkpoint inhibitors (ICIs) and developed a pharmacologically guided nomogram to optimize TBP decision-making.
Methods:
This retrospective analysis of 153 LC patients undergoing post-progression ICIs continuation identified significant predictors via the least absolute shrinkage and selection operator (LASSO) regression and multivariate Cox analysis. A nomogram predicting overall survival (OS) and progression-free survival (PFS) was constructed and validated using time-dependent receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA).
Results:
Treatment regimen, Eastern Cooperative Oncology Group (ECOG) performance status, efficacy evaluation, lymph node metastasis, and liver metastasis independently predicted OS, while liver metastasis and efficacy evaluation influenced PFS. The nomogram demonstrated robust discrimination (OS C-index=0.700; PFS C-index=0.599) with area under the curve (AUC) values of 0.786/0.777/0.705 (OS) and 0.621/0.638/0.630 (PFS) at 6/12/24 months. DCA confirmed the clinical utility of the OS nomogram. Patients were stratified into high- and low-risk groups based on optimal cutoff values, and risk stratification revealed significant survival differences (p<0.01).
Conclusion:
This validated nomogram provides a clinically actionable tool to identify patients benefiting from sustained ICIs exposure, enabling pharmacologically informed TBP strategies while minimizing futile drug exposure. Future prospective multicenter studies should validate utility across diverse pharmacogenomic populations.
