An online clinical model and risk stratification system to predict progression-free survival for advanced non-small-cell lung cancer patients treated with PD-(L)1 inhibitor

BackgroundOur study aimed to build a risk stratification system predicting the progression-free survival (PFS) classify patients into diverse prognostic subgroups for advanced non-small-cell lung cancer treated with PD-(L)1 inhibitor.Methods404 from our center were enrolled in this and 70% (n = 282) randomly assigned training cohort other 30% 122) validation cohort. A testing contained 81 centers used assess generalizability of model. Cox regression analyses identify most significant clinical parameters. The model's performance was assessed by using concordance index (C-index), calibration curves, Decision Curve Analyses (DCAs), net reclassification improvement (NRI), integrated discrimination (IDI) analyses, curve.ResultsFive parameters identified as predictors cox regression. We then them Nomogram Evaluate relative PFS ICIs Treatment (NEPIT). C-index NEPIT cohort, 0.789 (95%CI: 0.750–0.828), 0.745 0.706–0.784), 0.766 0.744–0.788), respectively. curves presented good congruence between predictions actual observations. (DCAs) reflected positive benefits can be obtained NEPIT. results NRI IDI showed that could improve predictive power TPS. In addition, further constructed effectively categorize different subgroups.ConclusionThe tools developed would have value guiding optimal patient selection precision care.