Abstract
OBJECTIVE: Construction nomogram was to effectively predict long-term prognosis in patients with non-small cell lung cancer (NSCLC). MATERIALS AND METHODS: The nomogram is developed by a retrospective study of 347 patients with NSCLC who underwent cardiopulmonary exercise testing (CPET) before surgery from May 2019 to February 2022. Cross-validation divided the data into a training cohort and validation cohort. The discrimination and accuracy ability of the nomogram were proofed by concordance index (C-index), calibration curve, receiver operating characteristic (ROC) curve, the area under the curve (AUC), and time-dependent ROC in validation cohort. RESULTS: Age, intraoperative blood loss, VO(2) peak, and VE/VCO(2) slope were included in the model of nomogram. The model demonstrated good discrimination and accuracy with C-index of 0.770 (95% CI: 0.712-0.822). AUC of 6 (AUC: 0.789, 95% CI: 0.726-0.851) and 12 months (AUC: 0.787, 95% CI: 0.724-0.850) were shown in ROC. Time-independent ROC maintains a good effect within 12 months. CONCLUSION: We developed a nomogram based on CPET. This model has a good ability of discrimination and accuracy. It could help clinicians to make treatment decision in clinical decision.