Development and external validation of a radiomics combined with clinical nomogram for preoperative prediction prognosis of resectable pancreatic ductal adenocarcinoma patients
Fangqing Wang, Yuxuan Zhao, Jianwei Xu, Shao Sai, Dexin Yu
Abstract
Purpose To develop and externally validate a prognosis nomogram based on contrast-enhanced computed tomography (CECT) combined clinical for preoperative prognosis prediction of patients with pancreatic ductal adenocarcinoma (PDAC). Methods 184 patients from Center A with histopathologically confirmed PDAC who underwent CECT were included and allocated to training cohort (n=111) and internal validation cohort (n=28). The radiomic score (Rad - score) for predicting overall survival (OS) was constructed by using the least absolute shrinkage and selection operator (LASSO). Univariate and multivariable Cox regression analysis was used to construct clinic-pathologic features. Finally, a radiomics nomogram incorporating the Rad - score and clinical features was established. External validation was performed using Center B dataset (n = 45). The validation of nomogram was evaluated by calibration curve, Harrell’s concordance index (C-index) and decision curve analysis (DCA). The Kaplan-Meier (K-M) method was used for OS analysis. Results Univariate and multivariate analysis indicated that Rad – score, preoperative CA 19-9 and postoperative American Joint Committee on Cancer (AJCC) TNM stage were significant prognostic factors. The nomogram based on Rad - score and preoperative CA19-9 was found to exhibit excellent prediction ability: in the training cohort, C-index was superior to that of the preoperative CA19-9 (0.713 vs 0.616, P < 0.001) and AJCC TNM stage (0.713 vs 0.614, P < 0.001); the C-index was also had good performance in the validation cohort compared with CA19-9 (internal validation cohort: 0.694 vs 0.555, P < 0.001; external validation cohort: 0.684 vs 0.607, P < 0.001) and AJCC TNM stage (internal validation cohort: 0.694 vs 0.563, P < 0.001; external validation cohort: 0.684 vs 0.596, P < 0.001). The calibration plot and DCA showed excellent predictive accuracy in the validation cohort. Conclusion We established a well-designed nomogram to accurately predict OS of PDAC preoperatively. The nomogram showed a satisfactory prediction effect and was worthy of further evaluation in the future.