Predicting early recurrence for resected pancreatic ductal adenocarcinoma: a multicenter retrospective study in China.

Abstract

A precise classification of early recurrence (ER) after radical surgery of pancreatic ductal adenocarcinoma (PDAC) has not been standardized. We aim to develop an optimal cut-off based on scientific evidence to distinguish early and late recurrence (LR) for PDAC after radical surgery and develop a predictive model for ER of PDAC. The best threshold for recurrence-free survival (RFS) was assessed with a minimum P-value method, and patients were categorized into ER and LR groups. We used a logistic regression model to assess potential risk factors for ER and develop a predictive model for ER risk. The best threshold between high-risk and intermediate-high-risk groups was identified by using the receiver operating characteristic curve. Among 3,279 patients included, 1,234 (37.6%) experienced ER. The RFS of 9 months is the optimal threshold to distinguish ER and LR. Univariable and multivariable analysis identified four preoperative risk factors for ER, including larger tumor maximal diameter on computed tomography (CT), enlarged lymph nodes on CT, carbohydrate antigen (CA) 125 > 35 U/ml, and CA19-9 > 235 U/ml. The concordance index (C-index) for the predictive model in the training cohort and the validation cohort was 0.651 (95% confidence interval (CI): 0.624-0.678), and 0.636 (95% CI: 0.593-0.679), respectively, showing promising predictive ability. The high-risk group had a score above 203, and the corresponding risk of ER for this group was 56.7%. An RFS of 9 months is the best threshold to distinguish ER and LR. The model can accurately predict the risk of ER in PDAC after radical resection, and risk grouping can predict the patients who could benefit from upfront surgery.

• Authors: Weikang Liu, Bingjun Tang, Feng Wang, Chang Qu, Hao Hu, Yan Zhuang, Hongqiao Gao, Xuehai Xie, Xiaodong Tian, Yinmo Yang
• Journal: American journal of cancer research (Am J Cancer Res) Vol. 11 Issue 6 Pg. 3055-3069 ( 2021) ISSN: 2156-6976 [Print] United States
• PMID: 34249444 (Publication Type: Journal Article)
• Copyright: AJCR Copyright © 2021.