Robotic pancreaticoduodenectomy decreases the risk of clinically relevant post-operative pancreatic fi stula: a propensity score matched NSQIP analysis

Background: A single-institution study demonstrated robotic pancreaticoduodenectomy (RPD) was protective against clinically-relevant postoperative pancreatic fistula (CR-POPF) compared to open pancreaticoduodenectomy (OPD). We sought to compare the national rate of CR-POPF by approach. Methods: Procedure-targeted pancreatectomy Participant User Data File was queried from 2014 to 2017 for all patients undergoing pancreaticoduodenectomy. A modified fistula risk score was calculated and patients were stratified into risk categories. Multivariate logistic regression and propensity score matching was used. Results: The rate of CR-POPF (15.6% vs. 11.9%; p = 0.026) was higher in OPD compared to RPD. On subgroup analysis, OPD had higher CR-POPF in high risk patients (32.9% vs. 19.4%; p = 0.007). On multivariable analysis OPD was a predictor of increased CR-POPF (Odds Ratio [OR] = 1.61 [1.15-2.25]; p = 0.005). Other operative factors associated with increased CR-POPF included soft pancreatic texture (OR = 2.65 [2.27-3.09]; p < 0.001) and concomitant visceral resection (OR = 1.41 [1.03-1.93]; p = 0.031). Increased duct size (reference < 3 mm) was predictive of decreased CR-POPF: 3-6 mm (OR = 0.70 [0.61-0.81]; p < 0.001) and > 6 mm (OR = 0.47 [0.37-0.60]; p < 0.001). Following propensity score matching, RPD continued to be protective against the occurrence of CR-POPF (OR = 1.54 [1.09-2.17]; p = 0.013). Conclusions: This is the largest multicenter study to evaluate the impact of RPD on POPF. It suggests that RPD can be protective against POPF, especially for high risk patients.