External validation and comparison of the original, alternative and updated-alternative fistula risk scores for the prediction of postoperative pancreatic fistula after pancreatoduodenectomy

Abstract

Background: Many postoperative pancreatic fistula (POPF) predictions models were developed and validated in western populations. Direct use of these models in the large Indian/Asian population, however, requires proper validation.

Objective: To validate the original, alternative and updated alternative fistula risk score (FRS) models.

Methods: A validation study was performed in consecutive patients undergoing pancreatoduodenectomy (PD) from January 2011 to March 2018. The area under the receiver operating curve (ROC) and calibration plots were used to assess the performance of original-FRS (o-FRS), alternative FRS (a-FRS) and updated alternative FRS (ua-FRS) models.

Results: This cohort consisted of 825 patients of which 66% were males with a median age of 55 years and mean body mass index of 22.6. The majority of tumors (61.8%) were of periampullary origin. Clinically relevant POPF was observed in 16.8% patients. Area under curve (AUC) of ROC for the o-FRS was 0.65, 0.69 for a-FRS and 0.70 for ua-FRS, respectively (p = 0.006).

Conclusions: In this large Indian cohort of predominantly periampullary tumors, the ua-FRS performed better than the a-FRS and o-FRS, although differences were small. Since the AUC value of the ua-FRS is at the accepted threshold there might be room for improvement for a FRS.

Keywords: POPF; Prediction model; Whipple.