A Machine Learning Approach to Predict Postoperative Pancreatic Fistula After Pancreaticoduodenectomy Using Only Preoperatively Known Data

Amir Ashraf Ganjouei; Fernanda Romero-Hernandez; Jaeyun Jane Wang; Megan Casey; Willow Frye; Daniel Hoffman; Kenzo Hirose; Eric Nakakura; Carlos Corvera; Ajay V Maker; Kimberly S Kirkwood; Adnan Alseidi; Mohamed A Adam

doi:10.1245/s10434-023-14041-x

A Machine Learning Approach to Predict Postoperative Pancreatic Fistula After Pancreaticoduodenectomy Using Only Preoperatively Known Data

Ann Surg Oncol. 2023 Nov;30(12):7738-7747. doi: 10.1245/s10434-023-14041-x. Epub 2023 Aug 7.

Affiliations

¹ Department of Surgery, University of California, San Francisco, USA.
² School of Medicine, University of California, San Francisco, USA.
³ Division of Surgical Oncology, Department of Surgery, University of California, San Francisco, CA, USA.
⁴ Division of Surgical Oncology, Department of Surgery, University of California, San Francisco, CA, USA. mohamed.adam@ucsf.edu.

PMID: 37550449
DOI: 10.1245/s10434-023-14041-x

Abstract

Background: Clinically-relevant postoperative pancreatic fistula (CR-POPF) following pancreaticoduodenectomy (PD) is a major postoperative complication and the primary determinant of surgical outcomes. However, the majority of current risk calculators utilize intraoperative and postoperative variables, limiting their utility in the preoperative setting. Therefore, we aimed to develop a user-friendly risk calculator to predict CR-POPF following PD using state-of-the-art machine learning (ML) algorithms and only preoperatively known variables.

Methods: Adult patients undergoing elective PD for non-metastatic pancreatic cancer were identified from the ACS-NSQIP targeted pancreatectomy dataset (2014-2019). The primary endpoint was development of CR-POPF (grade B or C). Secondary endpoints included discharge to facility, 30-day mortality, and a composite of overall and significant complications. Four models (logistic regression, neural network, random forest, and XGBoost) were trained, validated and a user-friendly risk calculator was then developed.

Results: Of the 8666 patients who underwent elective PD, 13% (n = 1160) developed CR-POPF. XGBoost was the best performing model (AUC = 0.72), and the top five preoperative variables associated with CR-POPF were non-adenocarcinoma histology, lack of neoadjuvant chemotherapy, pancreatic duct size less than 3 mm, higher BMI, and higher preoperative serum creatinine. Model performance for 30-day mortality, discharge to a facility, and overall and significant complications ranged from AUC 0.62-0.78.

Conclusions: In this study, we developed and validated an ML model using only preoperatively known variables to predict CR-POPF following PD. The risk calculator can be used in the preoperative setting to inform clinical decision-making and patient counseling.

Keywords: Artificial intelligence; Machine learning; Pancreatic fistula; Pancreaticoduodenectomy; Personalized medicine.