Machine learning approach in diagnosis and risk factors detection of pancreatic fistula

Abstract

Abstract Purpose. The aim of the study is to develop a predictive ML model of development of postoperative pancreatic fistula and biochemical leak and to detect the main risk factors of the complications. Methods. We performed a single-centre retrospective clinical study. 150 patients, who underwent pancreatoduodenal resection in FSBI NMRRC, were included in the study. We developed CatBoost ML models, basing on the 1 and 3–5 postoperative days data. Binary model classes were no fistula and biochemical leak or fistula B/C. 3-dimentional model distinguished no fistula, biochemical leak and fistula B/C. The risk factors of pancreatic fistula were evaluated with model parameter “importance” and Kendall correlation, p < 0.05. Results. We detected significant positive correlation of blood and drain amylase level increase in association with biochemical leak and pancreatic fistula B/C. Binary model, roc auc 71%, detected the main risk factors of all the fistulas on the first postoperative day: tumor vascular invasion, age and BMI. Risk factors of fistula B/C were BMI, age, tumor volume and vascular invasion, the 3-dimensional model roc auc 70%. Basing on the 3–5 days data, binary model risk factors were blood and drain amylase levels, blood leukocytes, roc auc 86%. Fistula B/C risk factors were the same, the 3-dimensional model roc auc 75%. BMI and age were also important. Conclusion. We developed sufficient quality ML models of postoperative pancreatic fistulas. Blood and drain amylase level increase were the major risk factors of fistula B/C. Young age and high tumor volume were common factors of fistulas development.