Machine learning-based real-time prediction of duodenal stump leakage from gastrectomy in gastric cancer patients

Jae Hun Chung^1,2,3Yushin Kim⁴Dongjun Lee⁴Dongwon Lim¹Sun-Hwi Hwang^1,2,3Si-Hak Lee^1,2,3*Woohwan Jung^4*

• ¹School of Medicine, Pusan National University, Busan, Republic of Korea
• ²Pusan National University Yangsan Hospital, Yangsan, South Gyeongsang, Republic of Korea
• ³Biomedical Research Institute, Pusan National University Yangsan Hospital, Yangsan, South Gyeongsang, Republic of Korea
• ⁴Department of Applied Artificial Intelligence (Major in Bio Artificial Intelligence), Hanyang University, Ansansi, Republic of Korea

This study aimed to develop a machine learning (ML) model for real-time prediction of duodenal stump leakage (DSL) following gastrectomy in patients with gastric cancer (GC) using a comprehensive set of clinical variables to improve postoperative outcomes and monitoring efficiency.A retrospective analysis was conducted on 1107 patients with GC who underwent gastrectomy at Pusan National University Yangsan Hospital between 2019 and 2022. One hundred eighty-nine features were extracted from each patient record, including demographic data, preoperative comorbidities, and blood test outcomes from the subsequent seven postoperative days (POD). Six ML algorithms were evaluated: Logistic Regression (LR), Knearest neighbors (KNN), Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGB), and Neural Network (NN). The models predicted DSL occurrence preoperatively and on POD 1, 2, 3, 5, and 7. Performance was assessed using the Area Under the Receiver Operating Characteristic Curve (AUROC) and Recall@K.Among the 1107 patients, 29 developed DSL. XGB demonstrated the highest AUROC score (0.880), followed by RF (0.858), LR (0.823), SVM (0.819), NN (0.753), and KNN (0.726).The RF achieved the best Recall@K score of 0.643. Including additional POD features improved the predictive performance, with the AUROC value increasing to 0.879 on POD 7.The confidence scores of the model indicated that the DSL predictions became more reliable over time.The study concluded that ML models, notably the XGB algorithm, can effectively predict DSL in real-time using comprehensive clinical data, enhancing the clinical decision-making process for GC patients.