Risk prediction platform for pancreatic fistula after pancreatoduodenectomy using artificial intelligence

作     者：In Woong Han Kyeongwon Cho Youngju Ryu Sang Hyun Shin Jin Seok Heo Dong Wook Choi Myung Jin Chung Oh Chul Kwon Baek Hwan Cho 

作者机构：Department of SurgerySamsung Medical CenterSungkyunkwan University School of MedicineSeoul 06351South Korea Medical Artificial Intelligence Research CenterDepartment of Medical Device Management and ResearchSAIHSTSamsung Medical CenterSungkyunkwan University School of MedicineSeoul 06351South Korea Department of RadiologySamsung Medical CenterSungkyunkwan University School of MedicineSeoul 06351South Korea Artificial Intelligence Research CenterMedical DataBase IncorporatedSeoul 06048South Korea 

出 版 物：《World Journal of Gastroenterology》 (世界胃肠病学杂志（英文版）)

年 卷 期：2020年第26卷第30期

页      面：4453-4464页

核心收录：

学科分类：1002[医学-临床医学] 100210[医学-外科学(含：普外、骨外、泌尿外、胸心外、神外、整形、烧伤、野战外)] 10[医学] 

基　　金：Supported by the National Research Foundation of Korea grant funded by the Korea government(Ministry of Science and ICT),No.NRF-2019R1F1A1042156 and the Bio&Medical Technology Development Program,No.NRF-2017M3A9E1064784 

主　　题：Postoperative pancreatic fistula Pancreatoduodenectomy Neural networks Recursive feature elimination 

摘      要：BACKGROUND Despite advancements in operative technique and improvements in postoperative managements,postoperative pancreatic fistula(POPF)is a life-threatening complication following pancreatoduodenectomy(PD).There are some reports to predict POPF preoperatively or intraoperatively,but the accuracy of those is *** intelligence(AI)technology is being actively used in the medical field,but few studies have reported applying it to outcomes after *** To develop a risk prediction platform for POPF using an AI *** Medical records were reviewed from 1769 patients at Samsung Medical Center who underwent PD from 2007 to 2016.A total of 38 variables were inserted into AI-driven *** algorithms tested to make the risk prediction platform were random forest(RF)and a neural network(NN)with or without recursive feature elimination(RFE).The median imputation method was used for missing *** area under the curve(AUC)was calculated to examine the discriminative power of algorithm for POPF *** The number of POPFs was 221(12.5%)according to the International Study Group of Pancreatic Fistula definition *** median imputation,AUCs using 38 variables were 0.68±0.02 with RF and 0.71±0.02 with *** maximal AUC using NN with RFE was *** risk factors for POPF were identified by AI algorithm:Pancreatic duct diameter,body mass index,preoperative serum albumin,lipase level,amount of intraoperative fluid infusion,age,platelet count,extrapancreatic location of tumor,combined venous resection,co-existing pancreatitis,neoadjuvant radiotherapy,American Society of Anesthesiologists’score,sex,soft texture of the pancreas,underlying heart disease,and preoperative endoscopic biliary *** developed a web-based POPF prediction platform,and this application is freely available at http://*** This study is the first to predict POPF with multiple risk factors using *** platform is reli