Published online Aug 14, 2020. doi: 10.3748/wjg.v26.i30.4453
Peer-review started: April 22, 2020
First decision: April 29, 2020
Revised: July 13, 2020
Accepted: July 30, 2020
Article in press: July 30, 2020
Published online: August 14, 2020
Despite advancements in operative technique and improvements in postoperative managements, postoperative pancreatic fistula (POPF) is a life-threatening complication following pancreatoduodenectomy (PD). Artificial intelligence (AI) technology is being actively used in the medical field, but few studies have reported applying it to outcomes after PD.
There are some reports to predict POPF preoperatively or intraoperatively, but the accuracy of those is questionable. Compared with established POPF risk prediction methods, we expect that our ML algorithms can better predict the POPF risk correctly.
This study aimed to develop a risk prediction platform for POPF with single center dataset using an AI model.
A total of 38 variables from 1769 patients who underwent PD from 2007 to 2016 at Samsung Medical Center were inserted into AI-driven algorithms. The algorithms tested to make the risk prediction platform were random forest (RF) and a neural network (NN) with or without recursive feature elimination (RFE). These algorithms can better incorporate multiple risk factors and account for more nuanced relationships between the risk factors and POPF. The median imputation method was used for missing values.
The number of POPFs was 221 (12.5%) according to the International Study Group of Pancreatic Fistula definition 2016. The maximal AUC using NN with RFE was 0.74. Sixteen 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 decompression. We developed a web-based POPF prediction platform available at https://popfrisk.smchbp.org.
This study is the first to predict POPF with multiple risk factors using AI. This platform is reliable (AUC 0.74), so it could be used to select patients who need especially intense therapy and to preoperatively establish an effective treatment strategy.
This study developed a risk prediction platform for POPF with single center dataset using an AI model. The follow-up study will be conducted by performing an external validation on patients in multiple institutions. Also, future prospective studies could stratify treatments based on the outcome of this platform and provide comprehensive treatment algorithms.