首页|Third Military Medical University - Army Medical University Reports Findings in Cholangiocarcinoma (Machine Learning Model to Predict Early Recurrence in Patien ts with Perihilar Cholangiocarcinoma Planned Treatment with Curative Resection: A ...)
Third Military Medical University - Army Medical University Reports Findings in Cholangiocarcinoma (Machine Learning Model to Predict Early Recurrence in Patien ts with Perihilar Cholangiocarcinoma Planned Treatment with Curative Resection: A ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Oncology - Cholangioca rcinoma is the subject of a report. According to news reporting originating in C hongqing, People’s Republic of China, by NewsRx journalists, research stated, “E arly recurrence is the leading cause of death for patients with perihilar cholan giocarcinoma (pCCA) after surgery. Identifying high-risk patients preoperatively is important.” The news reporters obtained a quote from the research from Third Military Medica l University - Army Medical University, “This study aimed to construct a preoper ative prediction model for the early recurrence of pCCA patients planned treatme nt with curative resection. This study ultimately enrolled 400 pCCA patients aft er curative resection in five hospitals between 2013 and 2019. They were randoml y divided into training (n=300) and testing groups (n=100) at a ratio of 3:1. As sociated variables were identified via LASSO regression. Four machine learning m odels were constructed: support vector machine (SVM), random forest (RF), logist ic regression, and K-nearest neighbors (KNN). The predictive ability of the mode ls was evaluated via receiver operating characteristic (ROC) curves, precision-r ecall curve (PRC) curves, and decision curve analysis (DCA). KaplanMeier surviva l curves were drawn for the high/low-risk population. Five factors, CA19-9, tumo r size, total bilirubin, hepatic artery invasion, and portal vein invasion, were selected by LASSO regression. In both the training and testing groups, the ROC curve (AUC: 0.983 vs 0.952) and the PRC (0.981 vs 0.939) showed that RF was the best. The cutoff value for distinguishing high- and low-risk patients was 0.51. KM survival curves revealed that in both groups, there was a significant differe nce in RFS between high- and low-risk patients (P <0.001).”
ChongqingPeople’s Republic of ChinaA siaCancerCholangiocarcinomaCyborgsEmerging TechnologiesHealth and Medi cineMachine LearningOncologySurgery
NETL
NSTL
