Establishment of artificial neural network predication model of postoperative fatigue syndrome in patients with painless colonoscopy / 中华麻醉学杂志

ABSTRACT

Objective:To establish an artificial neural network (ANN) model for predication of postoperative fatigue syndrome (POFS) in patients with painless colonoscopy.Methods:The out-patients received painless colonoscopy from October 2016 to February 2017 were selected.A total of 38 factors influencing POFS during perioperative period were collected.Christensen postoperative fatigue score was performed when resuscitation achieved the standard.The patients were divided into POFS group (Christensen score≥3) and non-POFS group (Christensen score<3) according to whether POFS occurred.Logistic regression predication model and ANN predication model were established and tested, respectively.The areas under the receiver operating characteristic curve were used to compare the efficacy of the two models for predication of POFS.Results:The error rates of the ANN prediction model training set and test set were 23.1% and 28.1%, respectively.The sensitivity and specificity of the training set were 88.6% and 52.7%, respectively.The sensitivity and specificity of the test set were 91.6% and 71.1%, respectively.The areas under the curves of logistic regression predication model and ANN predication model were 0.698 and 0.776, respectively.Conclusion:ANN prediction model has been successfully established, which provides better efficacy than logistic regression predication model for predication of POFS in patients with painless colonoscopy .