Peng S Y, Wu K C, Wang J J, Chuang J H, Peng S K, Lai Y H
Department of Anesthesiology, Taichung Veterans General Hospital, Taiwan, Republic of China.
Br J Anaesth. 2007 Jan;98(1):60-5. doi: 10.1093/bja/ael282. Epub 2006 Oct 25.
Several medications have proved to be useful in preventing postoperative nausea and vomiting (PONV). However, routine antiemetic prophylaxis is not cost-effective. We evaluated the accuracy and discriminating power of an artificial neural network (ANN) to predict PONV.
We analysed data from 1086 in-patients who underwent various surgical procedures under general anaesthesia without antiemetic prophylaxis. Predictors used for ANN training were selected by computing the value of chi(2) statistic and information gain with respect to PONV. The configuration of the ANN was chosen by using a software tool. Then the training of the ANN was performed based on data from a training set (n=656). Testing validation was performed with the remaining patients (n=430) whose outcome regarding PONV was unknown to the ANN. Area under the receiver operating characteristic (ROC) curves were used to quantify predictive performance. ANN performance was compared with those of the Naïve Bayesian classifier model, logistic regression model, simplified Apfel score and Koivuranta score.
ANN accuracy was 83.3%, sensitivity 77.9% and specificity 85.0% in predicting PONV. The areas under the ROC curve follow: ANN, 0.814 (0.774-0.850); Naïve Bayesian classifier, 0.570 (0.522-0.617); logistic regression, 0.669 (0.623-0.714); Koivuranta score, 0.626 (0.578-0.672); simplified Apfel score, 0.624 (0.576-0.670). ANN discriminatory power was superior to those of the other predicting models (P<0.05).
The ANN provided the best predictive performance among all tested models.
多种药物已被证明对预防术后恶心和呕吐（PONV）有用。然而，常规的止吐预防并不具有成本效益。我们评估了人工神经网络（ANN）预测PONV的准确性和辨别能力。
我们分析了1086例在全身麻醉下接受各种外科手术且未进行止吐预防的住院患者的数据。通过计算卡方统计量的值和关于PONV的信息增益来选择用于ANN训练的预测因子。使用软件工具选择ANN的配置。然后基于训练集（n = 656）的数据对ANN进行训练。对其余患者（n = 430）进行测试验证，这些患者的PONV结果对于ANN来说是未知的。使用受试者操作特征（ROC）曲线下的面积来量化预测性能。将ANN的性能与朴素贝叶斯分类器模型、逻辑回归模型、简化的阿佩尔评分和科伊武兰塔评分的性能进行比较。
ANN在预测PONV方面的准确率为83.3%，灵敏度为77.9%，特异性为85.0%。ROC曲线下的面积如下：ANN为0.814（0.774 - 0.850）；朴素贝叶斯分类器为0.570（0.522 - 0.617）；逻辑回归为0.669（0.623 - 0.714）；科伊武兰塔评分为0.626（0.578 - 0.672）；简化的阿佩尔评分为0.624（0.576 - 0.670）。ANN的辨别能力优于其他预测模型（P<0.05）。
在所有测试模型中，ANN提供了最佳的预测性能。
