Prediction of neurologic deterioration based on support vector machine algorithms and serum osmolarity equations
Prediction of neurologic deterioration based on support vector machine algorithms and serum osmolarity equations
复制标题
DOI：
10.1002/brb3.1023
复制
发表时间：
2018-07-01
影响因子：
3.1
通讯作者：
Zhao, Jing
中科院分区：
文献类型：
--
作者：
Lin, Jixian;Jiang, Aihua;Zhao, Jing
目的：入院时脱水与神经功能恶化（ND）相关。我们的研究的主要目的是使用支持向量机（SVM）算法来确定一个ND预后模型，脱水equations.Methods的基础上：本研究共包括382例急性缺血性中风住院患者。记录以下参数：年龄、性别、实验室检查值（血清钠、钾、氯、葡萄糖和尿素）和血管危险因素数据。使用受试者工作特征（ROC）曲线分析来评估BUN/Cr比值以及预测ND的38个方程中的每一个的区分性能。我们使用Boruta算法进行特征选择。在优化支持向量机核参数后，我们建立了一个支持向量机模型来预测ND，并使用测试集来获得预测值，以评估模型的准确性。结果：在总共382例急性缺血性脑卒中患者中，有102例（26.7%）发生ND。在所有患者中，BUN/Cr比值和38个方程中的每一个都是ND的显著预测因子。方程20 [1.86 x Na+ +葡萄糖+尿素+9]产生了ROC曲线下面积最大，并且在预后性能方面表现最佳（截止值为284.49 mM，灵敏度为94.12%，特异性为61.43%）。方程32预测了不同人群中的卒中后ND，在老年人和年轻人中效果良好（临界值为297.08 mM，灵敏度为93.14%，特异性为60.00%）。使用Boruta算法进行特征选择，将条件中的变量数量从18个减少到5个。试验样本对SVM预测模型的特异性从44.1%提高到89.4%，AUC从0.700提高到0.927。结论：SVM算法可用于建立脱水相关性神经营养不良的预测模型，具有良好的分类效果。
Objective: Dehydration on admission is correlated with neurological deterioration (ND). The primary objective of our study was to use support vector machine (SVM) algorithms to identify an ND prognostic model, based on dehydration equations.Methods: This study included a total of 382 patients hospitalized with acute ischemic stroke. The following parameters were recorded: age, sex, laboratory values (serum sodium, potassium, chlorinum, glucose, and urea), and vascular risk factor data. Receiver operating characteristic (ROC) curve analysis was used to evaluate the discriminative performance of the BUN/Cr ratio as well as each of 38 equations for predicting ND. We used the Boruta algorithm for feature selection. After optimizing the SVM kernel parameters, we built an SVM model to predict ND and used the test set to obtain predictive values for assessing model accuracy.Results: In total, 102 of 382 patients (26.7%) with acute ischemic stroke developed ND. In all patients, the BUN/Cr ratio and each of 38 equations were significant predictors of ND. Equation 20 [1.86 x Na+ + glucose + urea + 9] yielded the maximum area under the ROC curve, and faired best in terms of prognostic performance (a cutoff value of 284.49 mM yielded a sensitivity of 94.12% and specificity of 61.43%). Equation 32 predicted ND poststroke across population groups, and worked well in older as well as young adults; (a cutoff value of 297.08 mM yielded a sensitivity of 93.14% and specificity of 60.00%). Feature selection by the Boruta algorithm was used to decrease the number of variables from 18 to 5 in the condition. The specificity of test samples for the SVM prediction model increased from 44.1% to 89.4%, and the AUC increased from 0.700 to 0.927.Conclusions: SVM algorithms can be used to establish a prediction model for dehydration-associated ND, with good classification results.