Comparison of Conventional Logistic Regression and Machine Learning Methods for Predicting Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage: A Multicentric Observational Cohort Study.
Comparison of Conventional Logistic Regression and Machine Learning Methods for Predicting Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage: A Multicentric Observational Cohort Study.
复制标题
DOI：
10.3389/fnagi.2022.857521
复制
发表时间：
2022
影响因子：
4.8
通讯作者：
中科院分区：
文献类型：
--
作者：
及时准确地预测迟发性脑缺血是改善蛛网膜下腔出血患者预后的关键。机器学习（ML）算法越来越被认为具有比传统逻辑回归（LR）更高的预测能力。本研究旨在构建LR和ML模型，并比较其对蛛网膜下腔出血（aSAH）后迟发性脑缺血（DCI）的预测能力。这是一项多中心、回顾性、观察性队列研究，入组了中国5家医院的蛛网膜下腔出血患者。共前瞻性入组了404例aSAH患者。我们按照75- 25%的比例将患者随机分为训练组（N = 303）和验证组（N = 101）。一个LR和六个流行的ML算法被用来构建模型。使用受试者工作特征曲线下面积（AUC）、准确度、平衡准确度、混淆矩阵、灵敏度、特异性、校准曲线和Hosmer-Lemeshow检验来评估和比较模型性能。最后，我们计算了每个特征的重要性。共有112例（27.7%）患者发生了DCI。我们的结果表明，AUC值为0.824的传统LR验证队列中的AUC为0.792，优于k-最近邻、决策树、支持向量机和极端梯度增强模型（95%CI：0.73-0.91（95%CI：0.68-0.9，P = 0.46）、0.675（95%CI：0.56-0.79，P < 0.01）、0.677（95%CI：0.57-0.77，P < 0.01）和0.78（95%CI：0.68-0.87，P = 0.50）。而随机森林模型和人工神经网络模型的AUC（0.858，95%CI：0.78-0.93，P = 0.26）相同，优于LR模型。RF的准确性和平衡准确性分别比后者高20.8%和11%，并且RF在验证队列中也显示出良好的校准（Hosmer-Lemeshow：P = 0.203）。我们发现蛛网膜下腔出血的CT值、白细胞计数、中性粒细胞计数、脑水肿的CT值和单核细胞计数是RF模型中预测DCI的五个最重要的特征。然后，我们开发了一个基于重要特征的在线预测工具（https：//dynamic-nomogram.shinyapps.io/DynNomapp-DCI/），以精确计算DCI风险。在这项多中心研究中，我们发现几种ML方法，特别是RF，优于传统LR。此外，开发了基于RF模型的在线预测工具，以识别SAH后DCI的高风险患者，并促进及时干预。http://www.chictr.org.cn，唯一标识符：ChiCTR 2100044448。
Timely and accurate prediction of delayed cerebral ischemia is critical for improving the prognosis of patients with aneurysmal subarachnoid hemorrhage. Machine learning (ML) algorithms are increasingly regarded as having a higher prediction power than conventional logistic regression (LR). This study aims to construct LR and ML models and compare their prediction power on delayed cerebral ischemia (DCI) after aneurysmal subarachnoid hemorrhage (aSAH). This was a multicenter, retrospective, observational cohort study that enrolled patients with aneurysmal subarachnoid hemorrhage from five hospitals in China. A total of 404 aSAH patients were prospectively enrolled. We randomly divided the patients into training (N = 303) and validation cohorts (N = 101) according to a ratio of 75–25%. One LR and six popular ML algorithms were used to construct models. The area under the receiver operating characteristic curve (AUC), accuracy, balanced accuracy, confusion matrix, sensitivity, specificity, calibration curve, and Hosmer–Lemeshow test were used to assess and compare the model performance. Finally, we calculated each feature of importance. A total of 112 (27.7%) patients developed DCI. Our results showed that conventional LR with an AUC value of 0.824 (95%CI: 0.73–0.91) in the validation cohort outperformed k-nearest neighbor, decision tree, support vector machine, and extreme gradient boosting model with the AUCs of 0.792 (95%CI: 0.68–0.9, P = 0.46), 0.675 (95%CI: 0.56–0.79, P < 0.01), 0.677 (95%CI: 0.57–0.77, P < 0.01), and 0.78 (95%CI: 0.68–0.87, P = 0.50). However, random forest (RF) and artificial neural network model with the same AUC (0.858, 95%CI: 0.78–0.93, P = 0.26) were better than the LR. The accuracy and the balanced accuracy of the RF were 20.8% and 11% higher than the latter, and the RF also showed good calibration in the validation cohort (Hosmer-Lemeshow: P = 0.203). We found that the CT value of subarachnoid hemorrhage, WBC count, neutrophil count, CT value of cerebral edema, and monocyte count were the five most important features for DCI prediction in the RF model. We then developed an online prediction tool (https://dynamic-nomogram.shinyapps.io/DynNomapp-DCI/) based on important features to calculate DCI risk precisely. In this multicenter study, we found that several ML methods, particularly RF, outperformed conventional LR. Furthermore, an online prediction tool based on the RF model was developed to identify patients at high risk for DCI after SAH and facilitate timely interventions. http://www.chictr.org.cn, Unique identifier: ChiCTR2100044448.