From the Department of Radiology, The First Affiliated Hospital of Nanjing Medical University.
Department of Interventional Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu Province.
J Comput Assist Tomogr. 2022;46(5):775-780. doi: 10.1097/RCT.0000000000001341. Epub 2022 Jun 3.
The aim of this study was to evaluate the performance of machine learning (ML) algorithms in predicting the functional outcome of mechanical thrombectomy (MT) outside the 6-hour therapeutic time window in patients with acute ischemic stroke (AIS).
One hundred seventy-seven consecutive AIS patients with large-vessel occlusion in the anterior circulation who underwent MT in the extended time window were enrolled. Clinical, neuroimaging, and treatment variables that could be obtained quickly in the real-world emergency settings were collected. Four machine learning algorithms (random forests, regularized logistic regression, support vector machine, and naive Bayes) were used to predict good outcomes (modified Rankin Scale scores of 0-2) at 90 days by using (1) only variables at admission and (2) both baseline and treatment variables. The performance of each model was evaluated using receiver operating characteristic (ROC) curve analysis. Feature importance was ranked using random forest algorithms.
Eighty patients (45.2%) had a favorable 90-day outcome. Machine learning models including baseline clinical and neuroimaging characteristics predicted 90-day modified Rankin Scale with an area under the ROC curve of 0.80-0.81, sensitivity of 0.60-0.71 and specificity of 0.71-0.76. Further inclusion the treatment variables significantly improved the predictive performance (mean area under the ROC curve, 0.89-0.90; sensitivity, 0.77-0.85; specificity, 0.75-0.87). The most important characteristics for predicting 90-day outcomes were age, hypoperfusion intensity ratio at admission, and National Institutes of Health Stroke Scale score at 24 hours after MT.
Machine learning algorithms may facilitate prediction of 90-day functional outcomes in AIS patients with an extended therapeutic time window.
本研究旨在评估机器学习（ML）算法在预测急性缺血性卒中（AIS）患者机械取栓（MT）治疗时间窗延长至 6 小时后的功能结局的表现。
共纳入 177 例前循环大血管闭塞的 AIS 患者，这些患者在延长的时间窗内行 MT。收集了可在真实世界急救环境中快速获得的临床、神经影像学和治疗变量。采用随机森林、正则逻辑回归、支持向量机和朴素贝叶斯 4 种机器学习算法，仅使用（1）入院时的变量和（2）基线和治疗时的变量，预测 90 天的良好结局（改良 Rankin 量表评分 0-2 分）。采用受试者工作特征（ROC）曲线分析评估各模型的性能。采用随机森林算法对特征重要性进行排序。
80 例（45.2%）患者 90 天预后良好。包括基线临床和神经影像学特征的机器学习模型预测 90 天改良 Rankin 量表评分的曲线下面积为 0.80-0.81，敏感性为 0.60-0.71，特异性为 0.71-0.76。进一步纳入治疗变量可显著提高预测性能（平均曲线下面积 0.89-0.90；敏感性 0.77-0.85；特异性 0.75-0.87）。预测 90 天结局的最重要特征是年龄、入院时低灌注强度比和 MT 后 24 小时的美国国立卫生研究院卒中量表评分。
机器学习算法可有助于预测治疗时间窗延长的 AIS 患者 90 天的功能结局。
