Department of Neurosurgery, State University of New York Upstate Medical University, Syracuse, NY, USA.
Department of Neurosurgery, State University of New York Upstate Medical University, Syracuse, NY, USA.
J Stroke Cerebrovasc Dis. 2023 Mar;32(3):106989. doi: 10.1016/j.jstrokecerebrovasdis.2023.106989. Epub 2023 Jan 16.
Prediction of malignant middle cerebral artery infarction (MMI) could identify patients for early intervention. We trained and internally validated a ML model that predicts MMI following mechanical thrombectomy (MT) for ACLVO.
All patients who underwent MT for ACLVO between 2015 - 2021 at a single institution were reviewed. Data was divided into 80% training and 20% test sets. 10 models were evaluated on the training set. The top 3 models underwent hyperparameter tuning using grid search with nested 5-fold CV to optimize the area under the receiver operating curve (AUROC). Tuned models were evaluated on the test set and compared to logistic regression.
A total of 381 patients met the inclusion criteria. There were 50 (13.1%) patients who developed MMI. Out of the 10 ML models screened on the training set, the top 3 performing were neural network (median AUROC 0.78, IQR 0.72 - 0.83), support vector machine ([SVM] median AUROC 0.77, IQR 0.72 - 0.83), and random forest (median AUROC 0.75, IQR 0.68 - 0.81). On the test set, random forest (median AUROC 0.78, IQR 0.73 - 0.83) and neural network (median AUROC 0.78, IQR 0.73 - 0.83) were the top performing models, followed by SVM (median AUROC 0.77, IQR 0.70 - 0.83). These scores were significantly better than those for logistic regression (AUROC 0.72, IQR 0.66 - 0.78), individual risk factors, and the Malignant Brain Edema score (p < 0.001 for all).
ML models predicted MMI with good discriminative ability. They outperformed standard statistical techniques and individual risk factors.
预测恶性大脑中动脉梗死（MMI）可以识别需要早期干预的患者。我们训练并内部验证了一个机器学习模型，用于预测接受机械血栓切除术（MT）治疗急性大脑中动脉闭塞性病变（ACLVO）后的 MMI。
回顾了 2015 年至 2021 年在一家机构接受 MT 治疗 ACLVO 的所有患者。数据分为 80%的训练集和 20%的测试集。在训练集上评估了 10 个模型。使用嵌套 5 倍交叉验证的网格搜索对前 3 个模型进行超参数调整，以优化接收者操作特征曲线（AUROC）下的面积。在测试集上评估调整后的模型，并与逻辑回归进行比较。
共有 381 名患者符合纳入标准。其中 50 名（13.1%）患者发生 MMI。在训练集上筛选的 10 个 ML 模型中，表现最好的前 3 个是神经网络（中位数 AUROC 为 0.78，IQR 为 0.72-0.83）、支持向量机（[SVM]中位数 AUROC 为 0.77，IQR 为 0.72-0.83）和随机森林（中位数 AUROC 为 0.75，IQR 为 0.68-0.81）。在测试集上，随机森林（中位数 AUROC 为 0.78，IQR 为 0.73-0.83）和神经网络（中位数 AUROC 为 0.78，IQR 为 0.73-0.83）表现最好，其次是 SVM（中位数 AUROC 为 0.77，IQR 为 0.70-0.83）。这些分数明显优于逻辑回归（AUROC 为 0.72，IQR 为 0.66-0.78）、单个危险因素和恶性脑水肿评分（所有 p<0.001）。
机器学习模型具有良好的判别能力，可以预测 MMI。它们优于标准统计技术和单个危险因素。
