Xu Jiangbao, Yuan Cuijie, Yu Guofeng, Li Hao, Dong Qiutong, Mao Dandan, Zhan Chengpeng, Yan Xinjiang
The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou, China.
Postgraduate Training Base Alliance of Wenzhou Medical University, Wenzhou, China.
Front Neurol. 2024 Oct 3;15:1419608. doi: 10.3389/fneur.2024.1419608. eCollection 2024.
The early prediction of cerebral edema changes in patients with spontaneous intracerebral hemorrhage (SICH) may facilitate earlier interventions and result in improved outcomes. This study aimed to develop and validate machine learning models to predict cerebral edema changes within 72 h, using readily available clinical parameters, and to identify relevant influencing factors.
An observational study was conducted between April 2021 and October 2023 at the Quzhou Affiliated Hospital of Wenzhou Medical University. After preprocessing the data, the study population was randomly divided into training and internal validation cohorts in a 7:3 ratio (training: = 150; validation: = 65). The most relevant variables were selected using Support Vector Machine Recursive Feature Elimination (SVM-RFE) and Least Absolute Shrinkage and Selection Operator (LASSO) algorithms. The predictive performance of random forest (RF), GDBT, linear regression (LR), and XGBoost models was evaluated using the area under the receiver operating characteristic curve (AUROC), precision-recall curve (AUPRC), accuracy, F1-score, precision, recall, sensitivity, and specificity. Feature importance was calculated, and the SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) methods were employed to explain the top-performing model.
A total of 84 (39.1%) patients developed cerebral edema changes. In the validation cohort, GDBT outperformed LR and RF, achieving an AUC of 0.654 (95% CI: 0.611-0.699) compared to LR of 0.578 (95% CI, 0.535-0.623, DeLong: = 0.197) and RF of 0.624 (95% CI, 0.588-0.687, DeLong: = 0.236). XGBoost also demonstrated similar performance with an AUC of 0.660 (95% CI, 0.611-0.711, DeLong: = 0.963). However, in the training set, GDBT still outperformed XGBoost, with an AUC of 0.603 ± 0.100 compared to XGBoost of 0.575 ± 0.096. SHAP analysis revealed that serum sodium, HDL, subarachnoid hemorrhage volume, sex, and left basal ganglia hemorrhage volume were the top five most important features for predicting cerebral edema changes in the GDBT model.
The GDBT model demonstrated the best performance in predicting 72-h changes in cerebral edema. It has the potential to assist clinicians in identifying high-risk patients and guiding clinical decision-making.
自发性脑出血（SICH）患者脑水肿变化的早期预测有助于早期干预并改善预后。本研究旨在开发并验证机器学习模型，以利用现成的临床参数预测72小时内的脑水肿变化，并确定相关影响因素。
2021年4月至2023年10月在温州医科大学附属衢州医院进行了一项观察性研究。对数据进行预处理后，研究人群以7:3的比例随机分为训练队列和内部验证队列（训练组：=150；验证组：=65）。使用支持向量机递归特征消除（SVM-RFE）和最小绝对收缩与选择算子（LASSO）算法选择最相关的变量。使用受试者操作特征曲线下面积（AUROC）、精确召回率曲线（AUPRC）、准确率、F1分数、精确率、召回率、敏感性和特异性评估随机森林（RF）、梯度提升决策树（GDBT）、线性回归（LR）和XGBoost模型的预测性能。计算特征重要性，并采用夏普利值附加解释（SHAP）和局部可解释模型无关解释（LIME）方法解释表现最佳的模型。
共有84例（39.1%）患者出现脑水肿变化。在验证队列中，GDBT的表现优于LR和RF，AUC为0.654（95%CI：0.611-0.699），而LR为0.578（95%CI，0.535-0.623，德龙检验：=0.197），RF为0.624（95%CI，0.588-0.687，德龙检验：=0.236）。XGBoost也表现出类似的性能，AUC为0.660（95%CI，0.611-0.711，德龙检验：=0.963）。然而，在训练集中，GDBT的表现仍优于XGBoost，AUC为0.603±0.100，而XGBoost为0.575±0.096。SHAP分析显示，血清钠、高密度脂蛋白、蛛网膜下腔出血量、性别和左侧基底节出血量是GDBT模型中预测脑水肿变化最重要的五个特征。
GDBT模型在预测脑水肿72小时变化方面表现最佳。它有可能帮助临床医生识别高危患者并指导临床决策。
