Gao Weiwei, Zhu Renjing, She Jingjing, Huang Rong, Cai Lijuan, Jin Shouyue, Lin Yanping, Lin Jianzhong, Chen Xingyu, Chen Liangyi
Department of Neurology, Zhongshan Hospital of Xiamen University, School of Medicine, National Advanced Center for Stroke, Xiamen Key Subspecialty of Neurointerventional Radiology, Xiamen University, Xiamen, China.
Xiamen Clinical Research Center for Cerebrovascular Diseases, Xiamen, China.
Front Neurol. 2025 Apr 25;16:1567348. doi: 10.3389/fneur.2025.1567348. eCollection 2025.
Early differentiation of stroke etiology in acute large vessel occlusion stroke (LVOS) is crucial for optimizing endovascular treatment strategies. This study aimed to develop and validate a prediction model for pre-procedural etiological differentiation based on admission laboratory parameters.
We conducted a retrospective cohort study at a comprehensive stroke center, enrolling consecutive patients with acute LVOS who underwent endovascular treatment between January 2018 and October 2024. The study cohort ( = 415) was split into training ( = 291) and validation ( = 124) sets using a 7:3 ratio. We applied machine learning techniques-the Boruta algorithm followed by least absolute shrinkage and selection operator regression-for variable selection. The final predictive model was constructed using multivariable logistic regression. Model performance was evaluated through the area under the receiver operating characteristic curve (AUC), calibration plots, and decision curve analysis. We then developed a web-based calculator to facilitate clinical implementation.
Of 415 enrolled patients, 199 (48.0%) had cardioembolism (CE). The final model incorporated six independent predictors: age [adjusted odds ratio (aOR) 1.03], male sex (aOR 0.35), white blood cell count (aOR 0.86), platelet-large cell ratio (aOR 1.06), aspartate aminotransferase (aOR 1.02), and non-high-density lipoprotein cholesterol (aOR 0.75). The model demonstrated good discriminatory ability in both the training set (AUC = 0.802) and the validation set (AUC = 0.784). Decision curve analysis demonstrated consistent clinical benefit across threshold probabilities of 20%-75%.
We developed and internally validated a practical model using routine admission laboratory parameters to differentiate between CE and large artery atherosclerosis in acute LVOS. This readily implementable tool could aid in preoperative decision-making for endovascular intervention.
急性大血管闭塞性卒中（LVOS）病因的早期鉴别对于优化血管内治疗策略至关重要。本研究旨在基于入院实验室参数开发并验证一种用于术前病因鉴别的预测模型。
我们在一家综合卒中中心进行了一项回顾性队列研究，纳入2018年1月至2024年10月期间连续接受血管内治疗的急性LVOS患者。研究队列（n = 415）以7:3的比例分为训练集（n = 291）和验证集（n = 124）。我们应用机器学习技术——先使用博鲁塔算法，再使用最小绝对收缩和选择算子回归——进行变量选择。最终的预测模型采用多变量逻辑回归构建。通过受试者操作特征曲线下面积（AUC）、校准图和决策曲线分析评估模型性能。然后我们开发了一个基于网络的计算器以促进临床应用。
在415例纳入患者中，199例（48.0%）为心源性栓塞（CE）。最终模型纳入了六个独立预测因素：年龄[调整优势比（aOR）1.03]、男性（aOR 0.35）、白细胞计数（aOR 0.86）、血小板大细胞比例（aOR 1.06）、天冬氨酸转氨酶（aOR 1.02）和非高密度脂蛋白胆固醇（aOR 0.75）。该模型在训练集（AUC = 0.802）和验证集（AUC = 0.784）中均表现出良好的鉴别能力。决策曲线分析表明，在20% - 75%的阈值概率范围内均有一致的临床获益。
我们开发并在内部验证了一个实用模型，该模型利用常规入院实验室参数区分急性LVOS中的CE和大动脉粥样硬化。这个易于实施的工具可有助于血管内介入治疗的术前决策。
