Karabacak Mert, Ozkara Burak Berksu, Faizy Tobias D, Hardigan Trevor, Heit Jeremy J, Lakhani Dhairya A, Margetis Konstantinos, Mocco J, Nael Kambiz, Wintermark Max, Yedavalli Vivek S
From the Departments of Neurosurgery (M.K., T.H., K.M., J.M.), Mount Sinai Health System, New York, New York.
Department of Radiology (B.B.O.), Mount Sinai Health System, New York, New York.
AJNR Am J Neuroradiol. 2025 Apr 2;46(4):725-732. doi: 10.3174/ajnr.A8547.
Distal medium vessel occlusions (DMVOs) are estimated to cause acute ischemic stroke in 25%-40% of cases. Prognostic models can inform patient counseling and research by enabling outcome predictions. However, models designed specifically for DMVOs are lacking.
This retrospective study developed a machine learning model to predict 90-day unfavorable outcome (defined as an mRS score of 3-6) in 164 patients with primary DMVO. A model developed with the TabPFN algorithm used selected clinical, laboratory, imaging, and treatment data with the least absolute shrinkage and selection operator feature selection. Performance was evaluated via 5-repeat 5-fold cross-validation. Model discrimination and calibration were evaluated. SHapley Additive Explanations (SHAP) identified influential features. A Web application deployed the model for individualized predictions.
The model achieved an area under the receiver operating characteristic curve of 0.815 (95% CI, 0.79-0.841) for predicting unfavorable outcome, demonstrating good discrimination, and a Brier score of 0.19 (95% CI, 0.177-0.202), demonstrating good calibration. SHAP analysis ranked admission NIHSS score, premorbid mRS, type of thrombectomy, modified TICI score, and history of malignancy as top predictors. The Web application enables individualized prognostication.
Our machine learning model demonstrated good discrimination and calibration for predicting 90-day unfavorable outcomes in primary DMVO strokes. This study demonstrates the potential for personalized prognostic counseling and research to support precision medicine in stroke care and recovery.
据估计，25%-40%的急性缺血性卒中病例由远端中等血管闭塞（DMVO）所致。预后模型可通过预测结果为患者咨询和研究提供参考。然而，专门针对DMVO设计的模型尚缺。
本回顾性研究开发了一种机器学习模型，用于预测164例原发性DMVO患者90天不良结局（定义为改良Rankin量表[mRS]评分3-6分）。使用TabPFN算法开发的模型采用了经最小绝对收缩和选择算子特征选择的选定临床、实验室、影像和治疗数据。通过5次重复5折交叉验证评估模型性能。对模型的辨别力和校准情况进行评估。SHapley值相加解释法（SHAP）确定了有影响的特征。通过一个网络应用程序部署该模型以进行个性化预测。
该模型预测不良结局的受试者工作特征曲线下面积为0.815（95%CI，0.79-0.841），显示出良好的辨别力；Brier评分为0.19（95%CI，0.177-0.202），显示出良好的校准。SHAP分析将入院时美国国立卫生研究院卒中量表（NIHSS）评分、病前mRS、血栓切除术类型、改良脑梗死溶栓分级（TICI）评分和恶性肿瘤病史列为首要预测因素。该网络应用程序可实现个性化预后评估。
我们的机器学习模型在预测原发性DMVO卒中90天不良结局方面显示出良好的辨别力和校准情况。本研究证明了个性化预后咨询和研究在支持卒中护理及康复精准医疗方面的潜力。
