文献速递颈动脉与弓上血管

机器学习驱动颈动脉内膜切除术中清醒试验阳性预测因素

Predictive Factors Driving Positive Awake Test in Carotid Endarterectomy Using Machine Learning.
PubMed 文献 · Ann Vasc Surg · 2024-11-22

本研究基于2012年1月至2023年1月在区域麻醉下进行的颈动脉干预数据,采用病例对照设计,纳入216例患者(其中108例发生术中神经功能缺损),使用极端梯度提升(XGBoost)模型构建预测模型。模型曲线下面积为0.82,准确率0.75,精确率0.88,灵敏度0.59,F1分数0.71。高体重指数、对侧颈动脉狭窄及肢体轻瘫或瘫痪史为显著风险因素,术前血小板和血红蛋白水平升高与风险降低相关。

要点

  • 基于XGBoost的AI模型预测颈动脉内膜切除术中神经功能缺损的AUC为0.82。
  • 高BMI、对侧颈动脉狭窄及肢体轻瘫/瘫痪史是术中神经功能缺损的显著风险因素。
  • 术前血小板和血红蛋白水平升高与术中神经功能缺损风险降低相关。

核心结论

  • 该AI模型能精确预测颈动脉内膜切除术中的术中神经功能缺损,有助于对高危患者采取定制化干预并改善手术结局。
  • BMI、对侧狭窄及部分血液参数是關鍵预测因素,为颈动脉内膜切除术决策带来显著进步。
  • 需要在更大队列中进一步验证以推广临床应用。

研究设计与样本

  • 数据来自2012年1月至2023年1月在区域麻醉下进行的颈动脉干预。
  • 采用病例对照研究设计,选取发生术中神经功能缺损的患者及连续的无术中神经功能缺损对照。
  • 使用机器学习中的极端梯度提升(XGBoost)模型开发术中神经功能缺损预测模型,并与现有预测模型比较性能。
  • 采用Shapley Additive exPlanations(SHAP)分析进行模型解释。
  • 共纳入216例患者,其中108例在颈动脉内膜切除术中发生术中神经功能缺损。

主要发现

  • AI预测模型的曲线下面积为0.82,准确率为0.75,精确率为0.88,灵敏度为0.59,F1分数为0.71。
  • 高体重指数、对侧颈动脉狭窄增加及肢体轻瘫或瘫痪史是术中神经功能缺损的显著风险因素。
  • 术前血小板和血红蛋白水平升高与术中神经功能缺损风险降低相关。

临床怎么用

  • 作者认为该AI模型可精确预测颈动脉内膜切除术中的术中神经功能缺损,从而对高危患者采取定制化干预并最终改善手术结局。
  • 作者指出BMI、对侧狭窄及部分血液参数是关键预测因素,为颈动脉内膜切除术决策带来显著进步。
  • 作者强调需要在更大队列中进一步验证以推广临床应用。

局限性

  • 需要在更大队列中进一步验证以推广临床应用。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Positive neurologic awake testing during the carotid cross-clamping may be present in around 8% of patients undergoing carotid endarterectomy (CEA). The present work aimed to assess the accuracy of an artificial intelligence (AI)-powered risk calculator in predicting intraoperative neurologic deficits (INDs). METHODS: Data was collected from carotid interventions performed between January 2012 and January 2023 under regional anesthesia. Patients with IND were selected along with consecutive controls without IND in a case-control study design. A predictive model for IND was developed using machine learning, specifically Extreme Gradient Boosting (XGBoost) model, and its performance was assessed and compared to an existing predictive model. Shapley Additive exPlanations (SHAP) analysis was employed for the model interpretation. RESULTS: Among 216 patients, 108 experienced IND during CEA. The AI-based predictive model achieved a robust area under the curve of 0.82, with an accuracy of 0.75, precision of 0.88, sensitivity of 0.59, and F1Score of 0.71. High body mass index (BMI) increased contralateral carotid stenosis, and a history of limb paresis or plegia were significant IND risk factors. Elevated preoperative platelet and hemoglobin levels were associated with reduced IND risk. CONCLUSIONS: This AI model provides precise IND prediction in CEA, enabling tailored interventions for high-risk patients and ultimately improving surgical outcomes. BMI, contralateral stenosis, and selected blood parameters emerged as pivotal predictors, bringing significant advancements to decision-making in CEA procedures. Further validation in larger cohorts is essential for broader clinical implementation.

来源:Ann Vasc Surg,查看原文。版权归原作者所有。

引用

  1. Pereira-Macedo J, Pias AD, Duarte-Gamas L, et al. Predictive Factors Driving Positive Awake Test in Carotid Endarterectomy Using Machine Learning. Ann Vasc Surg. 2024. PMID: 39580028. doi:10.1016/j.avsg.2024.10.011

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。