机器学习模型可识别动脉瘤破裂并找出相关临床特征
随机森林模型AUC最高为0.81,动脉瘤位置和大小是对模型贡献最大的特征,后交通、前交通和小脑后下动脉位置与破裂关联最强。
要点
- 随机森林模型区分破裂与未破裂动脉瘤的AUC达0.81。
- 动脉瘤位置和大小是预测破裂的最重要特征。
- 后交通、前交通和小脑后下动脉位置与破裂关联最强。
核心结论
- 机器学习模型能较准确区分破裂与未破裂颅内动脉瘤并识别与破裂相关的特征。
- 与既往研究一致,动脉瘤位置和大小与破裂关联最强。
研究设计与样本
- 回顾性队列研究,纳入2002–2018年本院血管影像检出的颅内动脉瘤患者。
- 完整数据共845个动脉瘤(615例患者),训练随机森林、线性支持向量机(SVM)和径向基核SVM三种模型。
主要发现
- 破裂动脉瘤309个(37%),平均大小6.51 mm,未破裂动脉瘤平均5.73 mm(P=0.02)。
- 破裂动脉瘤位于后循环的比例为20%,未破裂动脉瘤为11%(P<0.001)。
- 受试者工作特征曲线下面积:线性SVM为0.77,径向基核SVM为0.78,随机森林为0.81。
- 动脉瘤位置和大小是对模型贡献最大的两个特征。
- 后交通动脉、前交通动脉和小脑后下动脉位置与破裂关联最强,旁床突和大脑中动脉位置与未破裂状态关联最强。
临床怎么用
- 机器学习模型可作为辅助工具,结合动脉瘤位置和大小评估破裂风险。
- 对后交通、前交通和小脑后下动脉位置的动脉瘤应提高破裂风险警惕。
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: Machine learning (ML) has been increasingly used in medicine and neurosurgery. We sought to determine whether ML models can distinguish ruptured from unruptured aneurysms and identify features associated with rupture. METHODS: We performed a retrospective review of patients with intracranial aneurysms detected on vascular imaging at our institution between 2002 and 2018. The dataset was used to train 3 ML models (random forest, linear support vector machine [SVM], and radial basis function kernel SVM). Relative contributions of individual predictors were derived from the linear SVM model. RESULTS: Complete data were available for 845 aneurysms in 615 patients. Ruptured aneurysms (n = 309, 37%) were larger (mean 6.51 mm vs. 5.73 mm; P = 0.02) and more likely to be in the posterior circulation (20% vs. 11%; P < 0.001) than unruptured aneurysms. Area under the receiver operating curve was 0.77 for the linear SVM, 0.78 for the radial basis function kernel SVM models, and 0.81 for the random forest model. Aneurysm location and size were the 2 features that contributed most significantly to the model. Posterior communicating artery, anterior communicating artery, and posterior inferior cerebellar artery locations were most highly associated with rupture, whereas paraclinoid and middle cerebral artery locations had the strongest association with unruptured status. CONCLUSIONS: ML models are capable of accurately distinguishing ruptured from unruptured aneurysms and identifying features associated with rupture. Consistent with prior studies, location and size show the strongest association with aneurysm rupture.
引用
- Silva MA, Patel J, Kavouridis V, et al. Machine Learning Models can Detect Aneurysm Rupture and Identify Clinical Features Associated with Rupture. World Neurosurg. 2019. PMID: 31295616. doi:10.1016/j.wneu.2019.06.231
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。