文献速递脑血管病外科神经重症

基于机器学习的自发性蛛网膜下腔出血后慢性分流依赖性脑积水预测

Machine Learning-Based Prediction of Chronic Shunt-Dependent Hydrocephalus After Spontaneous Subarachnoid Hemorrhage.
PubMed 文献 · World Neurosurg · 2024-09-12

该研究分析了2013至2018年在本机构治疗的510例自发性蛛网膜下腔出血患者,使用监督机器学习模型预测慢性分流依赖性脑积水。逻辑回归模型表现最优,受试者工作特征曲线下面积为0.819,精确率-召回率曲线下面积为0.482,F1分数最高为0.473。女性及前交通动脉无动脉瘤与较低的分流需求可能性相关。

要点

  • 逻辑回归模型预测慢性分流依赖性脑积水的AUC为0.819,AUPRC为0.482,F1分数为0.473。
  • 各模型平衡准确率范围为0.735至0.764,逻辑回归在AUC和AUPRC等关键指标上持续优于其他模型。
  • 女性及前交通动脉无动脉瘤与较低的分流需求可能性相关。

核心结论

  • 机器学习模型包括逻辑回归对自发性蛛网膜下腔出血后早期慢性分流依赖性脑积水具有较强预测能力,可能有助于更及时地实施分流手术。

研究设计与样本

  • 对2013年至2018年在本机构治疗的510例蛛网膜下腔出血患者进行分析,评估临床和影像学变量,使用Python和scikit-learn训练和比较监督机器学习模型,并通过重复交叉验证严格评估模型性能。

主要发现

  • 逻辑回归模型表现最优,受试者工作特征曲线下面积为0.819,精确率-召回率曲线下面积为0.482,F1分数最高为0.473。
  • 各模型平衡准确率范围为0.735至0.764,逻辑回归在受试者工作特征曲线下面积和精确率-召回率曲线下面积等关键指标上持续优于其他模型。
  • 女性及前交通动脉无动脉瘤与较低的分流需求可能性相关。

临床怎么用

  • 作者认为机器学习模型包括逻辑回归的预测能力得到其网络界面的支持,该界面简化了这些模型的应用,帮助临床医生高效判断分流手术的必要性。

局限性

  • 原文未报告局限性

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: Chronic posthemorrhagic hydrocephalus often arises following spontaneous subarachnoid hemorrhage (SAH). Timely identification of patients predisposed to develop chronic shunt-dependent hydrocephalus may significantly enhance clinical outcomes. METHODS: We performed an analysis of 510 SAH patients treated at our institution between 2013 and 2018. Clinical and radiological variables, including age, sex, Hunt & Hess grade, Fisher Score, external ventricular drainage placement, central nervous system infection, aneurysm characteristics, and treatment modalities, were evaluated. Supervised machine learning (ML) models, trained and compared using Python and scikit-learn, were employed to predict chronic shunt-dependent hydrocephalus. Model performance was rigorously assessed through repeated cross-validation. To facilitate transparency and collaboration, we publicly released the dataset and code on GitHub (https://github.com/RISCSoftware/shuntclf) and developed an interactive web application (https://huggingface.co/spaces/risc42/shuntclf). RESULTS: Among the evaluated ML models, logistic regression exhibited superior performance, with an area under the receiver operating characteristic curve of 0.819 and an area under the precision-recall curve of 0.482, along with the highest F1 score of 0.473. Although the balanced accuracy scores of the models were generally proximate, ranging from 0.735 to 0.764, logistic regression consistently outperforms others in key metrics such as area under the receiver operating characteristic curve and area under the precision-recall curve. Conversely, female gender and absence of aneurysm within the anterior communicating artery were associated with reduced shunt requirement likelihood. CONCLUSIONS: ML models, including logistic regression, demonstrate strong predictive capability for early chronic shunt-dependent hydrocephalus following spontaneous SAH, which may potentially contribute to more timely shunt placement interventions. This predictive capability is supported by our web interface, which simplifies the application of these models, aiding clinicians in efficiently determining the need for shunt placement.

来源:World Neurosurg,查看原文。版权归原作者所有。

引用

  1. Gollwitzer M, Steindl M, Stroh N, et al. Machine Learning-Based Prediction of Chronic Shunt-Dependent Hydrocephalus After Spontaneous Subarachnoid Hemorrhage. World Neurosurg. 2024. PMID: 39276974. doi:10.1016/j.wneu.2024.09.047

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。