Contribution of an Automatic Algorithm for Quantifying the Volume of Aneurysmal Subarachnoid Hemorrhage to the Evaluation of the Risk of Occurrence of Delayed Cerebral Ischemia: A Cohort Study.

IF 3.1 3区医学 Q2 CLINICAL NEUROLOGY

Neurocritical Care Pub Date : 2024-10-08 DOI:10.1007/s12028-024-02135-7

Pierre Simeone, Thomas Corrias, Nicolas Bruder, Salah Boussen, Dan Cardoso, Audrey Alonzo, Anthony Reyre, Hervé Brunel, Nadine Girard, Thomas Graillon, Henry Dufour, David Couret, Lionel Velly

{"title":"Contribution of an Automatic Algorithm for Quantifying the Volume of Aneurysmal Subarachnoid Hemorrhage to the Evaluation of the Risk of Occurrence of Delayed Cerebral Ischemia: A Cohort Study.","authors":"Pierre Simeone, Thomas Corrias, Nicolas Bruder, Salah Boussen, Dan Cardoso, Audrey Alonzo, Anthony Reyre, Hervé Brunel, Nadine Girard, Thomas Graillon, Henry Dufour, David Couret, Lionel Velly","doi":"10.1007/s12028-024-02135-7","DOIUrl":null,"url":null,"abstract":"Background: This study focuses on aneurysmal subarachnoid hemorrhage (aSAH) with a high risk of delayed cerebral ischemia (DCI) and acute hydrocephalus (AH). The aim was to compare the performance of an automatic algorithm for quantifying the volume of intracranial blood with the reference radiological scales to predict DCI, AH, and neurological outcome.Methods: This was a single-center retrospective observational study of a cohort of patients with aSAH. We developed an automated blood detection algorithm based on the specific density of the blood clot. The blood clot was segmented on the first brain scan (total, supratentorial, cisternal, intraventricular). The predictive value of our model was compared, using the area under the receiver operating characteristic curve (ROCAUC), to eight radiological scales: Fisher, modified Fisher, Claassen, Barrow Neurological Institute, Hijdra, Graeb, LeRoux scales, and intraventricular hemorrhage score.Results: We analyzed the scans of 145 patients with aSAH. In our cohort, 51 patients (43%) had DCI and 70 patients (54%) had AH. At 3 months, 22% of patients had died and 19% had poor outcome (Glasgow Outcome Scale extended 2-4). Cisternal blood volume was significantly correlated with cisternal Hijdra scale (R2 = 0.79; P < 0.001). The ROCAUC of cisternal blood volume was comparable to the ROCAUC of the Hijdra scale in predicting the occurrence of DCI (ROCAUC = 0.83 [95% confidence interval {CI} 0.75-0.89] vs. 0.86 [95% CI 0.79-0.9]; P = 0.23). The ROCAUC of intraventricular blood volume was not significantly different from the intraventricular hemorrhage score in predicting the occurrence of AH (ROCAUC = 0.78 [95% CI 0.70-0.84] vs. 0.79 [95% CI 0.72-0.85]; P = 0.28). The ROCAUC and supratentorial blood volumes were not significantly different from the Simplified Acute Physiology Score II in predicting the occurrence of poor neurological outcome at 3 months (ROCAUC = 0.75 [95% CI 0.67-0.82] vs. 0.81 [95% CI 0.74-0.87]; P = 0.073).Conclusions: With no manual intervention, our algorithm performed as well as the best radiological scores in predicting the occurrence of DCI, AH, and neurological outcome.","PeriodicalId":19118,"journal":{"name":"Neurocritical Care","volume":" ","pages":""},"PeriodicalIF":3.1000,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurocritical Care","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s12028-024-02135-7","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: This study focuses on aneurysmal subarachnoid hemorrhage (aSAH) with a high risk of delayed cerebral ischemia (DCI) and acute hydrocephalus (AH). The aim was to compare the performance of an automatic algorithm for quantifying the volume of intracranial blood with the reference radiological scales to predict DCI, AH, and neurological outcome.

Methods: This was a single-center retrospective observational study of a cohort of patients with aSAH. We developed an automated blood detection algorithm based on the specific density of the blood clot. The blood clot was segmented on the first brain scan (total, supratentorial, cisternal, intraventricular). The predictive value of our model was compared, using the area under the receiver operating characteristic curve (ROC_AUC), to eight radiological scales: Fisher, modified Fisher, Claassen, Barrow Neurological Institute, Hijdra, Graeb, LeRoux scales, and intraventricular hemorrhage score.

Results: We analyzed the scans of 145 patients with aSAH. In our cohort, 51 patients (43%) had DCI and 70 patients (54%) had AH. At 3 months, 22% of patients had died and 19% had poor outcome (Glasgow Outcome Scale extended 2-4). Cisternal blood volume was significantly correlated with cisternal Hijdra scale (R² = 0.79; P < 0.001). The ROC_AUC of cisternal blood volume was comparable to the ROC_AUC of the Hijdra scale in predicting the occurrence of DCI (ROC_AUC = 0.83 [95% confidence interval {CI} 0.75-0.89] vs. 0.86 [95% CI 0.79-0.9]; P = 0.23). The ROC_AUC of intraventricular blood volume was not significantly different from the intraventricular hemorrhage score in predicting the occurrence of AH (ROC_AUC = 0.78 [95% CI 0.70-0.84] vs. 0.79 [95% CI 0.72-0.85]; P = 0.28). The ROC_AUC and supratentorial blood volumes were not significantly different from the Simplified Acute Physiology Score II in predicting the occurrence of poor neurological outcome at 3 months (ROC_AUC = 0.75 [95% CI 0.67-0.82] vs. 0.81 [95% CI 0.74-0.87]; P = 0.073).

Conclusions: With no manual intervention, our algorithm performed as well as the best radiological scores in predicting the occurrence of DCI, AH, and neurological outcome.

查看原文本刊更多论文

动脉瘤性蛛网膜下腔出血体积量化自动算法对延迟性脑缺血发生风险评估的贡献：一项队列研究。

背景：本研究的重点是动脉瘤性蛛网膜下腔出血（aSAH），该病具有延迟性脑缺血（DCI）和急性脑积水（AH）的高风险。目的是比较量化颅内血容量的自动算法与参考放射尺度在预测DCI、AH和神经功能预后方面的性能：这是一项单中心回顾性观察研究，研究对象是一组颅内积血患者。我们根据血凝块的特定密度开发了一种自动血液检测算法。血凝块在第一次脑部扫描时被分割（全脑、幕上、蝶骨、脑室内）。我们使用接收者操作特征曲线下面积（ROCAUC）将模型的预测价值与八种放射量表进行了比较：结果：我们分析了 145 名 ASAH 患者的扫描结果。在我们的队列中，51 名患者（43%）患有 DCI，70 名患者（54%）患有 AH。3个月后，22%的患者死亡，19%的患者预后不佳（格拉斯哥预后量表扩展为2-4）。在预测 DCI 发生率方面，纤支镜血容量与纤支镜 Hijdra 量表有明显相关性（R2 = 0.79；P），纤支镜血容量的 AUC 与 Hijdra 量表的 ROCAUC 相当（ROCAUC = 0.83 [95% 置信区间 {CI} 0.75-0.89] vs. 0.86 [95% CI 0.79-0.9]; P = 0.23）。在预测 AH 发生方面，脑室内血容量的 ROCAUC 与脑室内出血评分无显著差异（ROCAUC = 0.78 [95% CI 0.70-0.84] vs. 0.79 [95% CI 0.72-0.85]; P = 0.28）。在预测3个月后不良神经功能预后方面，ROCAUC和脑室上血容量与简化急性生理学评分II没有显著差异（ROCAUC = 0.75 [95% CI 0.67-0.82] vs. 0.81 [95% CI 0.74-0.87]; P = 0.073）：结论：在没有人工干预的情况下，我们的算法在预测 DCI、AH 和神经功能预后方面的表现与最佳放射学评分不相上下。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Neurocritical Care 医学-临床神经学

CiteScore

7.40

自引率

8.60%

发文量

221

审稿时长

4-8 weeks

期刊介绍： Neurocritical Care is a peer reviewed scientific publication whose major goal is to disseminate new knowledge on all aspects of acute neurological care. It is directed towards neurosurgeons, neuro-intensivists, neurologists, anesthesiologists, emergency physicians, and critical care nurses treating patients with urgent neurologic disorders. These are conditions that may potentially evolve rapidly and could need immediate medical or surgical intervention. Neurocritical Care provides a comprehensive overview of current developments in intensive care neurology, neurosurgery and neuroanesthesia and includes information about new therapeutic avenues and technological innovations. Neurocritical Care is the official journal of the Neurocritical Care Society.