基于深度学习量化动脉瘤性蛛网膜下腔出血患者总出血量及其与并发症、残疾和死亡的关系
研究纳入单中心2018至2021年发病72小时内入院的819例动脉瘤性蛛网膜下腔出血成人患者,用自动深度学习模型在入院平扫头颅CT上量化总出血量(TBV),按TBV四分位分组分析其与并发症、残疾和死亡的关系。结果显示最高TBV四分位(>37.94 ml)患者发生脑积水、再出血、死亡和12个月残疾的风险显著高于最低四分位(<8.34 ml)患者。
要点
- 最高TBV四分位(>37.94 ml)患者脑积水风险是最低四分位(<8.34 ml)的aOR 4.38倍(95%CI 1.61-11.87;p=0.004)。
- 最高TBV四分位患者再出血aOR 3.26(95%CI 1.03-10.33;p=0.045),死亡aOR 6.92(95%CI 1.89-25.37;p=0.004)。
- 最高TBV四分位患者12个月残疾(mRS≥3)aOR 3.30(95%CI 1.62-6.72;p=0.001)。
核心结论
- 总出血量升高与脑积水、再出血、死亡和不良预后风险增加相关。
研究设计与样本
- 单中心电子健康记录数据提取2018至2021年发病72小时内入院的成人动脉瘤性蛛网膜下腔出血患者。
- 使用自动深度学习模型在入院平扫头颅CT上完整分割并量化总出血量。
- 共纳入819例患者,按总出血量四分位分组,采用多变量logistic回归、限制性立方样条和亚组分析探索总出血量与各临床结局的关系。
主要发现
- 66例(8.1%)发生脑积水,43例(5.3%)再出血,141例(17.2%)迟发性脑缺血,88例(10.7%)出院后12个月内死亡,208例(25.7%)出院后12个月改良Rankin量表评分≥3。
- 与最低TBV四分位(<8.34 ml)相比,最高TBV四分位(>37.94 ml)患者脑积水aOR 4.38(95%CI 1.61-11.87;p=0.004)、再出血aOR 3.26(95%CI 1.03-10.33;p=0.045)、死亡aOR 6.92(95%CI 1.89-25.37;p=0.004)、12个月残疾aOR 3.30(95%CI 1.62-6.72;p=0.001)。
- 限制性立方样条显示脑积水风险与TBV呈非线性正相关(p=0.025),再出血、死亡和残疾风险与TBV呈线性正相关(p>0.05)。
- 亚组分析中,TBV对12个月结局的影响女性大于男性(交互作用p=0.0499),对再出血发生率的影响血管内弹簧圈栓塞患者大于手术夹闭患者(交互作用p=0.008)。
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
OBJECTIVE: The relationships between immediate bleeding severity, postoperative complications, and long-term functional outcomes in patients with aneurysmal subarachnoid hemorrhage (aSAH) remain uncertain. Here, the authors apply their recently developed automated deep learning technique to quantify total bleeding volume (TBV) in patients with aSAH and investigate associations between quantitative TBV and secondary complications, adverse long-term functional outcomes, and death. METHODS: Electronic health record data were extracted for adult patients admitted to a single institution within 72 hours of aSAH onset between 2018 and 2021. An automatic deep learning model was used to fully segment and quantify TBV on admission noncontrast head CT images. Patients were subgrouped by TBV quartile, and multivariable logistic regression, restricted cubic splines, and subgroup analysis were used to explore the relationships between TBV and each clinical outcome. RESULTS: A total of 819 patients were included in the study. Sixty-six (8.1%) patients developed hydrocephalus, while 43 (5.3%) experienced rebleeding, 141 (17.2%) had delayed cerebral ischemia, 88 (10.7%) died in the 12 months after discharge, and 208 (25.7%) had a modified Rankin Scale score ≥ 3 12 months after discharge. On multivariable analysis, patients in the highest TBV quartile (> 37.94 ml) had an increased risk of hydrocephalus (adjusted OR [aOR] 4.38, 95% CI 1.61-11.87; p = 0.004), rebleeding (aOR 3.26, 95% CI 1.03-10.33; p = 0.045), death (aOR 6.92, 95% CI 1.89-25.37; p = 0.004), and 12-month disability (aOR 3.30, 95% CI 1.62-6.72; p = 0.001) compared with the lowest TBV quantile (< 8.34 ml). The risks of hydrocephalus (nonlinear, p = 0.025), rebleeding, death, and disability (linear, p > 0.05) were positively associated with TBV by restricted cubic splines. In subgroup analysis, TBV had a stronger effect on 12-month outcome in female than male patients (p for interaction = 0.0499) and on rebleeding prevalence in patients with endovascular coiling than those with surgical clipping (p for interaction = 0.008). CONCLUSIONS: Elevated TBV is associated with a greater risk of hydrocephalus, rebleeding, death, and poor prognosis.
引用
- Hu P, Wu Y, Yan T, et al. Deep learning-based quantification of total bleeding volume and its association with complications, disability, and death in patients with aneurysmal subarachnoid hemorrhage. J Neurosurg. 2024. PMID: 38552240. doi:10.3171/2024.1.JNS232280
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。