文献速递心脑血管急症重症综合管理与镇静镇痛

脑出血后血肿扩大预测:临床医生预测与深度学习影像组学模型的比较

Predicting hematoma expansion after intracerebral hemorrhage: a comparison of clinician prediction with deep learning radiomics models.
PubMed 文献 · Neurocrit Care · 2025-02-07
一句话结论在900例自发性脑出血患者中,专家临床医生预测血肿扩大的AUC为0.591,深度学习影像组学模型AUC为0.680,模型可能优于临床医生。

本研究基于抗高血压治疗急性脑出血2研究(Antihypertensive Treatment of Acute Cerebral Hemorrhage 2 Study)的900例脑出血患者数据,用基线头颅CT影像及入院临床数据在训练队列(n=621)开发机器学习模型,并在独立测试队列(n=279)中评估其预测24小时内血肿扩大(定义为血肿体积增加≥33%或>6 mL)的性能。同时调查专家临床医生,让其使用相同的初始CT影像和临床数据预测血肿扩大。结果:专家临床医生预测血肿扩大的AUC为0.591,评估者间Kappa为0.156;仅用影像组学数据的深度学习模型AUC为0.680;联合影像组学与临床数据的随机森林模型AUC为0.677。临床判断与最佳机器学习模型的组内相关系数为0.47(95%CI 0.23-0.75)。作者认为,监督机器学习算法预测血肿扩大可能优于临床医生,尽管总体AUC仅为中等,但为这一即使专家也感困难的任务设定了新的相对基准,并强调需要持续改进和增强临床决策支持以优化脑出血患者管理。

要点

  • 在900例自发性脑出血患者中,专家临床医生预测24小时血肿扩大(≥33%或>6 mL)的AUC为0.591,评估者间Kappa仅0.156。
  • 仅用影像组学数据的深度学习模型预测血肿扩大AUC为0.680,联合影像组学与临床数据的随机森林模型AUC为0.677。
  • 临床判断与最佳机器学习模型的组内相关系数为0.47(95%CI 0.23-0.75)。
  • 作者认为机器学习模型预测血肿扩大可能优于临床医生,但总体AUC仅为中等,强调需要持续改进临床决策支持。

适用人群与场景

  • 非创伤性自发性脑出血患者,来自抗高血压治疗急性脑出血2研究(Antihypertensive Treatment of Acute Cerebral Hemorrhage 2 Study)的900例参与者。
  • 模型开发使用训练队列(n=621)的基线头颅CT影像及入院临床数据,性能评估使用独立测试队列(n=279)。

诊断标准与关键阈值

  • 血肿扩大定义为24小时内血肿体积增加≥33%或>6 mL。

研究设计与关键结果

  • 研究类型:基于抗高血压治疗急性脑出血2研究数据的机器学习模型开发与验证研究,训练队列n=621,独立测试队列n=279。
  • 专家临床医生预测血肿扩大的AUC为0.591,评估者间Kappa为0.156。
  • 仅用影像组学数据的深度学习模型(图像输入)AUC为0.680;联合影像组学与临床数据的随机森林模型AUC为0.677。
  • 临床判断与最佳机器学习模型的组内相关系数为0.47(95%CI 0.23-0.75)。

证据类型、等级与局限

  • 证据类型:基于临床试验数据的机器学习模型开发与验证研究(使用抗高血压治疗急性脑出血2研究数据)。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,监督机器学习算法预测血肿扩大可能优于临床医生,尽管总体AUC为中等,结果为这一即使专家也感困难的任务设定了新的相对基准。
  • 作者强调需要持续改进和进一步增强临床决策支持,以优化脑出血患者的管理。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

BACKGROUND: Early prediction of hematoma expansion (HE) following nontraumatic intracerebral hemorrhage (ICH) may inform preemptive therapeutic interventions. We sought to identify how accurately machine learning (ML) radiomics models predict HE compared with expert clinicians using head computed tomography (HCT).

METHODS: We used data from 900 study participants with ICH enrolled in the Antihypertensive Treatment of Acute Cerebral Hemorrhage 2 Study. ML models were developed using baseline HCT images, as well as admission clinical data in a training cohort (n = 621), and their performance was evaluated in an independent test cohort (n = 279) to predict HE (defined as HE by 33% or > 6 mL at 24 h). We simultaneously surveyed expert clinicians and asked them to predict HE using the same initial HCT images and clinical data. Area under the receiver operating characteristic curve (AUC) were compared between clinician predictions, ML models using radiomic data only (a random forest classifier and a deep learning imaging model) and ML models using both radiomic and clinical data (three random forest classifier models using different feature combinations). Kappa values comparing interrater reliability among expert clinicians were calculated. The best performing model was compared with clinical predication.

RESULTS: The AUC for expert clinician prediction of HE was 0.591, with a kappa of 0.156 for interrater variability, compared with ML models using radiomic data only (a deep learning model using image input, AUC 0.680) and using both radiomic and clinical data (a random forest model, AUC 0.677). The intraclass correlation coefficient for clinical judgment and the best performing ML model was 0.47 (95% confidence interval 0.23-0.75).

CONCLUSIONS: We introduced supervised ML algorithms demonstrating that HE prediction may outperform practicing clinicians. Despite overall moderate AUCs, our results set a new relative benchmark for performance in these tasks that even expert clinicians find challenging. These results emphasize the need for continued improvements and further enhanced clinical decision support to optimally manage patients with ICH.

来源:Neurocrit Care,查看原文。版权归原作者所有。

参考来源

  1. Yu B, Melmed KR, Frontera J, et al. Predicting hematoma expansion after intracerebral hemorrhage: a comparison of clinician prediction with deep learning radiomics models. Neurocrit Care. 2025. PMID: 39920546. doi:10.1007/s12028-025-02214-3

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。