文献速递心脑血管急症儿科与产科急症重症综合管理与镇静镇痛

机器学习识别儿童心脏骤停后早期头颅CT上的缺氧缺血性脑损伤

Machine learning to identify hypoxic-ischemic brain injury on early head CT after pediatric cardiac arrest.
PubMed 文献 · Resuscitation · 2025-06-27
一句话结论回顾性研究显示,深度学习模型可在儿童院外心脏骤停后24小时内头颅CT上识别缺氧缺血性脑损伤,并能发现部分放射科医师肉眼未识别的推测性HIBI。

该回顾性研究纳入117例儿童院外心脏骤停(OHCA)病例(年龄3.1[0.7-12.2]岁),并与年龄匹配对照比较,训练深度学习模型在OHCA后24小时内CT上检测缺氧缺血性脑损伤(HIBI)。模型区分OHCA与对照的平均AUC为0.87±0.05;在OHCA病例中预测死亡和不良结局(出院时PCPC 4-6)的平均AUC分别为0.79±0.06和0.69±0.06。模型区分44例放射科医师识别HIBI的OHCA与对照的平均AUC为0.98±0.01;在73例放射科医师未识别HIBI的OHCA中,模型将36%判为推测性HIBI,其中31%死亡,而无放射学及模型HIBI的病例死亡率为17%(p=0.174)。结论认为深度学习模型可识别儿童OHCA后早期CT上的HIBI,并检测部分放射科医师肉眼未识别的推测性HIBI。

要点

  • 回顾性研究纳入117例儿童OHCA病例,年龄3.1[0.7-12.2]岁,43%死亡,58%出院时PCPC 4-6不良结局。
  • 模型区分OHCA病例与年龄匹配对照的平均AUC为0.87±0.05。
  • 在OHCA病例中,模型预测死亡和不良结局的平均AUC分别为0.79±0.06和0.69±0.06。
  • 模型区分44例放射科医师识别HIBI的OHCA与对照的平均AUC为0.98±0.01。
  • 73例放射科医师未识别HIBI的OHCA中,模型将36%判为推测性HIBI,其中31%死亡,而无放射学及模型HIBI的病例死亡率为17%(p=0.174)。

适用人群与场景

  • 儿童院外心脏骤停(OHCA)后24小时内完成头颅CT的病例,与年龄匹配对照比较。

研究设计与关键结果

  • 回顾性研究分析117例儿童OHCA病例(年龄3.1[0.7-12.2]岁),43%死亡,58%出院时PCPC 4-6不良结局;心脏骤停至CT中位时间2.1[1.0,7.2]小时。
  • 深度学习模型区分OHCA病例与对照的平均AUC为0.87±0.05。
  • 在OHCA病例中,模型预测死亡和不良结局的平均AUC分别为0.79±0.06和0.69±0.06。
  • 模型区分44例放射科医师识别HIBI的OHCA与对照的平均AUC为0.98±0.01。
  • 在73例放射科医师未识别HIBI的OHCA病例中,模型将36%判为推测性HIBI,其中31%死亡,而无放射学及模型HIBI的病例死亡率为17%(p=0.174)。

证据类型、等级与局限

  • 证据类型:回顾性研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 原文未据此给出推荐。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「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

AIMS: To train deep learning models to detect hypoxic-ischemic brain injury (HIBI) on early CT scans after pediatric out-of-hospital cardiac arrest (OHCA) and determine if models could identify HIBI that was not visually appreciable to a radiologist.

METHODS: Retrospective study of children who had a CT scan within 24 h of OHCA compared to age-matched controls. We designed models to detect HIBI by discriminating CT images from OHCA cases and controls, and predict death and unfavorable outcome (PCPC 4-6 at hospital discharge) among cases. Model performance was measured by AUC. We trained a second model to distinguish OHCA cases with radiologist-identified HIBI from controls without OHCA and tested the model on OHCA cases without radiologist-identified HIBI. We compared outcomes between OHCA cases with and without model-categorized HIBI.

RESULTS: We analyzed 117 OHCA cases (age 3.1 [0.7-12.2] years); 43 % died and 58 % had unfavorable outcome. Median time from arrest to CT was 2.1 [1.0,7.2] hours. Deep learning models discriminated OHCA cases from controls with a mean AUC of 0.87 ± 0.05. Among OHCA cases, mean AUCs for predicting death and unfavorable outcome were 0.79 ± 0.06 and 0.69 ± 0.06, respectively. Mean AUC was 0.98 ± 0.01 for discriminating between 44 OHCA cases with radiologist-identified HIBI and controls. Among 73 OHCA cases without radiologist-identified HIBI, the model identified 36 % as having presumed HIBI; 31 % of whom died compared to 17 % of cases without HIBI identified radiologically and via the model (p = 0.174).

CONCLUSION: Deep learning models can identify HIBI on early CT images after pediatric OHCA and detect some presumed HIBI visually not identified by a radiologist.

来源:Resuscitation,查看原文。版权归原作者所有。

参考来源

  1. Kirschen MP, Li J, Elmer J, et al. Machine learning to identify hypoxic-ischemic brain injury on early head CT after pediatric cardiac arrest. Resuscitation. 2025. PMID: 40582483. doi:10.1016/j.resuscitation.2025.110693

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。