文献速递复苏、休克与脓毒症重症综合管理与镇静镇痛

基于机器学习的猪心脏骤停模型心肺复苏期间自主循环恢复预测:数据分辨率与多模态生理波形的影响

Machine Learning-Based Return of Spontaneous Circulation Prediction During Cardiopulmonary Resuscitation in a Swine Model of Cardiac Arrest: Effect of Data Resolution and Multimodal Physiological Waveforms.
PubMed 文献 · Crit Care Med · 2025-11-24
一句话结论在猪心脏骤停模型中,高分辨率监测改善早期单个信号的自主循环恢复预测,但多模态整合可弥补低分辨率的不足。

该研究为回顾性分析实验数据,使用机器学习模型预测187头儿科猪在标准化心脏骤停与心肺复苏方案下的自主循环恢复。监测信号包括主动脉血压、右心房压、二氧化碳波形图和心电图,评估四种数据方法:波形-高分辨率(100 Hz)、按压-高分辨率(逐次按压生理序列)、波形-低分辨率(15秒平均)和按压-低分辨率(15秒平均序列)。在早期心肺复苏(2-4分钟),按压-高分辨率对主动脉血压和右心房压的预测优于两种低分辨率方法(P<0.05);多模态模型中低分辨率与高分辨率表现相当(AUROC 0.76-0.79)。随复苏时间延长,基于主动脉血压的模型性能提升,全复苏期(2-10分钟)AUROC达0.90,与多模态模型(0.89)相当。结论认为高分辨率监测改善早期单个信号的自主循环恢复预测,多模态整合可补偿较低分辨率,支持数据驱动策略选择生理靶点和技术要求。

要点

  • 在早期心肺复苏(2-4分钟),按压-高分辨率对主动脉血压的自主循环恢复预测AUROC为0.74(0.65-0.82),优于两种低分辨率方法(0.65和0.54)。
  • 在早期心肺复苏(2-4分钟),按压-高分辨率对右心房压的预测AUROC为0.70(0.62-0.79),优于低分辨率方法(0.61和0.57;P<0.05)。
  • 多模态模型中低分辨率数据表现与高分辨率相当,AUROC为0.76-0.79。
  • 基于主动脉血压的模型性能随复苏时间延长而提升,全复苏期(2-10分钟)AUROC达0.90(0.84-0.95),与多模态模型(0.89[0.83-0.95])相当。
  • 作者认为这些发现支持数据驱动策略选择生理靶点和技术要求,用于生理导向的心肺复苏。

适用人群与场景

  • 187头接受标准化心脏骤停与心肺复苏方案的儿科猪。

研究设计与关键结果

  • 研究类型为回顾性分析实验数据,使用机器学习模型预测自主循环恢复,样本为187头儿科猪,在实验室环境下进行标准化心脏骤停与心肺复苏。
  • 评估四种数据方法:波形-高分辨率(100 Hz波形)、按压-高分辨率(逐次按压生理序列)、波形-低分辨率(15秒平均波形)和按压-低分辨率(15秒平均逐次按压序列),使用2-4、2-6、2-8和2-10分钟心肺复苏片段,单信号与组合信号模态。
  • 早期心肺复苏(2-4分钟),按压-高分辨率对主动脉血压的AUROC为0.74(0.65-0.82),优于两种低分辨率方法(0.65[0.55-0.74]和0.54[0.44-0.64]);对右心房压的AUROC为0.70(0.62-0.79),优于低分辨率方法(0.61[0.51-0.70]和0.57[0.48-0.66];P<0.05)。
  • 多模态模型中,低分辨率数据表现与高分辨率模型相当,AUROC为0.76-0.79。
  • 随复苏时间延长,基于主动脉血压的模型性能提升,全复苏期(2-10分钟)AUROC达0.90(0.84-0.95),与多模态模型(0.89[0.83-0.95])相当。

证据类型、等级与局限

  • 证据类型:回顾性分析实验数据。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,高分辨率监测改善早期单个信号的自主循环恢复预测,尤其是主动脉血压和右心房压;多模态整合可补偿较低分辨率,支持数据驱动策略选择生理靶点和技术要求用于生理导向的心肺复苏。

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

OBJECTIVES: To determine whether high-resolution (HighRes) and multimodal integration of physiologic signals improve prediction of return of spontaneous circulation (ROSC) during pediatric cardiopulmonary resuscitation (CPR) compared with low-resolution (LowRes) and single-modality approaches.

DESIGN: Retrospective analysis of experimental data using machine learning models for outcome prediction.

SETTING: Laboratory setting with pediatric swine models of cardiac arrest.

SUBJECTS: A total of 187 pediatric swine undergoing standardized cardiac arrest and CPR protocols.

INTERVENTIONS: Animals were monitored using multiple physiologic signals during CPR, including aortic blood pressure (ABP), right atrial pressure (RAP), capnography, and electrocardiography. No therapeutic interventions were evaluated.

MEASUREMENTS AND MAIN RESULTS: Four data approaches were evaluated: 1) Waveform-HighRes (100 Hz waveforms); 2) Compression-HighRes (compression-by-compression physiologic series); 3) Waveform-LowRes (15-s averaged waveforms); and 4) Compression-LowRes (15-s averaged compression-by-compression series). Models were developed to predict ROSC using segments 2-4, 2-6, 2-8, and 2-10 minutes of CPR, using both single and combined signal modalities. Area under the receiver operating characteristic curve (AUROC) was used to evaluate models' performance. In early CPR (2-4 min), Compression-HighRes outperformed both LowRes approaches for ABP (AUROC, 0.74 [0.65-0.82] vs. 0.65 [0.55-0.74] and 0.54 [0.44-0.64]) and RAP (0.70 [0.62-0.79] vs. 0.61 [0.51-0.70] and 0.57 [0.48-0.66]; p < 0.05). In multimodal models, LowRes data performed comparably to HighRes models (AUROC, 0.76-0.79). Across time points, ABP-based model performance improved, reaching AUROC 0.90 (0.84-0.95) for the full CPR period (2-10 min)-comparable to the multimodal model (0.89 [0.83-0.95]).

CONCLUSIONS: HighRes monitoring improved early ROSC prediction for individual signals, especially ABP and RAP. However, combining multiple modalities compensates for lower resolution, enabling comparable predictive performance. These findings support data-driven strategies for selecting physiologic targets and technical requirements in physiology-directed CPR.

来源:Crit Care Med,查看原文。版权归原作者所有。

参考来源

  1. Silva LEV, Gaudio HA, Padmanabhan V, et al. Machine Learning-Based Return of Spontaneous Circulation Prediction During Cardiopulmonary Resuscitation in a Swine Model of Cardiac Arrest: Effect of Data Resolution and Multimodal Physiological Waveforms. Crit Care Med. 2025. PMID: 41631940. doi:10.1097/CCM.0000000000006968

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。