文献速递呼吸衰竭与机械通气重症综合管理与镇静镇痛

利用机器学习从原始呼吸机波形数据筛查急性呼吸窘迫综合征

Use of Machine Learning to Screen for Acute Respiratory Distress Syndrome Using Raw Ventilator Waveform Data.
PubMed 文献 · Crit Care Explor · 2021-01-08
一句话结论回顾性队列显示,仅用呼吸机波形数据训练的随机森林模型可较好区分ARDS与其他原因呼吸衰竭,24/6模型AUC 0.89。

取达标后首个24小时(非ARDS为插管后首个24小时)的压力与流量时间序列提取9个生理特征,训练随机森林模型区分ARDS。24/24模型AUC 0.88、敏感度0.90、特异度0.71、PPV 0.77、NPV 0.90;24/6模型AUC 0.89、敏感度0.90、特异度0.75、PPV 0.83、NPV 0.83。作者认为该法或可在插管后早期辅助ARDS筛查,与常规诊断标准结合可能改善识别时效。

要点

  • 仅用呼吸机原始波形提取的9个生理特征训练随机森林,24/6模型AUC 0.89、敏感度0.90、特异度0.75、PPV 0.83、NPV 0.83。
  • 24/24模型AUC 0.88、敏感度0.90、特异度0.71、PPV 0.77、NPV 0.90,显示用首个24小时数据训练与测试性能相近。
  • 研究为单中心回顾性队列,ARDS 50例、非ARDS 50例,模型尚属探索性,不能替代传统诊断标准。
  • 作者提出该法可与传统诊断标准结合,用于插管后早期筛查及资源有限、常规诊断工具或电子病历不足的场景。

适用人群与场景

  • 学术医学中心ICU中需要有创机械通气的成人;ARDS组50例,非ARDS组50例为有创机械通气主要适应证非低氧性呼吸衰竭者。

诊断标准与关键阈值

  • ARDS判定基于急性呼吸窘迫综合征标准(原文未列出具体条件与界值);非ARDS为有创机械通气主要适应证非低氧性呼吸衰竭。
  • 数据窗口:ARDS患者为满足ARDS标准后首个24小时,非ARDS患者为机械通气首个24小时。
  • 模型输出用于区分ARDS与非ARDS,原文未给出临床启动或停止的阈值。

处置流程与药物剂量

  • 原文未提及具体处置流程或药物剂量;研究为观察性,无干预。

红旗征与不能漏的情况

  • 原文未提及

研究设计与关键结果

  • 干预与对照:无干预;比较ARDS与非ARDS患者的呼吸机波形特征。
  • 主要终点:24/24模型AUC 0.88、敏感度0.90、特异度0.71、PPV 0.77、NPV 0.90;24/6模型AUC 0.89、敏感度0.90、特异度0.75、PPV 0.83、NPV 0.83。
  • 关键次要终点与不良事件:原文未提及。

证据类型、等级与局限

  • 证据类型:回顾性观察性队列研究(原文未给出证据等级或推荐强度)。

对床旁实践的改变

  • 提示仅凭呼吸机波形数据即可在插管后早期(首个24小时内)辅助区分ARDS与其他原因呼吸衰竭,可与传统诊断标准结合用于早期筛查。
  • 作者提出该法可能适用于常规诊断工具或电子病历不足的场景,但当前证据为单中心回顾性探索,尚不能替代标准诊断流程。
  • 原文未提及适用与不适用人群的进一步限定,也未提及常见陷阱。

指南或共识出处

  • 原文未提及指南或共识出处;文献发表于Crit Care Explor。

以上提炼依据论文摘要(全文未开放获取,或许可不允许翻译转载);全文请点「阅读原文」。

英文原文(摘要)· 点击展开

UNLABELLED: To develop and characterize a machine learning algorithm to discriminate acute respiratory distress syndrome from other causes of respiratory failure using only ventilator waveform data.

DESIGN: Retrospective, observational cohort study.

SETTING: Academic medical center ICU.

PATIENTS: Adults admitted to the ICU requiring invasive mechanical ventilation, including 50 patients with acute respiratory distress syndrome and 50 patients with primary indications for mechanical ventilation other than hypoxemic respiratory failure.

INTERVENTIONS: None.

MEASUREMENTS AND MAIN RESULTS: Pressure and flow time series data from mechanical ventilation during the first 24-hours after meeting acute respiratory distress syndrome criteria (or first 24-hr of mechanical ventilation for non-acute respiratory distress syndrome patients) were processed to extract nine physiologic features. A random forest machine learning algorithm was trained to discriminate between the patients with and without acute respiratory distress syndrome. Model performance was assessed using the area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value. Analyses examined performance when the model was trained using data from the first 24 hours and tested using withheld data from either the first 24 hours (24/24 model) or 6 hours (24/6 model). Area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value were 0.88, 0.90, 0.71, 0.77, and 0.90 (24/24); and 0.89, 0.90, 0.75, 0.83, and 0.83 (24/6).

CONCLUSIONS: Use of machine learning and physiologic information derived from raw ventilator waveform data may enable acute respiratory distress syndrome screening at early time points after intubation. This approach, combined with traditional diagnostic criteria, could improve timely acute respiratory distress syndrome recognition and enable automated clinical decision support, especially in settings with limited availability of conventional diagnostic tests and electronic health records.

来源:Crit Care Explor,查看原文。版权归原作者所有。

参考来源

  1. Rehm GB, Cortés-Puch I, Kuhn BT, et al. Use of Machine Learning to Screen for Acute Respiratory Distress Syndrome Using Raw Ventilator Waveform Data. Crit Care Explor. 2021. PMID: 33458681. doi:10.1097/CCE.0000000000000313

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。