优化的动脉线伪差识别算法以高准确度清洗重症患者高频动脉线数据
该多中心观察性研究纳入加拿大安大略省ICU中休克和/或呼吸衰竭需有创机械通气的嵌套队列患者,提取15例患者的动脉线高频血压数据,计算收缩压、舒张压和平均动脉压的分钟平均值。经培训的研究者人工回顾40,798个逐分钟平均动脉压数据点,识别出119个伪差(0.29%);优化算法识别出其中116个(97%),并误删或修改537个数据点。与人工审查相比,纳入绝对阈值>30且<200 mm Hg的改良算法敏感度97.5%、特异度98.7%、马修斯相关系数0.41。作者认为,鉴于大型数据集和机器学习在重症研究中的应用日益增多,验证高频数据质量的方法对优化算法性能和防止基于伪差数据的虚假关联很重要。
要点
- 在15例ICU休克和/或呼吸衰竭患者中,人工审查40,798个逐分钟平均动脉压数据点,识别出119个伪差(0.29%)。
- 优化算法识别出119个人工识别伪差中的116个(97%),同时误删或修改537个数据点。
- 纳入绝对阈值>30且<200 mm Hg的改良算法与人工审查相比,敏感度97.5%、特异度98.7%、马修斯相关系数0.41。
- 作者认为,验证高频数据质量的方法对优化算法性能和防止基于伪差数据的虚假关联很重要。
适用人群与场景
- 加拿大安大略省ICU中休克和/或呼吸衰竭需要有创机械通气的嵌套队列患者,共提取15例患者的动脉线数据。
诊断标准与关键阈值
- 改良算法纳入绝对阈值>30且<200 mm Hg。
研究设计与关键结果
- 多中心观察性研究,纳入加拿大安大略省ICU中休克和/或呼吸衰竭需有创机械通气的15例患者,分析动脉线高频血压数据,计算收缩压、舒张压和平均动脉压分钟平均值。
- 经培训的研究者人工回顾40,798个逐分钟平均动脉压数据点,识别出119个伪差(0.29%)。
- 优化算法识别出116个(97%)人工识别的伪差,同时有537个数据点被错误删除或修改。
- 与人工审查相比,纳入绝对阈值>30且<200 mm Hg的改良算法敏感度97.5%、特异度98.7%、马修斯相关系数0.41。
证据类型、等级与局限
- 多中心观察性研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,鉴于大型数据集和机器学习在重症研究中的应用日益增多,验证高频数据质量的方法对优化算法性能和防止基于伪差数据的虚假关联很重要。
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
UNLABELLED: High-frequency data streams of vital signs may be used to generate individualized hemodynamic targets for critically ill patients. Central to this precision medicine approach to resuscitation is our ability to screen these data streams for errors and artifacts. However, there is no consensus on the best method for data cleaning. Our goal was to determine whether an error-checking algorithm developed for intraoperative use could be applied to high volumes of arterial line data in an ICU population.
DESIGN: Multicenter observational study.
SETTING: ICUs across Ontario, Canada.
PATIENTS: Nested cohort of ICU patients with shock and/or respiratory failure requiring invasive mechanical ventilation.
INTERVENTIONS: High-frequency blood pressure data was analyzed. Systolic, diastolic, and mean arterial pressure minute averages were calculated. For manual analysis, a trained researcher retrospectively reviewed mean arterial pressure data, removing values that were deemed nonphysiological. The algorithm was implemented and identified artifactual data.
MEASUREMENTS AND MAIN RESULTS: Arterial line data was extracted from 15 patients. A trained researcher manually reviewed 40,798 minute-by-minute data points, then subsequently analyzed them with the algorithm. Manual review resulted in the identification of 119 artifacts (0.29%). The optimized algorithm identified 116 (97%) of these artifacts. Five hundred thirty-seven data points were erroneously removed or modified. Compared with manual review, the modified algorithm incorporating absolute thresholds of greater than 30 and less than 200 mm Hg had 97.5% sensitivity, 98.7% specificity, and a Matthew correlation coefficient of 0.41.
CONCLUSIONS: The error-checking algorithm had high sensitivity and specificity in detecting arterial line blood pressure artifacts compared with manual data cleaning. Given the growing use of large datasets and machine learning in critical care research, methods to validate the quality of high-frequency data is important to optimize algorithm performance and prevent spurious associations based on artifactual data.
参考来源
- Khan JM, Maslove DM, Boyd JG, et al. Optimized Arterial Line Artifact Identification Algorithm Cleans High-Frequency Arterial Line Data With High Accuracy in Critically Ill Patients. Crit Care Explor. 2022. PMID: 36567784. doi:10.1097/CCE.0000000000000814
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。