文献速递重症综合管理与镇静镇痛

基于运动检测的自动化误报警减少在真实重症监护环境中的应用

Automated False Alarm Reduction in a Real-Life Intensive Care Setting Using Motion Detection.
PubMed 文献 · Neurocrit Care · 2020-01-01
一句话结论在真实ICU环境中,基于视频运动检测的报警分类算法对RED(真)报警灵敏度87.0%、特异度29.6%,对GREEN(假)报警灵敏度30.2%、特异度87.2%,但GREEN报警12.8%的假阳性率是关键问题。

该研究开发并验证了一种基于天花板摄像头自动运动检测的报警分类算法,将连续监测的动脉血氧饱和度、收缩压、平均血压、心率和平均颅内压报警分为RED(真)、ORANGE(可能假)和GREEN(假,即伪差)三类。共对45例患者的2349条报警进行了重分类,由盲法临床医生重新判定。结果显示RED报警灵敏度高(87.0%)但特异度低(29.6%),GREEN报警则相反(灵敏度30.2%、特异度87.2%)。作者认为该系统在报警减少方面是进步,但GREEN报警12.8%的假阳性率是关键问题,需增加信号曲线分析、多参数相关性分析和/或更复杂的视频分析来改进。

要点

  • 共2349条报警来自45例患者,由盲法临床医生重分类为RED(真)、ORANGE(可能假)、GREEN(假)三类以评估算法性能。
  • RED报警灵敏度87.0%、特异度29.6%(所有参数合并),作者认为因RED报警不应漏报、即使牺牲假阳性也可接受。
  • GREEN报警灵敏度30.2%、特异度87.2%,作者认为GREEN报警低灵敏度可接受(将GREEN标为RED/ORANGE无害且仍有助于报警减少)。
  • GREEN报警12.8%的假阳性率被作者称为关键问题(critical)。
  • 作者结论:该系统是报警减少的进步,但需增加信号曲线分析、多参数相关性分析和/或更复杂的视频分析来改进。

适用人群与场景

  • 在真实重症监护环境中连续监测动脉血氧饱和度、收缩压、平均血压、心率和平均颅内压的45例患者。

研究设计与关键结果

  • 研究类型:开发并验证基于视频自动运动检测的报警分类算法,使用混淆矩阵评估性能。
  • 样本量:45例患者的2349条报警被重分类。
  • 监测参数:动脉血氧饱和度、收缩压、平均血压、心率、平均颅内压。
  • 运动监测:天花板摄像头监测患者及其周围运动。
  • 报警分类:RED(真)、ORANGE(可能假)、GREEN(假,即伪差),由盲法临床医生重分类。
  • RED报警:灵敏度87.0%,特异度29.6%(所有参数)。
  • GREEN报警:灵敏度30.2%,特异度87.2%(与RED interrelated)。
  • GREEN报警假阳性率12.8%,作者称为关键问题。

证据类型、等级与局限

  • 证据类型:算法开发与验证研究(摘要未报告研究设计细节如回顾性或前瞻性)。
  • 作者结论:该系统是报警减少的进步,但需增加信号曲线分析、多参数相关性分析和/或更复杂的视频分析来改进。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为RED报警高灵敏度(87.0%)低特异度(29.6%)的性能可接受,因RED报警不应漏报、即使牺牲假阳性。
  • 作者认为GREEN报警低灵敏度(30.2%)可接受,因将GREEN报警标为RED/ORANGE无害且仍有助于报警减少。
  • 作者指出GREEN报警12.8%的假阳性率是关键问题。
  • 作者认为需增加信号曲线分析、多参数相关性分析和/或更复杂的视频分析来改进系统。

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

BACKGROUND: Contemporary monitoring systems are sensitive to motion artifacts and cause an excess of false alarms. This results in alarm fatigue and hazardous alarm desensitization. To reduce the number of false alarms, we developed and validated a novel algorithm to classify alarms, based on automatic motion detection in videos.

METHODS: We considered alarms generated by the following continuously measured parameters: arterial oxygen saturation, systolic blood pressure, mean blood pressure, heart rate, and mean intracranial pressure. The movements of the patient and in his/her surroundings were monitored by a camera situated at the ceiling. Using the algorithm, alarms were classified into RED (true), ORANGE (possibly false), and GREEN alarms (false, i.e., artifact). Alarms were reclassified by blinded clinicians. The performance was evaluated using confusion matrices.

RESULTS: A total of 2349 alarms from 45 patients were reclassified. For RED alarms, sensitivity was high (87.0%) and specificity was low (29.6%) for all parameters. As the sensitivities and specificities for RED and GREEN alarms are interrelated, the opposite was observed for GREEN alarms, i.e., low sensitivity (30.2%) and high specificity (87.2%). As RED alarms should not be missed, even at the expense of false positives, the performance was acceptable. The low sensitivity for GREEN alarms is acceptable, as it is not harmful to tag a GREEN alarm as RED/ORANGE. It still contributes to alarm reduction. However, a 12.8% false-positive rate for GREEN alarms is critical.

CONCLUSIONS: The proposed system is a step forward toward alarm reduction; however, implementation of additional layers, such as signal curve analysis, multiple parameter correlation analysis and/or more sophisticated video-based analytics are needed for improvement.

来源:Neurocrit Care,查看原文。版权归原作者所有。

参考来源

  1. Muroi C, Meier S, De Luca V, et al. Automated False Alarm Reduction in a Real-Life Intensive Care Setting Using Motion Detection. Neurocrit Care. 2020. PMID: 31290067. doi:10.1007/s12028-019-00711-w

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。