Ma Andy J, Rawat Nishi, Reiter Austin, Shrock Christine, Zhan Andong, Stone Alex, Rabiee Anahita, Griffin Stephanie, Needham Dale M, Saria Suchi
1Department of Computer Science, Johns Hopkins University, Baltimore, MD.2Department of Anesthesia and Critical Care Medicine, Johns Hopkins University School of Medicine, Baltimore, MD.3Armstrong Institute for Patient Safety and Quality, Johns Hopkins University School of Medicine, Baltimore, MD.4Johns Hopkins University School of Medicine, Baltimore, MD.5Outcomes after Critical Illness and Surgery Group, John Hopkins University School of Medicine, Baltimore, MD.6Division of Pulmonary and Critical Care Medicine, Johns Hopkins University School of Medicine, Baltimore, MD.7John Hopkins Hospital, Baltimore, MD.8Department of Physical Medicine and Rehabilitation, John Hopkins University School of Medicine, Baltimore, MD.9Department of Health Policy and Management, Johns Hopkins University Bloomberg School of Public Health, Baltimore, MD.
Crit Care Med. 2017 Apr;45(4):630-636. doi: 10.1097/CCM.0000000000002265.
To develop and validate a noninvasive mobility sensor to automatically and continuously detect and measure patient mobility in the ICU.
Prospective, observational study.
Surgical ICU at an academic hospital.
Three hundred sixty-two hours of sensor color and depth image data were recorded and curated into 109 segments, each containing 1,000 images, from eight patients.
None.
Three Microsoft Kinect sensors (Microsoft, Beijing, China) were deployed in one ICU room to collect continuous patient mobility data. We developed software that automatically analyzes the sensor data to measure mobility and assign the highest level within a time period. To characterize the highest mobility level, a validated 11-point mobility scale was collapsed into four categories: nothing in bed, in-bed activity, out-of-bed activity, and walking. Of the 109 sensor segments, the noninvasive mobility sensor was developed using 26 of these from three ICU patients and validated on 83 remaining segments from five different patients. Three physicians annotated each segment for the highest mobility level. The weighted Kappa (κ) statistic for agreement between automated noninvasive mobility sensor output versus manual physician annotation was 0.86 (95% CI, 0.72-1.00). Disagreement primarily occurred in the "nothing in bed" versus "in-bed activity" categories because "the sensor assessed movement continuously," which was significantly more sensitive to motion than physician annotations using a discrete manual scale.
Noninvasive mobility sensor is a novel and feasible method for automating evaluation of ICU patient mobility.
开发并验证一种非侵入性移动传感器，以自动、连续地检测和测量重症监护病房（ICU）患者的活动情况。
前瞻性观察研究。
一所学术医院的外科重症监护病房。
记录了8名患者的362小时传感器彩色和深度图像数据，并整理成109个片段，每个片段包含1000张图像。
无。
在一间ICU病房部署了3个微软Kinect传感器（微软，中国北京），以收集患者连续的活动数据。我们开发了软件，可自动分析传感器数据以测量活动情况，并在一段时间内确定最高活动水平。为了描述最高活动水平，将经过验证的11点活动量表归纳为四类：卧床不动、床上活动、床下活动和行走。在这109个传感器片段中，非侵入性移动传感器是利用3名ICU患者的26个片段开发的，并在来自5名不同患者的其余83个片段上进行了验证。三名医生对每个片段的最高活动水平进行标注。自动非侵入性移动传感器输出与医生手动标注之间一致性的加权Kappa（κ）统计量为0.86（95%CI，0.72 - 1.00）。不一致主要发生在“卧床不动”和“床上活动”类别之间，因为“传感器持续评估运动”，这对运动的敏感度明显高于医生使用离散手动量表的标注。
非侵入性移动传感器是一种用于自动评估ICU患者活动情况的新颖且可行的方法。
