Measuring Patient Mobility in the ICU Using a Novel Noninvasive Sensor

Abstract

Objectives To develop and validate a noninvasive mobility sensor to automatically and continuously detect and measure patient mobility in the ICU. Design Prospective, observational study. Setting Surgical ICU at an academic hospital. Patients 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. Interventions None. Measurements and Main Results 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. Conclusions Noninvasive mobility sensor is a novel and feasible method for automating evaluation of ICU patient mobility.

Intelligent ICU for Autonomous Patient Monitoring Using Pervasive Sensing and Deep Learning

“…This previously unattainable information can optimize patients’ care by providing more comprehensive data on patients’ status through accurate and granular quantification of patients’ movement. While there is previous work that has used video recordings in the ICU to detect patient’s status 30 , they were not able to measure the intensity of patients’ physical activity. The combined knowledge of patients’ functional status through video data and their physical activity intensity through movement analysis methods can help health practitioners to better decide on rehabilitation and assisted mobility needs.…”

Deep learning-enabled medical computer vision

“…3 ). In hospitals, for example, early works have demonstrated CV-based ambient intelligence in intensive care units to monitor for safety-critical behaviors such as hand hygiene activity 32 and patient mobilization 8 , 129 , 130 . CV has also been developed for the emergency department, to transcribe procedures performed during the resuscitation of a patient 131 , and for the operating room (OR), to recognize activities for workflow optimization 132 .…”

A computer vision system for deep learning-based detection of patient mobilization activities in the ICU

“…We show that computer vision algorithms can accurately detect patient mobility activities, their duration, and the number of personnel that complete them. Although our study builds on the work of Ma et al, 25 whose algorithm calculates a numeric mobility score for ICU patients, our algorithms enable more detailed study of how specific types of mobility events and variation in their frequency and duration will impact clinical outcomes. This aspect of our work is clinically significant, as there is currently great variation in protocols for early mobilization of critically ill patients, which limits the generalizability of study findings.…”

“…21,22 CVT has also been applied in the operating room, where algorithms recognize patient care tasks (such as moving the patient onto the operating table), steps and tools in a surgical procedure, and even the surgeon’s level of operative skill. 23,24 Finally and most relevant to our study, Ma et al 25 used CVT to determine a numeric mobility level for patients in a single ICU room. We build off of this work by using depth sensor-based CVT to collect data from seven individual adult ICU rooms and develop machine-learning algorithms to temporally detect patients’ bedside activities and the healthcare personnel involved.…”