Related Experiment Video
Updated: Mar 6, 2026
Home-Based Monitor for Gait and Activity Analysis
Published on: August 8, 2019
Measuring Patient Mobility in the ICU Using a Novel Noninvasive Sensor.
Andy J Ma1, Nishi Rawat, Austin Reiter
11Department 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.
A novel noninvasive mobility sensor accurately measures patient movement in the ICU. This automated system offers a feasible method for continuous, objective assessment of intensive care unit patient mobility.
Area of Science:
- Critical Care Medicine
- Biomedical Engineering
- Digital Health
Background:
- Continuous patient mobility monitoring in the Intensive Care Unit (ICU) is crucial for patient outcomes.
- Current methods for assessing mobility are often manual, subjective, and intermittent.
- There is a need for automated, objective, and continuous methods to track patient mobility in the ICU.
Purpose of the Study:
- To develop and validate a noninvasive sensor system for automatic and continuous measurement of patient mobility in the ICU.
- To compare the sensor's automated mobility assessment against manual physician annotations.
Main Methods:
- A prospective, observational study was conducted in a surgical ICU.
- Three Microsoft Kinect sensors were used to collect continuous color and depth image data.
- Software was developed to automatically analyze sensor data, categorizing mobility into four levels: nothing in bed, in-bed activity, out-of-bed activity, and walking.
Main Results:
- The noninvasive mobility sensor was developed using data from three patients and validated on data from five additional patients.
- Agreement between the automated sensor and manual physician annotations was high, with a weighted Kappa (κ) of 0.86.
- Disagreements were mainly between 'nothing in bed' and 'in-bed activity' due to the sensor's continuous motion sensitivity.
Conclusions:
- The developed noninvasive mobility sensor is a novel and feasible tool for automating the evaluation of ICU patient mobility.
- This technology offers a more sensitive and continuous assessment compared to discrete manual scales.
- Automated mobility assessment has the potential to improve patient care and outcomes in the ICU.
