Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Oct 27;8(10):e19874.
doi: 10.2196/19874.

Measuring Mobility and Room Occupancy in Clinical Settings: System Development and Implementation

Gabriele Marini #  1 , Benjamin Tag  1 , Jorge Goncalves  1 , Eduardo Velloso  1 , Raja Jurdak  2 , Daniel Capurro  1 , Clare McCarthy  3 , William Shearer  3 , Vassilis Kostakos  1
Affiliations

Measuring Mobility and Room Occupancy in Clinical Settings: System Development and Implementation

Gabriele Marini et al. JMIR Mhealth Uhealth. .

Abstract

Background: The use of location-based data in clinical settings is often limited to real-time monitoring. In this study, we aim to develop a proximity-based localization system and show how its longitudinal deployment can provide operational insights related to staff and patients' mobility and room occupancy in clinical settings. Such a streamlined data-driven approach can help in increasing the uptime of operating rooms and more broadly provide an improved understanding of facility utilization.

Objective: The aim of this study is to measure the accuracy of the system and algorithmically calculate measures of mobility and occupancy.

Methods: We developed a Bluetooth low energy, proximity-based localization system and deployed it in a hospital for 30 days. The system recorded the position of 75 people (17 patients and 55 staff) during this period. In addition, we collected ground-truth data and used them to validate system performance and accuracy. A number of analyses were conducted to estimate how people move in the hospital and where they spend their time.

Results: Using ground-truth data, we estimated the accuracy of our system to be 96%. Using mobility trace analysis, we generated occupancy rates for different rooms in the hospital occupied by both staff and patients. We were also able to measure how much time, on average, patients spend in different rooms of the hospital. Finally, using unsupervised hierarchical clustering, we showed that the system could differentiate between staff and patients without training.

Conclusions: Analysis of longitudinal, location-based data can offer rich operational insights into hospital efficiency. In particular, they allow quick and consistent assessment of new strategies and protocols and provide a quantitative way to measure their effectiveness.

Keywords: Bluetooth; efficiency; indoor; localization; metrics; mobile phone; mobility; occupancy; smartphone.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1
Figure 1
Graph representing the expected journey of a patient through the ward.
Figure 2
Figure 2
Beacons handed out to staff and patients; android devices that get mounted to the walls.
Figure 3
Figure 3
Snapshot of the web-based dashboard used to monitor the deployment and data collection. This was used to ensure the deployment runs as expected.
Figure 4
Figure 4
Laboratory measurements for different beacon advertisement rates (1 Hz, 5 Hz, and 10 Hz) and distance between the beacon and anchor node (1m, 2m, and 5m). We identified 5 Hz as the optimum setting, in terms of performance and battery consumption.
Figure 5
Figure 5
Unfiltered received signal strength indication readings and ground truth (gray line) for a single beacon moving across rooms. X-axis: time; y-axis: room identifier; color: RSSI strength (blue: weak; red: strong). RSSI: received signal strength indication.
Figure 6
Figure 6
Examples of how beacons were handed out. Strapped to a staff badge or to a patient's bracelet.
Figure 7
Figure 7
Received signal strength indication for a single beacon in a single room for a period of 3 min. A stronger signal suggests that the beacon was closer to the anchor node. RSSI: received signal strength indication; OR: operating room.
Figure 8
Figure 8
Unfiltered RSSI readings and ground truth (grey line) for a single beacon moving across rooms. X-axis: time; y-axis: room identifier; colour: RSSI strength (blue: weak; red: strong).
Figure 9
Figure 9
Comparison of three approaches to filter received signal strength indication data. RSSI: received signal strength indication; OR: operating room.
Figure 10
Figure 10
Comparison of using only the median filter (green line) versus using it in conjunction with other filters (red and blue). We test performance at different window sizes. RSSI: received signal strength indication.
Figure 11
Figure 11
Trace reconstruction from our data, as compared to ground truth (grey line).
Figure 12
Figure 12
A reconstructed trace for a single nurse over a 10-day period. X-axis: date/time; y-axis: room.
Figure 13
Figure 13
Room occupancy of nurses over a week.
Figure 14
Figure 14
Room occupancy of patients over a week.
Figure 15
Figure 15
Using hierarchical clustering to group people and rooms into similar clusters. The data used for clustering is the time spent per room by each person tracked. NSxx: medical staff; Pxx: patients; TTxx/HTxx: technical staff.
See this image and copyright information in PMC

References

    1. Lorcan C, Steve N, Paddy N, Aaron Q. Sensor Aggregation and Integration in Healthcare Location Based Services. Pervasive Health Conference and Workshops; PCTHEALTH'06; November 29-December 1, 2006; Innsbruck, Austria. 2006. - DOI
    1. Davidson P, Piche R. A survey of selected indoor positioning methods for smartphones. IEEE Commun Surv Tutorials. 2017;19(2):1347–70. doi: 10.1109/COMST.2016.2637663. doi: 10.1109/comst.2016.2637663. - DOI - DOI
    1. Miclo R, Fontanili F, Marquès G, Bomert P, Lauras M. RTLS-Based Process Mining: Towards an Automatic Process Diagnosis in Healthcare. International Conference on Automation Science and Engineering; CASE'15; August 24-28, 2015; Gothenburg, Sweden. 2015. - DOI
    1. Kamel Boulos MN, Berry G. Real-time locating systems (RTLS) in healthcare: a condensed primer. Int J Health Geogr. 2012 Jun 28;11:25. doi: 10.1186/1476-072X-11-25. https://ij-healthgeographics.biomedcentral.com/articles/10.1186/1476-072... - DOI - DOI - PMC - PubMed
    1. YNOMIA and CSIRO Collaboration. [2020-09-22]. https://ynomia.io/technology.

Publication types