Bluetooth system an effective tool for health care worker COVID-19 contact tracing
Click Here to Manage Email Alerts
Key takeaways:
- The Bluetooth-based system predicted close contacts with an accuracy between 0.88 and 1.
- The system also identified personnel present during rounds and the length of contact.
A Bluetooth low-energy-based contact-tracing system successfully identified potential COVID-19 contacts, providing specific additional data including location, date and cumulative contact time, researchers found.
“Health care personnel (HCP) are at significant risk for contracting and spreading SARS-CoV-2. Several methods relying on Bluetooth low-energy (BLE) have been explored in clinical applications focusing on single individuals,” M. Cristina Vazquez Guillamet MD, associate professor of medicine at the Washington University School of Medicine, and colleagues wrote.
“The results of a pilot study indicated that BLE wearable tags may be a tool for detecting contacts in hospital settings,” they wrote.
Vazquez Guillamet and colleagues developed and tested an automated BLE-based contact-tracing system designed for health care settings, focusing on contacts among HCP at two COVID-19 hospital units — one medical ward and one ICU.
The system consisted of small coin-sized, battery-operated wearable BLE devices, referred to as beacons, which were worn by HCP and transmitted short-range radio signals to small-embedded computers, or anchors, which captured the signals, and an edge server where contact-tracing algorithms were applied to the data. This system was deployed in the two units for 6 months between May 2021 and November 2021.
Using these data, the researchers calculated the proximity between users and close contacts during patient rounds. When an HCP tested positive for COVID-19, the system provided lists of all potential contacts, location, date and cumulative contact time. The researchers then estimated the impact of the system using a modified susceptible, exposed, infected, and recovered compartmental model.
In total, 186 HCP participated in the study for a total observed experiment time of 43 hours, and the system recorded data for 6 months. They found that the overall accuracy for room-level location ranged between 0.96 and 1, and improved as the number of anchors increased, leading the team to predict close contacts with an accuracy between 0.88 and 1 and an F1 score — which measures the model’s accuracy — of 0.91 to 1.
The system, which observed 36.8 hours during patient rounds, also showed that the core group of HCP during patient rounds consisted of seven people on average. The system’s clustering method accurately identified the personnel present during rounds and the time spent in contact with the group with accuracy and F1 score above 0.9.
Based on these findings, Vazquez Guillamet and colleagues wrote that BLE-based contact tracing “presents an affordable and scalable system that may function as a screening tool to complement traditional contact-tracing methods.”