In early 2020, before COVID-19 vaccines and effective treatments were widely available, universal mask-wearing was a key strategy to prevent COVID-19 transmission. However, hospitals and other mask-mandatory facilities faced a challenge. Reminding patients, visitors and staff to wear masks had to be done manually, which was time and labor intensive. Researchers from Brigham and Women’s Hospital (BWH), a founding member of the Mass General Brigham Health Care System, and the Massachusetts Institute of Technology (MIT) set out to test a tool for automated monitoring of medication intake and mask reminders using a computer vision algorithm. The team conducted a pilot study among hospital workers who volunteered to participate and found that the technology worked effectively and most participants reported positive experiences interacting with the system at the hospital entrance. The results of the study are published in BMJ open.
“Changing a behavior, like wearing a mask, takes a lot of effort, even among healthcare professionals,” said lead author Peter Chai, MD, MMS, of the Department of Emergency Medicine. “Our study suggests that a computer visualization system like this could be useful the next time there is a respiratory virus pandemic, where masking is an essential strategy in a hospital setting to control the spread of infection.” »
“Recognizing the challenges in ensuring appropriate mask use and the potential obstacles associated with employees reporting mask misuse by colleagues, we describe here an alternative based on computer vision and computer-aided assessment. Our colleagues from the initial acceptance of the platform,” the lead author said. C. Giovanni Traverso, MB, BChir, PhD, from BWH School of Medicine and MIT School of Mechanical Engineering.
For the study, the team used a computer vision program developed using low-resolution CCTV still images to detect mask-wearing. Between April 26, 2020 and April 30, 2020, researchers invited staff entering one of the hospital’s main entrances to participate in an observational study testing the computer vision model. The team recruited 111 participants who interacted with the system and were interviewed about their experiences.
The computer visualization system accurately detected the presence of mask adhesions 100% of the time. Most participants – 87% – reported positive experiences interacting with the system in the hospital.
The pilot project was limited to staff at a single hospital and may not be transferrable to other institutions. Additionally, masking behaviors and attitudes have changed during the pandemic and may differ across the United States. Future studies are needed to identify barriers to the implementation of computer visualization systems in healthcare facilities compared to other public facilities.
“Our data suggest that people in hospitals are receptive to using computer visualization systems to identify and remind people to wear masks effectively, particularly during the peak of a pandemic, to protect themselves while they are on the front lines serve. of a medical emergency,” Chai said. “The advancement of detection systems could provide us with a useful tool in the context of the COVID-19 pandemic or in preventing the spread of future airborne pathogens.