Sign in to my dashboard Create an account

A flexible AI approach for face mask compliance in healthcare settings

Person wearing a mask
Table of Contents

Share this page

Mike McNamara

Even as COVID-19 case rates are falling and vaccination rates are rising, the use of face masks and adequate social distancing are still essential in hospitals, assisted living facilities, and nursing homes. Proper masking is also crucial in clinical settings where distancing isn’t always practical, especially where rates of infection are high. Many healthcare facilities, including the medical center in my area, monitor and enforce masking for employees and patients at entrance and exit points.

Integrating AI with your existing video feeds

Video cameras are common in public healthcare spaces, creating an opportunity to combine existing video feeds with AI and computer vision to monitor compliance with masking and other guidelines to minimize risks unobtrusively. Many institutions have video systems but don’t have much, if any, automation associated with monitoring video feeds, limiting the value of those investments.

An AI model for face mask detection can be applied in various ways to address compliance requirements. For example, it’s possible to monitor public and private entryways to passively assess patients and staff entering a facility. Many facilities assign dedicated staff to monitor entry doors, a practice that might be unnecessary where compliance is high. However, as the percentage of the population that’s vaccinated increases, new problems can emerge. 

Although we haven’t yet implemented the capability, it should be possible to enhance an AI solution to deny entry to a facility or a particular area to anyone who isn’t properly masked. For this system to work, object detection and localization must occur in near real time, requiring inferencing at typical video frame rates. 

NetApp and SFL Scientific have implemented a flexible technology stack to meet the diverse requirements of healthcare and life sciences institutions. Depending on your IT and organizational needs, the NetApp® solution can be implemented on premises through purchase or subscription, or in the cloud through subscription.

Our methodology for face-mask compliance can be readily adapted to other compliance needs in healthcare and beyond. For example, hand washing is crucial for infection control, especially in areas such as ICUs, isolation wards, and operating rooms. A targeted solution could monitor hand-washing compliance in these areas.  Drug wastage and mishandling is another important challenge that many facilities face. An unobtrusive video compliance solution might help hospital pharmacies adhere to proper procedures or identify places where drugs are handled improperly.

To learn more about this topic, read the white paper Deep learning to identify COVID-19 lesions in lung CT scans and visit our AI in healthcare web site.  

Mike McNamara

Mike McNamara is a senior leader of product and solution marketing at NetApp with 25 years of data management and data storage marketing experience. Before joining NetApp over 10 years ago, Mike worked at Adaptec, EMC and HP. Mike was a key team leader driving the launch of the industry’s first cloud-connected AI/ML solution (NetApp), unified scale-out and hybrid cloud storage system and software (NetApp), iSCSI and SAS storage system and software (Adaptec), and Fibre Channel storage system (EMC CLARiiON). In addition to his past role as marketing chairperson for the Fibre Channel Industry Association, he is a member of the Ethernet Technology Summit Conference Advisory Board, a member of the Ethernet Alliance, a regular contributor to industry journals, and a frequent speaker at events. Mike also published a book through FriesenPress titled "Scale-Out Storage - The Next Frontier in Enterprise Data Management", and was listed as a top 50 B2B product marketer to watch by Kapos.

View all Posts by Mike McNamara
Drift chat loading