For lab managers and safety officers, the COVID-19 pandemic was a masterclass in the complexities of personal protective equipment (PPE). From supply chain collapses to the nuances of fit-testing, PPE became the frontline of workplace safety. However, understanding the specific, evolving challenges faced by workers across the US is a monumental data task.

New research from the National Institute for Occupational Safety and Health (NIOSH) suggests that the answer lies in machine learning. By applying AI to Occupational Safety and Health Administration (OSHA) complaint data, researchers Nora Payne and Emily Haas have developed a way to turn thousands of anecdotal reports into actionable intelligence.

Integrating machine learning to monitor PPE compliance

When workers face safety risks, they turn to OSHA. During the peak of the pandemic, these complaints surged, providing a raw, unfiltered look at the workforce's struggles. But there was a problem: the volume of data was too massive for manual analysis to provide timely help. Using machine learning to monitor these concerns and track their evolution over time is a cost-effective way to learn about the challenges workers face.

Training the model on real-world complaints

To bridge the gap between raw data and insight, the NIOSH team manually reviewed approximately 3,000 pandemic-related PPE complaints filed between January 2020 and July 2022. This manual review served as the foundation for training a machine learning model, which was then tested for accuracy in detecting specific PPE-related grievances.

The study revealed that nearly 40 percent of all pandemic-related OSHA complaints involved at least one PPE issue. While concerns ranged from physical discomfort and poor fit to a lack of proper training, the machine learning model proved particularly adept at identifying three critical categories:

• Availability—a lack of necessary PPE
• Employer enforcement—management failing to require PPE use
• Worker compliance—employees not wearing the provided gear

Strengthening lab safety through real-time risk assessment

Perhaps the most significant insight was how these concerns shifted over time. In the summer of 2020, as sectors began to reopen, the data showed a distinct pivot. Worker concerns shifted from a lack of supplies to a struggle with enforcement. As workplaces grew crowded, workers became more worried about following the rules than about the gear being in the building.

Lab Management Certificate

The Lab Management certificate is more than training—it’s a professional advantage.

Gain critical skills and IACET-approved CEUs that make a measurable difference.

For the laboratory community and public health agencies, this methodology offers a roadmap for future outbreaks. By identifying these patterns in near real time, lab managers can make more informed decisions about where to allocate resources and what specific guidance or interventions are needed for their teams.

The NIOSH team is now looking for ways to improve the approach. Their long-term goal is to develop a system that tracks PPE-related concerns in worker safety complaints as they happen. In an environment where the next infectious disease challenge may be just around the corner, the ability to listen—and respond—to the worker's voice through the lens of machine learning could be a life-saving innovation.

Data-driven strategies for lab leadership and safety culture

This research provides a framework for lab managers to transition from reactive troubleshooting to proactive leadership. By analyzing patterns in OSHA complaints, managers can determine where to prioritize their time and budget.

The data suggests that a high frequency of enforcement-related concerns often requires shifting focus from procurement to leadership training and behavioral safety audits. These AI-driven insights help management distinguish between a supply chain failure and a systemic cultural issue. By leveraging this data, managers can implement targeted interventions—such as refined fit-testing protocols or peer-to-peer safety coaching—that address the root causes of workforce risk and anxiety.

This article was created with the assistance of Generative AI and has undergone editorial review before publishing.