New research by the National Institute of Standards and Technology (NIST) utilises AI to predict potentially fatal cardiac events in firefighters

Firefighters, revered for their courage and tenacity, often face grave hazards in their line of duty.

Yet, surprisingly, it’s not fire or smoke inhalation that is the leading cause of on-duty fatalities.

Instead, sudden cardiac death accounts for about 40% of on-duty fatalities, according to recent research.

To tackle this, a team of researchers at the National Institute of Standards and Technology (NIST) and partners have used machine learning, a form of AI, to predict abnormal cardiac rhythms in firefighters.

According to a recent publication, the team hopes their research can lead to the development of a wearable heart monitor for firefighters, providing early warnings for heart troubles.

Developing a life-saving tool for firefighters

Data from the National Fire Protection Association (NFPA) indicates that sudden cardiac death claimed the lives of 36 firefighters on-duty in 2022.

Such incidents occur when an irregular heart rhythm halts the heart’s blood-pumping ability, often due to a heart attack.

It’s a tragic fact that sudden cardiac events kill on-duty firefighters at twice the rate of police officers and four times the rate of other emergency responders.

Chris Brown, a NIST researcher, stated: “Year after year, sudden cardiac events are by far the number one killer of firefighters.”

Beyond the fatalities, these cardiac events can also cause career-ending injuries and long-term disabilities.

The potential of AI in firefighter safety

Firefighters operate in exceptionally strenuous conditions.

Whether carrying heavy objects, climbing stairs, or enduring extreme temperatures with little opportunity to cool down, the physical demand is immense.

Yet, despite discomfort, firefighters often soldier on without realising their potential risk for sudden cardiac death.

To address this problem, NIST researchers collaborated with the University of Rochester School of Nursing.

A decade ago, Rochester researcher Mary Carey and her team collected 24-hour electrocardiogram (ECG) data from 112 firefighters. This unique data set became the basis for their AI model, known as the Heart Health Monitoring (H2M) model.

“The firefighter data we collected is so unique,” Rochester co-author Dillon Dzikowicz stated. “Having robust data is essential to move our work forward and protect firefighters.”

The team used the Rochester dataset and machine learning to train the H2M model. It learned ECG patterns from both normal and abnormal heartbeats, allowing it to predict irregular heart rhythms.

Next steps in firefighter health monitoring

Once trained and validated, H2M analysed new firefighter ECG data, identifying around 6,000 abnormal ECG samples correctly with a 97% accuracy rate.

When trained using non-firefighter data, the H2M model had a 40% error rate, highlighting the importance of the specific dataset.

“Using the right dataset to train the AI model was critical,” said NIST researcher Wai Cheong Tam.

Looking ahead, the researchers believe their model could be incorporated into wearable heart monitors for on-duty firefighters.

Such a tool could provide real-time warnings of cardiac irregularities.

“This technology can save lives,” said Tam.

He envisages the technology being applied more broadly in future, potentially benefiting other first responders and the general public, given the right training data.

IFSJ Comment

International Fire & Safety Journal is eager to follow the development of the H2M model, and its potential deployment in the field.

The capability to predict fatal cardiac events in real-time could drastically improve the safety of our firefighters and other first responders.

By tackling the leading cause of on-duty fatalities, this technology could revolutionise safety procedures within the firefighting community and beyond.

About NIST

The National Institute of Standards and Technology (NIST), an agency of the US Department of Commerce, is at the forefront of advancements in measurement science, standards, and technology.

With a mission to promote innovation and industrial competitiveness, NIST’s groundbreaking research continues to push the boundaries of scientific exploration.

The institute’s research on the prediction of fatal cardiac events in firefighters underscores their commitment to leveraging technology for societal benefits.