AI model from NIST able to predict potential cardiac arrest in firefighters
Thank you for choosing Automatic Translation. Currently we are offering translations from English into French and German, with more translation languages to be added in the near future. Please be aware that these translations are generated by a third party AI software service. While we have found that the translations are mostly correct, they may not be perfect in every case. To ensure the information you read is correct, please refer to the original article in English. If you find an error in a translation which you would like to bring to our attention, it would help us greatly if you let us know. We can correct any text or section, once we are aware of it. Please do not hesitate to contact our webmaster to let us know of any translation errors.
Researchers at the National Institute of Standards and Technology (NIST) and their colleagues have used machine learning to accurately identify abnormal cardiac rhythms in firefighters - which in turn could help a firefighter get out in time to avoid death by cardiac arrest.
The research team claims that once the AI model was familiar with firefighter-specific medical data, it was able to identify 6,000 abnormal ECG samples with 97% accuracy, reports Nist.gov.
The researchers hope their work will eventually lead to a portable heart monitor that firefighters could wear to catch early warning signs of heart trouble and prompt them to seek medical attention before it’s too late.
According to the article, most deaths for (American) firefighters on duty are not directly caused by fire or smoke inhalation. As much as approximately 40% of on-duty fatalities in the US reportedly come from sudden cardiac events, leading to cardiac arrest.
(The relative number of fatal cardiac events for Canadian firefighters are very different. See our reference to a Canadian study later in this article!)
The team, which includes researchers from NIST, the University of Rochester and Google, published its results in the Fire Safety Journal.
“Year after year, sudden cardiac events are by far the number one killer of firefighters,” said NIST researcher Chris Brown. “Cardiac events also cause career-ending injuries and long-term disabilities.”
According to the National Fire Protection Association (NFPA) sudden cardiac death claimed the lives of 36 firefighters on duty in the United States during 2022.
Sudden cardiac death occurs when an irregular heart rhythm causes the heart to stop pumping blood, most commonly due to a heart attack. Sudden cardiac events kill on-duty firefighters at twice the rate of police officers and four times the rate of other emergency responders, according to the article.
Firefighters work in remarkably strenuous environments, carrying heavy objects, climbing stairs, and enduring extreme temperatures with a limited ability to cool off. And while they may experience significant discomfort, reports have shown that firefighters often try to push through these situations without realizing they may be at risk for sudden cardiac death.
To address this issue, the NIST researchers got in touch with colleagues from the University of Rochester School of Nursing. A decade ago, Rochester researcher Mary Carey and her colleagues collected 24 hours of electrocardiogram (ECG) data from each of 112 firefighters, who had electrodes strapped to their chests.
The ECG data encompassed 16-hour on-duty shifts and eight-hour off-duty shifts during which the firefighters engaged in their daily activities such as answering fire and medical calls, exercising, eating, resting and sleeping.
“The firefighter data we collected is so unique,” said Rochester co-author Dillon Dzikowicz. “Having robust data is essential to move our work forward and protect firefighters.”
The researchers then used machine learning and the Rochester dataset to build what they call the Heart Health Monitoring (H2M) model. They trained H2M with 12-second segments of a large portion of the ECG data. Individual heartbeats in the ECGs were classified as normal beats or abnormal beats indicative of irregular heart rhythms such as an atrial fibrillation or ventricular tachycardia.
“The model is designed to effectively learn ECG patterns from both normal and abnormal beats,” said NIST guest researcher Jiajia Li.
Most cardiac events had underlying coronary narrowing
In a recent study, researchers concluded that roughly one in five cardiac cases were heart attack deaths; 82 percent of those deaths were related to coronary heart disease (narrowing of the heart arteries or enlarged hearts). This ties to an increase in risk of sudden cardiac death.
The newsroom at Heart.org published a study in 2018, indicating that underlying heart diseases are common among firefighters who die of cardiac arrest.
Analysis of autopsy records for U.S. male firefighters who died on duty between 1999 and 2014 showed that of 627 total deaths, 276 resulted from cardiac arrest and 351 from trauma. At the time of death, the firefighters were between 18 and 65 years old.
In this 2013 photo, nurse scientists Becki Vincent and Mary Carey from the University of Rochester collect electrocardiogram data from a firefighter at the Dewey Avenue Firehouse in Rochester, New York. Now, a decade later, researchers at NIST, Rochester and Google have used this data to train an AI model to predict cardiac events.
Credit: Karen O'Hern/University of Rochester School of Nursing
Environmental and stress factors also contributors to cardiac events
Exposure to smoke, soot and chemicals, as well as disrupted sleep patterns and high levels of occupational stress might all contribute to heart problems. Research indicates that the stress of firefighting can trigger a cardiac event in individuals with underlying disease. The study had limitations but the results offer evidence of the dangers of high-stress, physically demanding jobs for people with underlying heart disease, according to the article.
Less cardiac related deaths among Canadian firefighters
Even though cancer is still the leading cause of firefighter death also in the US, the numbers for cardiac related deaths are different in Canada. In a study published by the University of Fraser Valley and The Workers Compensation Board of Canada, cardiac events makes up a much smaller proportion of firefighter deaths in Canada than in the US.
Of the 738 firefighter fatalities reported in Canada between 2009 and 2018 by the AWCBC, approximately 74.5% of deaths (550) were caused by malignant neoplasms and tumors. When adding 94 other cancer-related fatalities coded as unspecified or not elsewhere classified, 90% of firefighter deaths in Canada are attributable to a form of cancer according to the study.
CTIF is actively seeking similar numbers and statistics for firefighter deaths in Europe and other parts of the world. If you know of studies on this topic (in any language) please do not hesitate to contact us.
Cover photo above: Pixabay Free License. https://pixabay.com/fi/photos/heart-attack-sairaus-terveytt%C3%A4-7479253/
Other photos in article: Mary Carey, University of Rochester School of Nursing