This study aimed to create a novel, non-invasive approach to predict core temperature (Tc) during heat stress among firefighters. BackgroundThe direct measure of Tc is typically performed through invasive techniques (rectal, esophageal, or intestinal). Existing predictive methods involve complex systems with multiple pieces of impractical equipment or are otherwise unsuitable for the work environment. Here, we hypothesized that a novel, non-invasive algorithm using variables collected from a single piece of commercially available equipment could effectively predict Tc. MethodsThe participants performed a steady-state exercise protocol in an environmental chamber (35 °C, 45% humidity) while donning firefighter personal protective equipment. The variables collected were skin temperature (Tsk), heart rate (HR), time, respiratory rate (RR), and rate of skin temperature acquisition per minute (Tsk/min). ResultsOf the variables collected, all contributed to the multiple regression model, except HR. Tsk/min was calculated using Tsk and time. The initial model created in this study predicted Tc with a standard error of the estimate (SEE) of 0.23 °C and an adjusted R2 of 0.897. Following a "leave-one-out" bootstrap method, a robust equation was created using mean coefficients. This robust equation predicted Tc with a SEE of 0.23 and an R2 of 0.902. DiscussionThis paper provides a practical, non-invasive model to predict Tc with minimal resources. This method has the potential to provide continuous monitoring of firefighters in the field and can be used as a metric to withdraw firefighters when under detrimental physiological stress. Ultimately, this could improve the health and longevity of firefighters.