Individualized Prediction of Heat Stress in Firefighters: A Data-Driven Approach Using Classification and Regression Trees

Abstract

The purpose of this study was to explore data-driven models, based on decision trees, to develop practical and easy to use predictive models for early identification of firefighters who are likely to cross the threshold of hyperthermia during live-fire training. Predictive models were created for three consecutive live-fire training scenarios. The final predicted outcome was a categorical variable: will a firefighter cross the upper threshold of hyperthermia - Yes/No. Two tiers of models were built, one with and one without taking into account the outcome (whether a firefighter crossed hyperthermia or not) from the previous training scenario. First tier of models included age, baseline heart rate and core body temperature, body mass index, and duration of training scenario as predictors. The second tier of models included the outcome of the previous scenario in the prediction space, in addition to all the predictors from the first tier of models. Classification and regression trees were used independently for prediction. The response variable for the regression tree was the quantitative variable: core body temperature at the end of each scenario. The predicted quantitative variable from regression trees was compared to the upper threshold of hyperthermia (38°C) to predict whether a firefighter would enter hyperthermia. The performance of classification and regression tree models was satisfactory for the second (success rate = 79%) and third (success rate = 89%) training scenarios but not for the first (success rate = 43%). Data-driven models based on decision trees can be a useful tool for predicting physiological response without modeling the underlying physiological systems. Early prediction of heat stress coupled with proactive interventions, such as pre-cooling, can help reduce heat stress in firefighters.

Effects of Heat Exposure from Live-Burn Fire Training on Postural Stability of Firefighters

“…In addition, firefighters also perceived an increase in physical fatigue and respiratory distress (Table 3). These findings are consistent with those reported in literature [13,17]. This is important to consider given that the training exercises are in controlled environments with short rest periods built into the training exercise.…”

“…Upon completion, post scenario 1 balance tests were performed. This was repeated for post scenario 2 and post scenario 3 measurements (Figure 1) [11,13].…”

Uncertainty Analysis of the Core Body Temperature Under Thermal and Physical Stress Using a Three-Dimensional Whole Body Model

“…In the future, evaluating the effect of the variations in ambient conditions, properties of the firefighting suit, and the variation of tissue parameters with temperature can further enhance the applicability of the whole body model. Further, data-driven models have been reported to be effective for short-term prediction of the T c_N of individual firefighters [38,39]. Therefore, individualized prediction of the T c_N for a firefighter could be improved by developing hybrid models which combines the strength of the whole body model and the utility of data-driven predictive models.…”

Ergonomics and Beyond

“…Therefore, early biomarkers and/or predictive model(s) for identifying hyperthermia are important areas of future research to minimize heat-associated injuries and fatality among workers of all ages. Literature provides two models for predicting hyperthermia (core temperature >100.4°F): (a) one based on physiology of heat stress (Yokota, Berglund, Santee, Butler, & Hoyt, 2005; Yokota, Berglund, & Bathalon, 2012; Yokota, Berglund, Santee, et al, 2012) and (b) data-driven decision trees (Mani, Rao, James, & Bhattacharya, 2015). Use of such predictive modeling has a critical role in designing and developing innovative interventions to minimize heat stress in the working population of all ages in hot environments (Mani et al, 2013, 2015), such as firefighters and agricultural and construction workers.…”