Tracking body core temperature in military thermal environments: An extended Kalman filter approach

Abstract

Military personnel operating in hot and humid environments are susceptible to heat-related illnesses. As heat-related illnesses are associated with a rise in body core temperature (Tc), a reliable system for real-time assessment of Tc is useful to minimize heat casualties. However, invasive measurement of Tc (such as rectal, intestinal and esophageal temperature) is impractical in the field settings. This paper describes the model construction and qualification results of tracking Tc using an extended Kalman filter (EKF) based on physiological data recorded from wearable sensors. Tc, surface skin temperature (Tsk) and heart rate (HR) data were collected from three studies with different experimental protocols, climatic conditions and soldier volunteers. The predictive performance of the model was evaluated by cross-validation and external validation. The final EKF model was implemented using a nonlinear (cubic) state-space model (Tsk versus Tc) with a stage-wise, autoregressive exogenous model (incorporating HR) as the time update model. Overall, when tested against an independent dataset, the model showed a prediction bias of 0.11°C, a root mean square deviation of 0.29°C, and 87% of all Tc predictions fell within ±0.3°C of the measured Tc values. The results from our study indicate that the derived EKF model is accurate enough to calculate subject-specific Tc for the minimization of heat injuries.