Early Prediction of Impending Exertional Heat Stroke With Wearable Multimodal Sensing and Anomaly Detection.

We employed wearable multimodal sensing (heart rate and triaxial accelerometry) with machine learning to enable early prediction of impending exertional heat stroke (EHS). US Army Rangers and Combat Engineers (N = 2,102) were instrumented while participating in rigorous 7-mile and 12-mile loaded rucksack timed marches. There were three EHS cases, and data from 478 Rangers were analyzed for model building and controls. The data-driven machine learning approach incorporated estimates of physiological strain (heart rate) and physical stress (estimated metabolic rate) trajectories, followed by reconstruction to obtain compressed representations which then fed into anomaly detection for EHS prediction. Impending EHS was predicted from 33 to 69 min before collapse. These findings demonstrate that low dimensional physiological stress to strain patterns with machine learning anomaly detection enables early prediction of impending EHS which will allow interventions that minimize or avoid pathophysiological sequelae. We describe how our approach can be expanded to other physical activities and enhanced with novel sensors.

Individualized monitoring of heat illness risk: novel adaptive physiological strain index to assess exercise-heat strain from athletes to fully encapsulated workers.

Objective. Exercise-heat strain estimation approaches often involve combinations of body core temperature (Tcore), skin temperature (Tsk) and heart rate (HR). A successful existing measure is the 'Physiological Strain Index' (PSI), which combines HR and Tcore values to estimate strain. However, depending on variables such as aerobic fitness and clothing, the equation's 'maximal/critical' Tcore must be changed to accurately represent the strain, in part because high Tsk (small Tcore-Tsk) can increase cardiovascular strain and thereby negatively affect performance. Here, an 'adaptive PSI' (aPSI) is presented where the original PSI Tcorecriticalvalue is 'adapted' dynamically by the delta between Tcore and Tsk.Approach. PSI and aPSI were computed for athletes (ELITE,N= 11 male and 8 female, 8 km time-trial) and soldiers in fully encapsulating personal protective equipment (PPE,N= 8 male, 2 km approach-march). While these were dissimilar events, it was anticipated given that the clothing and work rates would elicit similar very-high exercise-heat strain values.Main results. Mean end HR values were similar (∼180 beats min-1) with higher Tcore = 40.1 ± 0.4 °C for ELITE versus PPE 38.4 ± 0.6 °C (P< 0.05). PSI end values were different between groups (P< 0.01) and appeared 'too-high' for ELITE (11.4 ± 0.8) and 'too-low' for PPE (7.6 ± 2.0). However, aPSI values were not different (9.9 ± 1.4 versus 9.0 ± 2.5 versus;p> 0.05) indicating a 'very high' level of exercise-heat strain for both conditions.Significance. A simple adaptation of the PSI equation, which accounts for differences in Tcore-to-Tsk gradients, provides a physiological approach to dynamically adapt PSI to provide a more accurate index of exercise-heat strain under very different working conditions.

Gait instability and estimated core temperature predict exertional heat stroke.

OBJECTIVE: Exertional heat stroke (EHS), characterised by a high core body temperature (Tcr) and central nervous system (CNS) dysfunction, is a concern for athletes, workers and military personnel who must train and perform in hot environments. The objective of this study was to determine whether algorithms that estimate Tcr from heart rate and gait instability from a trunk-worn sensor system can forward predict EHS onset. METHODS: Heart rate and three-axis accelerometry data were collected from chest-worn sensors from 1806 US military personnel participating in timed 4/5-mile runs, and loaded marches of 7 and 12 miles; in total, 3422 high EHS-risk training datasets were available for analysis. Six soldiers were diagnosed with heat stroke and all had rectal temperatures of >41°C when first measured and were exhibiting CNS dysfunction. Estimated core temperature (ECTemp) was computed from sequential measures of heart rate. Gait instability was computed from three-axis accelerometry using features of pattern dispersion and autocorrelation. RESULTS: The six soldiers who experienced heat stroke were among the hottest compared with the other soldiers in the respective training events with ECTemps ranging from 39.2°C to 40.8°C. Combining ECTemp and gait instability measures successfully identified all six EHS casualties at least 3.5 min in advance of collapse while falsely identifying 6.1% (209 total false positives) examples where exertional heat illness symptoms were neither observed nor reported. No false-negative cases were noted. CONCLUSION: The combination of two algorithms that estimate Tcr and ataxic gate appears promising for real-time alerting of impending EHS.