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.

Active ascent accelerates the time course but not the overall incidence and severity of acute mountain sickness at 3,600 m.

Acute mountain sickness (AMS) typically peaks following the first night at high altitude (HA) and resolves over the next 2-3 days, but the impact of active ascent on AMS is debated. To determine the impact of ascent conditions on AMS, 78 healthy Soldiers (means ± SD; age = 26 ± 5 yr) were tested at baseline residence, transported to Taos, NM (2,845 m), hiked (n = 39) or were driven (n = 39) to HA (3,600 m), and stayed for 4 days. AMS-cerebral (AMS-C) factor score was assessed at HA twice on day 1 (HA1), five times on days 2 and 3 (HA2 and HA3), and once on day 4 (HA4). If AMS-C was ≥0.7 at any assessment, individuals were AMS susceptible (AMS+; n = 33); others were nonsusceptible (AMS-; n = 45). Daily peak AMS-C scores were analyzed. Ascent conditions (active vs. passive) did not impact the overall incidence and severity of AMS at HA1-HA4. The AMS+ group, however, demonstrated a higher (P < 0.05) AMS incidence in the active vs. passive ascent cohort on HA1 (93% vs. 56%), similar incidence on HA2 (60% vs. 78%), lower incidence (P < 0.05) on HA3 (33% vs. 67%), and similar incidence on HA4 (13% vs. 28%). The AMS+ group also demonstrated a higher (P < 0.05) AMS severity in the active vs. passive ascent cohort on HA1 (1.35 ± 0.97 vs. 0.90 ± 0.70), similar score on HA2 (1.00 ± 0.97 vs. 1.34 ± 0.70), and lower (P < 0.05) score on HA3 (0.56 ± 0.55 vs. 1.02 ± 0.75) and HA4 (0.32 ± 0.41 vs. 0.60 ± 0.72). Active compared with passive ascent accelerated the time course of AMS with more individuals sick on HA1 and less individuals sick on HA3 and HA4.NEW & NOTEWORTHY This research demonstrated that active ascent accelerated the time course but not overall incidence and severity of acute mountain sickness (AMS) following rapid ascent to 3,600 m in unacclimatized lowlanders. Active ascenders became sicker faster and recovered quicker than passive ascenders, which may be due to differences in body fluid regulation. Findings from this well-controlled large sample-size study suggest that previously reported discrepancies in the literature regarding the impact of exercise on AMS may be related to differences in the timing of AMS measurements between studies.

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.