Buller et al used body sensors to detect predictors for impending exertional heat stroke. The authors are from the US Army Research Institute of Environmental Medicine, Augusta University, Fort Benning and MIT.
Subjects: athlete, worker or soldier in a hot environment
Subject preparation: chest-worn sensors
Features of exertional heat stroke:
(1) high core body temperature (> 41°C rectal in study subjects)
(2) CNS dysfunction
Predictors:
(1) gait instability (based on three-axis accelerometer), such as ataxia
(2) estimated core body temperature (calculated from sequential measures of heart rate), based on the method of Buller et al (2013)
In Figure 2 it can be seen that the heart rate is > 175 beats per minute prior to collapse, then falls > 10% afterwards, with pulse less than 160.
Performance:
• There was a low false-positive rate (6%).
• The false negative rate was 0%.