Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BHNRC) » Beltsville Human Nutrition Research Center » Food Components and Health Laboratory » Research » Publications at this Location » Publication #321296
Title: Automated Guidance from Physiological Sensing to Reduce Thermal-Work Strain Levels on a Novel Task

Author
item BULLER, MARK - Us Army Research Institute Of Environmental Medicine
item WELLES, ALEXANDER - Us Army Research Institute Of Environmental Medicine
item STEVENS, MICHELLE - University Of Maryland
item LEGER, JAYME - University Of Maryland
item GRIBOJ, ANDREI - University Of Tennessee
item Rumpler, William

Submitted to: Meeting Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 5/23/2015
Publication Date: N/A
Citation: N/A

Interpretive Summary: Today, wearable physiological monitors are becoming common place. The daily use of these devices along with smart phones offers the possibility of determining and tracking health state. Automated human health-state monitoring aims to identify when an individual moves from a healthy to a compromised state. For example, changes in diet or physical activity can lead to life-threatening hypo or hyperglycemia in diabetics. In healthy individuals, heavy exertion in hot climates can quickly lead to life threatening over heating and subsequent heat stress or stroke. This study used an software application based on a mathematical model of work load and responses in body temperature. The system estimated an individual’s thermal-work strain health state using measures of heart rate alone and utilized a technique to provide pacing advice based upon an individual’s current thermal-work strain state, overall task goal and thermal safety constraints. The goal of this study was to examine whether this combination of techniques would 1) prevent instances of hyperthermia, and 2) allow individuals to complete the task with less thermal-work strain.

Technical Abstract: This experiment demonstrated that automated pace guidance generated from real-time physiological monitoring allowed least stressful completion of a timed (60 minute limit) 5 mile treadmill exercise. An optimal pacing policy was estimated from a Markov decision process that balanced the goals of the movement task and the thermal-work strain safety constraints. The machine guided pace was based on current physiological strain index (PSI), the time, and the distance completed already. Sixteen healthy and fit young subjects participated in the study (11 men, 5 women). Each participated in an unguided exercise session followed by a guided one. In the unguided session, they were instructed to complete 5 miles in 60 minutes and to try to finish at the lowest body temperature possible; in guided sessions, participants were instructed to match machine-provided guidance within 2 minute epochs. Continuous real-time measures of heart rate and core body temperature were obtained from a wearable Hidalgo EquivitalTM EQ-02 and the MiniMitter Jonah thermometer pill. Of the sixteen subjects, 15 completed 5 miles in one hour for the unguided session; at least three different self-pacing strategies were observed, with an alternating speed proving to be most effective. In the guided sessions, 6 subjects were stopped: 3 for exceeding a Tcore of 39.5 C and 3 were due to incorrect machine-guidance. One very well trained subject matched the machine guided outcome of optimized final thermal state, indicating that machine guided advice was useful to improving outcomes for performers of an unfamiliar task.