Time-motion analysis in the big data era: A promising method to assess the effects of heat stress on physical performance

The negative effects of heat stress on health, physiologic function and capacity to perform prolonged exercise or work are well described in literature. However, it remains difficult to quantify the detrimental effects of heat exposure on physical functioning without using invasive measurement equipment. Alternatively, time-motion analysis, in which movement and time spent on each movement is examined using video analysis, can be used to obtain insight into the physiological demands and movement patterns of an individual [1]. In the current study, Ioannou and colleagues explored the applicability of time-motion analysis to determine the impact of heat stress on labor loss in agriculture workers [2]. For this purpose, the authors assessed the impact of wet bulb globe temperature (WBGT) on work time spent in irregular work breaks of grape-picking workers [2]. Quantitative information was extracted from time-motion analysis of video data to examine the impact of heat stress on occupational productivity.

Ioannou et al. demonstrated that 12.4% of the total work shift time was lost on irregular breaks in which the majority of the breaks were observed in the middle 4-h period of the work shift. More importantly, a higher total break time and a decreased duration of uninterrupted labor was found with an increasing WBGT and skin temperature [2]. These findings show that workplace heat stress leads to a reduced productivity of agriculture workers. The present study also demonstrates that time-motion analysis is a valuable tool to provide detailed insight into behavioral thermoregulation and its impact on physical performance.

An important limitation of this research technique is the time needed to perform the frame by frame analysis of video footage. For example, 1,920 minutes of data were collected per subject (n = 7), whereas the ratio of video recording to time-motion analyses was 1:1.33 due to regular breaks for the researchers that performed the analyses. This time-consuming manual process may hamper implementation of time-motion analysis in larger occupational studies and/or the field of thermo-physiology in general. On the other hand, technological advances in data sciences may contribute to the introduction of (semi-)automated analyses of video frames in the present big data era. Artificial intelligence derived algorithms can already recognize human motion from video [3]. Future application of machine learning and deep learning techniques may further aid the development of software that can process video footage more quickly.

In the absence of time constraints, time-motion analysis could be a valuable tool to monitor the effects of heat stress on physical performance in occupational and sports settings. Information about thermal stress induced changes in an athlete's individual speed, duration of each movement, total distance covered and work-rest ratio provides insight in the detrimental effects of the heat. For example, tennis players are allowed to have a time interval of maximally 20 seconds in between two points, which is known to increase during hot ambient conditions [4]. If time intervals are exceeded too frequently due to heat-related fatigue, the umpire may use this information to allow extra breaks during the match. Alternatively, time-motion analysis can be used to identify players of team sports who demonstrated the largest decrements in performance outcomes (i.e. covered distance, exercise intensity, sprinting velocity and power output) in hot ambient conditions compared to moderate conditions. The coach can use this information to apply individualized strategies to reduce heat stress (i.e. pre- or percooling or extra acclimatization) or to exclude players who are at risk of performance decrements while competing in the heat [5].

Taken together, the study by Ioannou and colleagues demonstrated that time-motion analysis is a useful tool to assess occupational heat stress induced labor loss. As global warming is expected to increase the prevalence and magnitude of environmental heat stress during daily life activities and sports, novel methods to quantify the detrimental effects of heat exposure are warranted. Time-motion analysis using smart data science algorithms may facilitate the needs of laborers, employers, scientists, athletes and coaches.