Predicting Risk of Heat-Related Injuries for Individuals Wearing Personal Protective Equipment Using Smartwatches: Feasibility Observational Study
Bibliographic record
Abstract
Background: The risk of developing heat-related illness increases when personal protective equipment (PPE) is worn, especially in hot and humid environments. While cooling strategies are effective, they must be applied preemptively or delivered promptly, which can be difficult if individuals are working in dangerous environments or wearing contaminated PPE. Wearable sensors can be leveraged to continuously monitor health including heart rate, respiration rate, blood oxygen levels, and physical activity. Objective: This study aims to (1) evaluate the use of wearable sensors for monitoring the real-time health of individuals wearing PPE to mitigate the risk of developing a heat-related illness and enable timely intervention, (2) understand how PPE may affect smartwatch data quality and comfort, and (3) identify circumstances in which people wearing PPE may not be able to wear a smartwatch. Methods: Individuals participating in planned field trainings or exercises where PPE was being worn were asked to wear Garmin Fenix 6 smartwatch (Garmin Ltd) before, during, and after the event to monitor health and recovery. These convenience cohorts were selected to understand the feasibility of using smartwatches with different types of PPE (ie, level C PPE and firefighter gear) for different types of training (ie, a simulated environmental cleanup exercise and skill and tactical maneuver training for new firefighter recruits). Results: Two data collections were conducted using the Garmin Fenix 6 smartwatch to assess wearability, data quality, and data accuracy. For the first effort, participants wore the watch for 3.9-5.1 days, and wear compliance ranged from 83.8% to 99.9%. For the second effort, participants wore the watch for the exercise only, which was 3.5 hours. Participants were able to wear the watches for the entire time that they were wearing PPE and did not report any adverse events. Changes in heart rate corresponded with changes in physical activity, providing evidence that physiology can be acceptably monitored during physical activity. Heart rate data artifact ranged between 5.8% and 9.3% and was highest for the control participant (second data collection) who was not wearing PPE. Conclusions: Based on the results obtained from the 8 pilot users, the Garmin Fenix 6 smartwatch is an appropriate choice for continuously monitoring the health of individuals wearing PPE. The watch can be tolerated for extended wear periods and data quality is sufficient for monitoring heart rate and predicting core body temperature.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".