Department of Defense Biotechnology High Performance Computing Software Applications Institute, Telemedicine and Advanced Technology Research Center, United States Army Medical Research and Materiel Command, Fort Detrick, Maryland.
Department of Military and Emergency Medicine, Uniformed Services University of the Health Sciences , Bethesda, Maryland.
J Appl Physiol (1985). 2018 Jun 1;124(6):1387-1402. doi: 10.1152/japplphysiol.00837.2017. Epub 2018 Feb 8.
A rising core body temperature (T) during strenuous physical activity is a leading indicator of heat-injury risk. Hence, a system that can estimate T in real time and provide early warning of an impending temperature rise may enable proactive interventions to reduce the risk of heat injuries. However, real-time field assessment of T requires impractical invasive technologies. To address this problem, we developed a mathematical model that describes the relationships between T and noninvasive measurements of an individual's physical activity, heart rate, and skin temperature, and two environmental variables (ambient temperature and relative humidity). A Kalman filter adapts the model parameters to each individual and provides real-time personalized T estimates. Using data from three distinct studies, comprising 166 subjects who performed treadmill and cycle ergometer tasks under different experimental conditions, we assessed model performance via the root mean squared error (RMSE). The individualized model yielded an overall average RMSE of 0.33 (SD = 0.18)°C, allowing us to reach the same conclusions in each study as those obtained using the T measurements. Furthermore, for 22 unique subjects whose T exceeded 38.5°C, a potential lower T limit of clinical relevance, the average RMSE decreased to 0.25 (SD = 0.20)°C. Importantly, these results remained robust in the presence of simulated real-world operational conditions, yielding no more than 16% worse RMSEs when measurements were missing (40%) or laden with added noise. Hence, the individualized model provides a practical means to develop an early warning system for reducing heat-injury risk. NEW & NOTEWORTHY A model that uses an individual's noninvasive measurements and environmental variables can continually "learn" the individual's heat-stress response by automatically adapting the model parameters on the fly to provide real-time individualized core body temperature estimates. This individualized model can replace impractical invasive sensors, serving as a practical and effective surrogate for core temperature monitoring.
在剧烈的体力活动中，核心体温（T）的升高是热损伤风险的主要指标。因此，能够实时估计 T 并提供即将升温的预警的系统，可能使能够采取主动干预措施降低热损伤风险。然而，实时现场评估 T 需要不切实际的侵入性技术。为了解决这个问题，我们开发了一个数学模型，该模型描述了 T 与个体的非侵入性活动测量、心率和皮肤温度以及两个环境变量（环境温度和相对湿度）之间的关系。卡尔曼滤波器使模型参数适应每个个体，并提供实时个性化的 T 估计。使用来自三个不同研究的数据，这些研究包含 166 名在不同实验条件下进行跑步机和自行车测力计任务的受试者，我们通过均方根误差（RMSE）评估了模型性能。个体化模型的总体平均 RMSE 为 0.33（SD=0.18）°C，使我们能够在每项研究中得出与使用 T 测量相同的结论。此外，对于 22 名 T 超过 38.5°C 的独特受试者，即潜在的具有临床意义的较低 T 限值，平均 RMSE 降至 0.25（SD=0.20）°C。重要的是，即使在存在模拟现实操作条件的情况下，这些结果仍然稳健，当测量缺失（40%）或充满附加噪声时，RMSE 增加不超过 16%。因此，个体化模型为开发降低热损伤风险的预警系统提供了一种实用方法。
新的和值得注意的是，一种使用个体的非侵入性测量和环境变量的模型可以通过自动适应模型参数来“持续学习”个体的热应激反应，从而实时提供个性化的核心体温估计。这种个体化模型可以替代不切实际的侵入性传感器，作为核心体温监测的实用且有效的替代方法。
