With climate change increasing global temperatures, more workers are exposed to hotter ambient temperatures that exacerbate risk for heat injury and illness. Continuously monitoring core body temperature (TC) can help workers avoid reaching unsafe TC. However, continuous TC measurements are currently cost-prohibitive or invasive for daily use. Here, we show that Kenzen’s wearable device can accurately predict TC compared to gold standard TC measurements (rectal probe or gastrointestinal pill). Data from four different studies (n = 52 trials; 27 unique subjects; >4000 min data) were used to develop and validate Kenzen’s machine learning TC algorithm, which uses subject’s real-time physiological data combined with baseline anthropometric data. We show Kenzen’s TC algorithm meets pre-established accuracy criteria compared to gold standard TC: mean absolute error = 0.25 °C, root mean squared error = 0.30 °C, Pearson r correlation = 0.94, standard error of the measurement = 0.18 °C, and mean bias = 0.07 °C. Overall, the Kenzen TC algorithm is accurate for a wide range of TC, environmental temperatures (13–43 °C), light to vigorous heart rate zones, and both biological sexes. To our knowledge, this is the first study demonstrating a wearable device can accurately predict TC in real-time, thus offering workers protection from heat injuries and illnesses.

The need to obtain continuous non‐invasive and accurate measurements of core body temperature (TC) has heightened with the current SARS‐CoV‐2 pandemic, along with exposure to increasingly hotter environmental temperatures in athletic and work settings as a result of climate change. Not only can accurate TC monitoring predict and prevent the spread of contagious illnesses at the worksite, but also can protect workers and athletes from heat‐related injuries and illnesses. Although many non‐invasive solutions currently exist for conducting spot‐checks of TC, the accuracy of these solutions is highly variable, and is dependent upon subject characteristics and their environmental conditions. Therefore, the purpose of this study was to evaluate the accuracy of a new wearable device's TC algorithm in comparison to ground truth TC continuously across 24 h (n=46 male and female subjects for 65 total trials; mean age ± SD=31 ± 12 y; age range=18‐62 y; mean height ± SD=172.2 ± 10.0 cm; mean weight ± SD=72.6±17.9 kg). Subjects ingested a gastrointestinal pill (e‐Celsius, BodyCap Inc.) 1 h prior to the start of each trial, and then went about their normal daily routine while wearing a non‐invasive wearable device around their upper arm (Kenzen Inc.). Kenzen's wearable device continuously monitors heart rate (via PPG), skin and ambient temperature, relative humidity of the skin and environment, and activity (via accelerometry); gastrointestinal temperatures were recorded every 5 min throughout the monitoring period. Subjects either completed one (n=27 subjects) or two trials (n=19 subjects for 38 trials). Based on gastrointestinal pill transit times, trial times ranged from 8.5 to 84.5 h, with a mean trial time of 34.5 h. To our knowledge, this is the largest dataset to date that has collected ground truth TC continuously throughout a 24 h monitoring period, and across two timepoints. See Table 1 for ground truth TC statistics. Overall accuracy of Kenzen vs. ground truth TC: mean absolute error (MAE) = 0.27°C, mean percent error = 0.72%, mean bias = ‐0.07°C, root mean squared error = 0.35°C, limits of agreement = ±0.68°C (see Fig. 1). Subjects’ completing two trials had a similar TC range and circadian rhythm of TC during both trials. Resting heart rate was the single best predictor of the TC range for each subject during their trial (r = –0.41, P=0.01). In conclusion, according to previously established accuracy criteria for TC devices (i.e. MAE ≤0.27°C; Casa et al., JAT, 2007), the Kenzen device can be used as an accurate, non‐invasive measurement of continuous core body temperature, where TC ranges from 36‐41°C.