Determination of Biphasic Menstrual Cycle Based on the Fluctuation of Abdominal Skin Temperature during Sleep

• Published in: Advanced Biomedical Engineering Vol. 12; pp. 28 - 36
• Main Authors: Murayama, Yoshinobu, Uemura, Aiko, Kitazawa, Masumi, Toyotani, Jun, Taniuchi, Asako, Togawa, Tatsuo
• Format: Journal Article
• Language: English
• Published: Kagoshima Japanese Society for Medical and Biological Engineering 2023
• Subjects: Abdomen; abdominal skin temperature; Abdominal wall; Attenuation coefficients; Body temperature; Confidence intervals; Deep learning; fluctuation; Long short-term memory; Menstrual cycle; Menstruation; ovulation; Phases; Skin temperature; Sleep; Statistical analysis; Wearable technology
• ISSN: 2187-5219; 2187-5219
• DOI: 10.14326/abe.12.28

In this study, we focused on the fluctuation of the abdominal skin temperature (AST) during sleep as a second marker for determining the biphasic menstrual cycle, alongside the basal body temperature. The nocturnal AST was measured every 10 min using a wearable device mounted on the abdominal wall. With this system, the AST time-series data were recorded for a total of 1667, 1035, and 1690 days from seven participants for the menstrual/follicular, ovulatory, and luteal phases, respectively. First, the AST fluctuation was evaluated by plotting the cumulative probability distribution (CPD) of changes in AST every 10 min from 0 to 0.7℃. The results showed that the CPD fitted well with an exponential attenuation curve. Second, the mean attenuation coefficients obtained by exponential regression from the CPD data were compared among the three phases. For regular menstrual cycles, the attenuation coefficient was the highest in the menstrual/follicular phase (8.57; 95% confidence interval 8.44–8.70; R2 = 0.983; P < 0.001), followed by the ovulatory phase (7.80; 95% confidence interval 7.65–7.96; R2 = 0.985; P < 0.001) and then the luteal phase (7.24; 95% confidence interval 7.12–7.36; R2 = 0.985; P < 0.001). Finally, we examined whether the attenuation coefficients can be used as an index to classify the three phases by long short-term memory (LSTM)-based deep learning. Consequently, the attenuation coefficient affected the prediction of the menstrual/follicular, ovulatory, and luteal phases with significantly higher F-measures of 0.603, 0.328, and 0.660, respectively. These results suggest that the thermoregulatory system may increase the AST fluctuation in healthy women during the transition from the follicular phase to the ovulatory phase and then to the luteal phase.