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

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