Machine learning model for menstrual cycle phase classification and ovulation day detection based on sleeping heart rate under free-living conditions.

The accurate classification of menstrual cycle phases and detection of ovulation is critical for women's health management, particularly in addressing infertility, alleviating premenstrual syndrome, and preventing hormone-related disorders. However, traditional basal body temperature (BBT) measurement methods are susceptible to disruptions in sleep timing and environmental conditions, limiting practical application. This study is aimed to overcome these limitations by introducing a novel feature, heart rate at the circadian rhythm nadir (minHR), for classifying menstrual cycle phases and predicting ovulation. A machine learning model was developed using XGBoost, and data were collected under free-living conditions from 40 healthy women (18-34 years) over a maximum of three menstrual cycles. Three feature combinations- "day," "day + minHR," and "day + BBT"-were evaluated, and model performance was assessed using nested leave-one-group-out cross-validation. The feature "day" represents the number of days elapsed since the onset of menstruation. Participants were stratified into groups depending on high variability and low variability in sleep timing. Results demonstrated that adding minHR significantly improved luteal phase classification and ovulation day detection performance compared to "day" only. Furthermore, in participants with high variability in sleep timing, the minHR-based model outperformed the BBT-based model, significantly improving luteal phase recall and reducing ovulation day detection absolute errors by 2 d (p < 0.05). These findings highlight the robustness and practicality of the minHR-based model for menstrual cycle tracking, particularly in individuals with high variability in sleep timing. The proposed model holds great promise for personalized health management and large-scale epidemiological research.