Modeling menstrual cycle phases from urinary hormone trajectories using an autoregressive hidden Markov model

The recent availability of at-home menstrual cycle tracking technology has created opportunities for personalized assessment of reproductive health, alongside improved characterization of hormone patterns in women with and without reproductive disorders such as polyendocrine metabolic ovarian syndrome (PMOS), which affects approximately 10% of reproductive-age women. In this study, we leverage self-tracked urinary hormone data to develop an autoregressive Hidden Markov model (arHMM) that maps cycle days to physiologically meaningful phases based on hormone trajectories. By modeling day-to-day hormonal dynamics rather than absolute hormone levels, and allowing variable phase durations, this approach accommodates substantial variability in menstrual cycles, thereby enabling meaningful comparisons within and between individuals. Across more than 3800 cycles from over 1100 individuals, we find that arHMM-derived phases reproduce expected hormonal patterns within follicular, periovulatory, and luteal phases, and that phase-based timing for hormone testing outperforms conventional cycle day–based testing in capturing the luteinizing hormone surge and post-ovulatory progesterone rise, highlighting limitations of fixed-day clinical protocols. We identify phase-specific differences between healthy controls and individuals with self-reported PMOS, including lower luteinizing hormone in the periovulatory phase, and reduced luteal phase progesterone levels in PMOS. Furthermore, features derived from arHMM phase assignments show the potential for non-invasive PMOS screening using machine learning classification.Author summary: Tracking menstrual cycle information has become increasingly common, thanks in part to the availability of at-home urinary hormone data tracking technologies. In this study, we leveraged data from more than 3,800 menstrual cycles contributed by over 1,100 individuals in order to develop a model that predicts physiologically meaningful cycle phases based on day-to-day hormone patterns, exploring the potential of this model to provide ovulation proxies, improve clinical testing, and screen for reproductive disorders such as PMOS, a common endocrine disorder affecting approximately 1 in 10 reproductive age women. This study demonstrates the power of physiologically informed probabilistic modeling for leveraging data from at-home hormone monitoring towards a better characterization of menstrual cycle physiology and the development of noninvasive approaches for identifying reproductive health conditions such as PMOS.