Wearable Sensors Reveal Menses-Driven Changes in Physiology and Enable Prediction of the Fertile Window: Observational Study.

Previous research examining physiological changes across the menstrual cycle has considered biological responses to shifting hormones in isolation. Clinical studies, for example, have shown that women's nightly basal body temperature increases from 0.28 to 0.56 ˚C following postovulation progesterone production. Women's resting pulse rate, respiratory rate, and heart rate variability (HRV) are similarly elevated in the luteal phase, whereas skin perfusion decreases significantly following the fertile window's closing. Past research probed only 1 or 2 of these physiological features in a given study, requiring participants to come to a laboratory or hospital clinic multiple times throughout their cycle. Although initially designed for recreational purposes, wearable technology could enable more ambulatory studies of physiological changes across the menstrual cycle. Early research suggests that wearables can detect phase-based shifts in pulse rate and wrist skin temperature (WST). To date, previous work has studied these features separately, with the ability of wearables to accurately pinpoint the fertile window using multiple physiological parameters simultaneously yet unknown. In this study, we probed what phase-based differences a wearable bracelet could detect in users' WST, heart rate, HRV, respiratory rate, and skin perfusion. Drawing on insight from artificial intelligence and machine learning, we then sought to develop an algorithm that could identify the fertile window in real time. We conducted a prospective longitudinal study, recruiting 237 conception-seeking Swiss women. Participants wore the Ava bracelet (Ava AG) nightly while sleeping for up to a year or until they became pregnant. In addition to syncing the device to the corresponding smartphone app daily, women also completed an electronic diary about their activities in the past 24 hours. Finally, women took a urinary luteinizing hormone test at several points in a given cycle to determine the close of the fertile window. We assessed phase-based changes in physiological parameters using cross-classified mixed-effects models with random intercepts and random slopes. We then trained a machine learning algorithm to recognize the fertile window. We have demonstrated that wearable technology can detect significant, concurrent phase-based shifts in WST, heart rate, and respiratory rate (all P<.001). HRV and skin perfusion similarly varied across the menstrual cycle (all P<.05), although these effects only trended toward significance following a Bonferroni correction to maintain a family-wise alpha level. Our findings were robust to daily, individual, and cycle-level covariates. Furthermore, we developed a machine learning algorithm that can detect the fertile window with 90% accuracy (95% CI 0.89 to 0.92). Our contributions highlight the impact of artificial intelligence and machine learning's integration into health care. By monitoring numerous physiological parameters simultaneously, wearable technology uniquely improves upon retrospective methods for fertility awareness and enables the first real-time predictive model of ovulation.

Goodale BM ，Shilaih M ，Falco L ，Dammeier F ，Hamvas G ，Leeners B ... -  《JOURNAL OF MEDICAL INTERNET RESEARCH》

Oura Ring as a Tool for Ovulation Detection: Validation Analysis.

Oura Ring is a wearable device that estimates ovulation dates using physiology data recorded from the finger. Estimating the ovulation date can aid fertility management for conception or nonhormonal contraception and provides insights into follicular and luteal phase lengths. Across the reproductive lifespan, changes in these phase lengths can serve as a biomarker for reproductive health. We assessed the strengths, weaknesses, and limitations of using physiology from the Oura Ring to estimate the ovulation date. We compared performance across cycle length, cycle variability, and participant age. In each subgroup, we compared the algorithm's performance with the traditional calendar method, which estimates the ovulation date based on an individual's last period start date and average menstrual cycle length. The study sample contained 1155 ovulatory menstrual cycles from 964 participants recruited from the Oura Ring commercial database. Ovulation prediction kits served as a benchmark to evaluate the performance. The Fisher test was used to determine an odds ratio to assess if ovulation detection rate significantly differed between methods or subgroups. The Mann-Whitney U test was used to determine if the accuracy of the estimated ovulation date differed between the estimated and reference ovulation dates. The physiology method detected 1113 (96.4%) of 1155 ovulations with an average error of 1.26 days, which was significantly lower (U=904942.0, P<.001) than the calendar method's average error of 3.44 days. The physiology method had significantly better accuracy across all cycle lengths, cycle variability groups, and age groups compared with the calendar method (P<.001). The physiology method detected fewer ovulations in short cycles (odds ratio 3.56, 95% CI 1.65-8.06; P=.008) but did not differ between typical and long or abnormally long cycles. Abnormally long cycle lengths were associated with decreased accuracy (U=22,383, P=.03), with a mean absolute error of 1.7 (SEM .09) days compared with 1.18 (SEM .02) days. The physiology method was not associated with differences in accuracy across age or typical cycle variability, while the calendar method performed significantly worse in participants with irregular cycles (U=21,643, P<.001). The physiology method demonstrated superior accuracy over the calendar method, with approximately 3-fold improvement. Calendar-based fertility tracking could be used as a backup in cases of insufficient physiology data but should be used with caution, particularly for individuals with irregular menstrual cycles. Our analyses suggest the physiology method can reliably estimate ovulation dates for adults aged 18-52 years, across a variety of cycle lengths, and in users with regular or irregular cycles. This method may be used as a tool to improve fertile window estimation, which can aid in conceiving or preventing pregnancies. This method also offers a low-effort solution for follicular and luteal phase length tracking, which are key biomarkers for reproductive health.

Thigpen N ，Patel S ，Zhang X 《JOURNAL OF MEDICAL INTERNET RESEARCH》

Cervical mucus patterns and the fertile window in women without known subfertility: a pooled analysis of three cohorts.

What is the normal range of cervical mucus patterns and number of days with high or moderate day-specific probability of pregnancy (if intercourse occurs on a specific day) based on cervical mucus secretion, in women without known subfertility, and how are these patterns related to parity and age? The mean days of peak type (estrogenic) mucus per cycle was 6.4, the mean number of potentially fertile days was 12.1; parous versus nulliparous, and younger nulliparous (<30 years) versus older nulliparous women had more days of peak type mucus, and more potentially fertile days in each cycle. The rise in estrogen prior to ovulation supports the secretion of increasing quantity and estrogenic quality of cervical mucus, and the subsequent rise in progesterone after ovulation causes an abrupt decrease in mucus secretion. Cervical mucus secretion on each day correlates highly with the probability of pregnancy if intercourse occurs on that day, and overall cervical mucus quality for the cycle correlates with cycle fecundability. No prior studies have described parity and age jointly in relation to cervical mucus patterns. This study is a secondary data analysis, combining data from three cohorts of women: 'Creighton Model MultiCenter Fecundability Study' (CMFS: retrospective cohort, 1990-1996), 'Time to Pregnancy in Normal Fertility' (TTP: randomized trial, 2003-2006), and 'Creighton Model Effectiveness, Intentions, and Behaviors Assessment' (CEIBA: prospective cohort, 2009-2013). We evaluated cervical mucus patterns and estimated fertile window in 2488 ovulatory cycles of 528 women, followed for up to 1 year. Participants were US or Canadian women age 18-40 years, not pregnant, and without any known subfertility. Women were trained to use a standardized protocol (the Creighton Model) for daily vulvar observation, description, and recording of cervical mucus. The mucus peak day (the last day of estrogenic quality mucus) was used as the estimated day of ovulation. We conducted dichotomous stratified analyses for cervical mucus patterns by age, parity, race, recent oral contraceptive use (within 60 days), partial breast feeding, alcohol, and smoking. Focusing on the clinical characteristics most correlated to cervical mucus patterns, linear mixed models were used to assess continuous cervical mucus parameters and generalized linear models using Poisson regression with robust variance were used to assess dichotomous outcomes, stratifying by women's parity and age, while adjusting for recent oral contraceptive use and breast feeding. The majority of women were <30 years of age (75.4%) (median 27; IQR 24-29), non-Hispanic white (88.1%), with high socioeconomic indicators, and nulliparous (70.8%). The mean (SD) days of estrogenic (peak type) mucus per cycle (a conservative indicator of the fertile window) was 6.4 (4.2) days (median 6; IQR 4-8). The mean (SD) number of any potentially fertile days (a broader clinical indicator of the fertile window) was 12.1 (5.4) days (median 11; IQR 9-14). Taking into account recent oral contraceptive use and breastfeeding, nulliparous women age ≥30 years compared to nulliparous women age <30 years had fewer mean days of peak type mucus per cycle (5.3 versus 6.4 days, P = 0.02), and fewer potentially fertile days (11.8 versus 13.9 days, P < 0.01). Compared to nulliparous women age <30 years, the likelihood of cycles with peak type mucus ≤2 days, potentially fertile days ≤9, and cervical mucus cycle score (for estrogenic quality of mucus) ≤5.0 were significantly higher among nulliparous women age ≥30 years, 1.90 (95% confidence interval (CI) 1.18, 3.06); 1.46 (95% CI 1.12, 1.91); and 1.45 (95% CI 1.03, 2.05), respectively. Between parous women, there was little difference in mucus parameters by age. Thresholds set a priori for within-woman variability of cervical mucus parameters by cycle were examined as follows: most minus fewest days of peak type mucus >3 days (exceeded by 72% of women), most minus fewest days of non-peak type mucus >4 days (exceeded by 54% of women), greatest minus least cervical mucus cycle score >4.0 (exceeded by 73% of women), and most minus fewest potentially fertile days >8 days (found in 50% of women). Race did not have any association with cervical mucus parameters. Recent oral contraceptive use was associated with reduced cervical mucus cycle score and partial breast feeding was associated with a higher number of days of mucus (both peak type and non-peak type), consistent with prior research. Among the women for whom data were available (CEIBA and TTP), alcohol and tobacco use had minimal impact on cervical mucus parameters. We did not have data on some factors that may impact ovulation, hormone levels, and mucus secretion, such as physical activity and body mass index. We cannot exclude the possibility that some women had unknown subfertility or undiagnosed gynecologic disorders. Only 27 women were age 35 or older. Our study participants were geographically dispersed but relatively homogeneous with regard to race, ethnicity, income, and educational level, which may limit the generalizability of the findings. Patterns of cervical mucus secretion observed by women are an indicator of fecundity and the fertile window that are consistent with the known associations of age and parity with fecundity. The number of potentially fertile days (12 days) is likely greater than commonly assumed, while the number of days of highly estrogenic mucus (and higher probability of pregnancy) correlates with prior identifications of the fertile window (6 days). There may be substantial variability in fecundability between cycles for the same woman. Future work can use cervical mucus secretion as an indicator of fecundity and should investigate the distribution of similar cycle parameters in women with various reproductive or gynecologic pathologies. Funding for the three cohorts analyzed was provided by the Robert Wood Johnson Foundation (CMFS), the Eunice Kennedy Shriver National Institute of Child Health and Human Development (TTP), and the Office of Family Planning, Office of Population Affairs, Health and Human Services (CEIBA). The authors declare that they have no conflict of interest. N/A.

Najmabadi S ，Schliep KC ，Simonsen SE ，Porucznik CA ，Egger MJ ，Stanford JB ... -  《-》

Performance of algorithms using wrist temperature for retrospective ovulation day estimate and next menses start day prediction: a prospective cohort study.

Can algorithms using wrist temperature, available on compatible models of iPhone and Apple Watch, retrospectively estimate the day of ovulation and predict the next menses start day? Algorithms using wrist temperature can provide retrospective ovulation estimates and next menses start day predictions for individuals with typical or atypical cycle lengths. Wrist skin temperature is affected by hormonal changes associated with the menstrual cycle and can be used to estimate the timing of cycle events. We conducted a prospective cohort study of 262 menstruating females (899 menstrual cycles) aged 14 and older who logged their menses, performed urine LH testing to define day of ovulation, recorded daily basal body temperature (BBT), and collected overnight wrist temperature. Participants contributed between 2 and 13 menstrual cycles. Algorithm performance was evaluated for three algorithms: one for retrospective ovulation day estimate in ongoing cycles (Algorithm 1), one for retrospective ovulation day estimate in completed cycles (Algorithm 2), and one for prediction of next menses start day (Algorithm 3). Each algorithm's performance was evaluated under multiple scenarios, including for participants with all typical cycle lengths (23-35 days) and those with some atypical cycle lengths (<23, >35 days), in cycles with the temperature change of ≥0.2°C typically associated with ovulation, and with any temperature change included. Two hundred and sixty participants provided 889 cycles. Algorithm 1 provided a retrospective ovulation day estimate in 80.5% of ongoing menstrual cycles of all cycle lengths with ≥0.2°C wrist temperature signal with a mean absolute error (MAE) of 1.59 days (95% CI 1.45, 1.74), with 80.0% of estimates being within ±2 days of ovulation. Retrospective ovulation day in an ongoing cycle (Algorithm 1) was estimated in 81.9% (MAE 1.53 days, 95% CI 1.35, 1.70) of cycles for participants with all typical cycle lengths and 77.7% (MAE 1.71 days, 95% CI 1.42, 2.01) of cycles for participants with atypical cycle lengths. Algorithm 2 provided a retrospective ovulation day estimate in 80.8% of completed menstrual cycles with ≥0.2°C wrist temperature signal with an MAE of 1.22 days (95% CI 1.11, 1.33), with 89.0% of estimates being within ±2 days of ovulation. Wrist temperature provided the next menses start day prediction (Algorithm 3) at the time of ovulation estimate (89.4% within ±3 days of menses start) with an MAE of 1.65 (95% CI 1.52, 1.79) days in cycles with ≥0.2°C wrist temperature signal. There are several limitations, including reliance on LH testing to identify ovulation, which may mislabel some cycles. Additionally, the potential for false retrospective ovulation estimates when no ovulation occurred reinforces the idea that this estimate should not be used in isolation. Algorithms using wrist temperature can provide retrospective ovulation estimates and next menses start day predictions for individuals with typical or atypical cycle lengths. Apple is the funding source for this manuscript. Y.W., C.Y.Z., J.P., S.Z., and C.L.C. own Apple stock and are employed by Apple. S.M. has research funding from Apple for a separate study, the Apple Women's Health Study, including meeting and travel support to present research findings related to that separate study. A.M.Z.J., D.D.B., B.A.C., and J.P. had no conflicts of interest. NCT05852951.

Wang Y ，Park J ，Zhang CY ，Jukic AMZ ，Baird DD ，Coull BA ，Hauser R ，Mahalingaiah S ，Zhang S ，Curry CL ... -  《-》

Timed intercourse for couples trying to conceive.

Gibbons T ，Reavey J ，Georgiou EX ，Becker CM ... -  《Cochrane Database of Systematic Reviews》