Background 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. Objective 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. Methods 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. Results 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). Conclusions Our contribut...

Background As a daily point measurement, basal body temperature (BBT) might not be able to capture the temperature shift in the menstrual cycle because a single temperature measurement is present on the sliding scale of the circadian rhythm. Wrist skin temperature measured continuously during sleep has the potential to overcome this limitation. Objective This study compares the diagnostic accuracy of these two temperatures for detecting ovulation and to investigate the correlation and agreement between these two temperatures in describing thermal changes in menstrual cycles. Methods This prospective study included 193 cycles (170 ovulatory and 23 anovulatory) collected from 57 healthy women. Participants wore a wearable device (Ava Fertility Tracker bracelet 2.0) that continuously measured the wrist skin temperature during sleep. Daily BBT was measured orally and immediately upon waking up using a computerized fertility tracker with a digital thermometer (Lady-Comp). An at-home luteinizing hormone test was used as the reference standard for ovulation. The diagnostic accuracy of using at least one temperature shift detected by the two temperatures in detecting ovulation was evaluated. For ovulatory cycles, repeated measures correlation was used to examine the correlation between the two temperatures, and mixed effect models were used to determine the agreement between the two temperature curves at different menstrual phases. Results Wrist skin temperature was more sensitive than BBT (sensitivity 0.62 vs 0.23; P<.001) and had a higher true-positive rate (54.9% vs 20.2%) for detecting ovulation; however, it also had a higher false-positive rate (8.8% vs 3.6%), resulting in lower specificity (0.26 vs 0.70; P=.002). The probability that ovulation occurred when at least one temperature shift was detected was 86.2% for wrist skin temperature and 84.8% for BBT. Both temperatures had low negative predictive values (8.8% for wrist skin temperature and 10.9% for BBT). Significant positive correlation between the two temperatures was only found in the follicular phase (rmcorr correlation coefficient=0.294; P=.001). Both temperatures increased during the postovulatory phase with a greater increase in the wrist skin temperature (range of increase: 0.50 °C vs 0.20 °C). During the menstrual phase, the wrist skin temperature exhibited a greater and more rapid decrease (from 36.13 °C to 35.80 °C) than BBT (from 36.31 °C to 36.27 °C). During the preovulatory phase, there were minimal changes in both temperatures and small variations in the estimated daily difference between the two temperatures, indicating an agreement between the two curves. Conclusions For women interested in maximizing the chances of pregnancy, wrist skin temperature continuously measured during sleep is more sensitive than BBT for detecting ovulation. The difference in the diagnostic accuracy of these methods was likely attributed to the greater temperature increase in the postovulatory phase and greater temperature decrease during the menstrual phase for the wrist skin temperatures.

INTRODUCTION: Loss to follow-up and missing data are common reasons why clinical studies fail. In a site-less digital clinical trial we assessed the accuracy of a wearable fertility tracker, where we examined participants’ retention, compliance, and satisfaction with the site-less design. METHODS: In this IRB approved study, participants were recruited remotely through social media, online platforms, and email invitations. Participants wore the Ava Fertility Tracker for up to 6 menstrual cycles, took body temperature and urinary luteinizing hormone tests. We collected all self-reported outcomes and wearable device data via a mobile app, wherein the study coordinator could monitor compliance and send participation reminders. An independent customer support team provided technical support. Participants gave input on the site-less study design via an online survey. RESULTS: Fifty-six Swiss women completed the satisfaction survey (85% of the 66 enrolled study participants), rating their experience with social media recruitment (83%), online registration (98%) and online invitations (98%) as good or very good. Almost two-thirds of respondents considered the trial design easy to integrate into their everyday life. Most participants were highly satisfied with the technical support (78%), while 98% reported the study coordinator’s remote support as very helpful. CONCLUSION: Our predominantly digital approach resulted in high rates of completion (92%) and procedural compliance (87%), while maintaining participant satisfaction. This suggests site-less designs in reproductive health research could increase the quality and quantity of clinical data collected while minimizing participation burden. Future replication studies with longer follow-up times should consider whether the sampled population is biased towards digital natives.

BACKGROUND As a daily point measurement, basal body temperature (BBT) might not be able to capture the temperature shift in the menstrual cycle because a single temperature measurement is present on the sliding scale of the circadian rhythm. Wrist skin temperature measured continuously during sleep has the potential to overcome this limitation. OBJECTIVE This study compares the diagnostic accuracy of these two temperatures for detecting ovulation and to investigate the correlation and agreement between these two temperatures in describing thermal changes in menstrual cycles. METHODS This prospective study included 193 cycles (170 ovulatory and 23 anovulatory) collected from 57 healthy women. Participants wore a wearable device (Ava Fertility Tracker bracelet 2.0) that continuously measured the wrist skin temperature during sleep. Daily BBT was measured orally and immediately upon waking up using a computerized fertility tracker with a digital thermometer (Lady-Comp). An at-home luteinizing hormone test was used as the reference standard for ovulation. The diagnostic accuracy of using at least one temperature shift detected by the two temperatures in detecting ovulation was evaluated. For ovulatory cycles, repeated measures correlation was used to examine the correlation between the two temperatures, and mixed effect models were used to determine the agreement between the two temperature curves at different menstrual phases. RESULTS Wrist skin temperature was more sensitive than BBT (sensitivity 0.62 vs 0.23; <i>P</i>&lt;.001) and had a higher true-positive rate (54.9% vs 20.2%) for detecting ovulation; however, it also had a higher false-positive rate (8.8% vs 3.6%), resulting in lower specificity (0.26 vs 0.70; <i>P</i>=.002). The probability that ovulation occurred when at least one temperature shift was detected was 86.2% for wrist skin temperature and 84.8% for BBT. Both temperatures had low negative predictive values (8.8% for wrist skin temperature and 10.9% for BBT). Significant positive correlation between the two temperatures was only found in the follicular phase (<i>rmcorr</i> correlation coefficient=0.294; <i>P</i>=.001). Both temperatures increased during the postovulatory phase with a greater increase in the wrist skin temperature (range of increase: 0.50 °C vs 0.20 °C). During the menstrual phase, the wrist skin temperature exhibited a greater and more rapid decrease (from 36.13 °C to 35.80 °C) than BBT (from 36.31 °C to 36.27 °C). During the preovulatory phase, there were minimal changes in both temperatures and small variations in the estimated daily difference between the two temperatures, indicating an agreement between the two curves. CONCLUSIONS For women interested in maximizing the chances of pregnancy, wrist skin temperature continuously measured during sleep is more sensitive than BBT for detecting ovulation. The difference in the diagnostic accuracy of these methods was likely attributed to the greater temperature increase in the postovulatory phase and greater temperature decrease during the menstrual phase for the wrist skin temperatures.

No abstract