Ava’s Technology

The Ava sensor bracelet is a physiological parameters tracking device worn at the wrist by women during sleep

The measured data is synced with a smartphone app, where the daily fertility status, predicted menses, and nightly physiological data is displayed. Ava’s product was validated based on data from a clinical trial conducted by the University Hospital Zurich / Switzerland. The data shows that Ava could detect an average of 5.3 fertile days with 89% accuracy per menstrual cycle in real time. The algorithm performance was presented in the Annual Meeting of ASRM (American Society of Reproductive Medicine)1, SGGG (Swiss Society of Gynecology and Obstetrics)2 and DGGG (German Society of Gynecology and Obstetrics)3.

1 Stein, P., Falco, L., Kuebler, F., Annaheim, S., Lemkaddem, A., Delgado-Gonzalo, R., Verjus, C., Leeners, B. (2016, October), Digital Women’s Health based on Wearables and Big Data, Poster presented at the Annual Meeting of American Society of Reproductive Medicine (ASRM), Salt Lake City, UT, USA.

2 Leeners, B., Stein, P. (2016, June). Digital Women’s Health based on Wearables and Big Data (supported by Bayer Healthcare), Symposium conducted at the Annual Meeting of Swiss Society of Gynecology and Obstetrics (SGGG), Interlaken, Switzerland.

3 Stein, P., Falco, L., Kuebler, F., Annaheim, S., Lemkaddem, A., Delgado-Gonzalo, R., Verjus, C., Leeners, B. (2016, October), Digital women’s health based on wearables and big data – new findings in physiological changes throughout the menstrual cycle, Poster presented at the Annual Meeting of German Society of Gynecology and Obstetrics (DGGG), Stuttgart, Germany.

The fertile days

Increasing the chances to conceive
The fertile days and their timing in the menstrual cycle

During the ovulatory menstrual cycle there is a limited number of days when a women can get pregnant. There are several factors that affect the probability of conception on a given day of the menstrual cycle, including (but not limited to):

  • the timing of intercourse relative to ovulation
  • the viability of the ovum
  • the survival of sperm in the female reproductive tract
  • and the penetrability of cervical mucus.

Sperm can survive in the female reproductive tract for up to 6 days. The median survival time for an ovum is approximately 12 h.1 This results in an estimated fertile phase of 6 days ending on the ovulation day1, 2.

Likelihood of conceiving on different days of the menstrual cycle*

*Live births (N=129), data for healthy, young couples, Wilcox 1996

Figure based on data from Wilcox, 1995, Live births (N=129), data for healthy, young couples2
The value of an indication of fertile days for women who are trying to conceive

For a successful conception sexual intercourse needs to take place during the fertile days, where the two days prior ovulation and the day of ovulation itself produce the highest chances to conceive. Ava labels these days as peak fertile days.

Timed intercourse during these days results in a higher probability of conception as well as daily intercourse or intercourse every other day. Adopting one of the aforementioned methods leads to an estimated conception probabilities >=0.30, while untimed intercourse averaging once per week produces a 0.15 chance of conception per cycle. Hence, timed intercourse allows to double the chances to conceive compared with untimed intercourse once per week. If only live birth are considered the researching team estimates the probability to be 0.25 with daily intercourse, 0.22 with inter-course every other day, and 0.10 with weekly intercourse.2

Couples who are willing to have sex every or every other day can achieve high chances to conceive without using a fertility awareness method (FAM) like Ava. FAMs are especially helpful for couples who cannot or do not want to have sexual intercourse in high frequency. It has been demonstrated that stress, generally, and fertility-problems stress, specifically, has a negative impact on marriages including the frequency of intercourse. For couples facing such a situation, timed intercourse based on a FAM in comparison to having intercourse daily or every other day might be favorable3.

1 Weinberg CR, Wilcox AJ. A model for estimating the potency and survival of human gametes in vivo. Biometrics. 1995; 51:405–412.

2 Wilcox AJ, Weinberg CR, Baird DD. Timing of Sexual Intercourse in Relation to Ovulation. Obstet Gynecol Surv. 1995;51(6):357-358. doi:10.1097/00006254-199606000-00016.

3 Andrews FM, Abbey A, Halman LJ. Is fertility-problem stress different The dynamics of stress in fertile and infertile couples. Fertil Steril. 1992;57(6):1247-1253. doi:10.1016/S0015-0282(16)55082-1.

Prediction of the fertile days

Hormonal variations throughout the menstrual cycle

The menstrual cycle is divided into two phases: the follicular phase starting at the first day of menstruation and ending with ovulation and the luteal phase starting with ovulation and ending at the day before the first day of the next menstruation. During normal menstrual cycles the levels of ovarian and pituitary hormones change in a periodic pattern.

For Ava, the variation of the two ovarian hormones estrogen and progesterone is crucial. In the course of the menstrual cycle Estradiol is produced by the growing follicle and triggers, via a positive feedback system, the hypothalamic-pituitary events that lead to the luteinizing hormone surge, inducing ovulation.

A limited preovulatory Progesterone production is initiated by the surge of LH. In the luteal phase, estradiol, in conjunction with progesterone, prepares the endometrium for implantation. In the non-conceptive cycle progesterone increases with a peak in the mid-luteal phase.

In addition to the regulation of the menstrual cycle and preparing the body for ovulation and implantation, reproductive hormones also influence a variety of physiological parameters. Ava uses the changes in the physiological parameters imparted by reproductive hormones to calculate the current status of the cycle.

Variations of physiology correlating with the menstrual cycle phases
OVERVIEW

Overview
The menstrual cycle is regulated by varying hormonal levels. The influence of these changing hormonal levels on physiology is well documented in the scientific literature. The following pages give an overview on how the physiological parameters measured by Ava correlate with the menstrual cycle phases.

SKIN TEMPERATURE

Skin temperature
The biphasic pattern of basal body temperature (BBT) during the menstrual cycle is a well-known phenomenon to estimate the day of ovulation. Daily measurements of rectal or oral temperature just after awakening is a widely used method to estimate the BBT. As shown by Cagnacci et al. in ovulatory menstrual cycles, the circadian rhythm is superimposed on a menstrual-associated rhythm. Nightly average body temperature are approximately increased by 0.4°C in the luteal phase compared with the pre-ovulatory follicular phase1. These findings are consistent with other  clinical trials2. Kräuchi et al. observed that skin temperature rhythms, including skin temperatures measured at the wrist, exhibited similar menstrual cycle amplitudes and phases with maxima and minima at the end of the luteal and follicular phases, respectively3. These findings were reproduced using Ava’s hardware in a trial conducted by Ava’s researchers in collaboration with researchers from University Hospital Zurich. The average difference between fertile phase and luteal phase was 0.4° C4.

1 Cagnacci A, Soldani R, Laughlin GA, Yen SC. Modification of circadian body temperature rythm during the luteal menstrual phase: role of melantonin. 1996.

2 Baker FC, Waner JI, Vieira EF, Taylor SR, Driver HS, Mitchell D. Sleep and 24 hour body temperatures: A comparison in young men, naturally cycling women and women taking hormonal contraceptives. J Physiol. 2001;530(3):565-574. doi:10.1111/j.1469-7793.2001.0565k.x.

3 Kräuchi K, Konieczka K, Roescheisen-Weich C, et al. Diurnal and menstrual cycles in body temperature are regulated differently: A 28-day ambulatory study in healthy women with thermal discomfort of cold extremities and controls. Chronobiol Int. 2014;31(1):102-113. doi:10.3109/07420528.2013.829482.

4 Shilaih, M., Annaheim, S., De Clerck, V., Falco, L., Kuebler, F., and Leeners, B. (2016, November). The continuous measurement of wrist skin temperature during the night as an alternative method to detect the basal body temperature shift in the luteal phase of the menstrual cycle, In preparation

PULSE RATE

Pulse rate
In a clinically controlled environment, Moran et al. demonstrated that resting pulse rate is significantly increased in the fertile window compared to the menstrual phase1. This increase carried through the luteal phase to reach a resting pulse rate peak during the mid-luteal phase1. It is speculated that this rise is attributable to oestrogen increasing the blood volume and/or by enhancing sympathetic cardiac-acceleration. In a prospective clinical trial conducted by University Hospital Zurich in cooperation with Ava we observed a significant increase in the median pulse rate during the fertile window compared to the menstrual phase (2.0 beat-per-minute, p<.01). Moreover, the median pulse rate during the mid-luteal phase was also significantly elevated compared to the fertile window (1.5 beat-per-minute, p<.01), and the menstrual phase (3.3 beat-per-minute,p<.01)2. These results together with the findings on skin temperature (described below) were presented at the 2016 Annual Meetings of the American Society of Reproductive Medicine3, the Swiss Society of Gynecology and Obestetrics4 and the German Society of Gynecology and Obstetrics5.

1 Moran VH, Leathard HL, Coley J. Cardiovascular functioning during the menstrual cycle. Clin Physiol. 2000;20(6):496-504. doi:10.1046/j.1365 2281.2000.00285.x.

2 Shilaih, M., De Clerck, V., Falco, L., Kuebler, F., and Leeners, B. (2016, November). Pulse Rate Measurement During Sleep Using Wearable Sensors, and its Correlation with the Menstrual Cycle Phases, A Prospective Observational Study, Submitted to Scientific Report

3 Stein, P., Falco, L., Kuebler, F., Annaheim, S., Lemkaddem, A., Delgado-Gonzalo, R., Verjus, C., Leeners, B. (2016, October), Digital Women’s Health based on Wearables and Big Data, Poster presented at the Annual Meeting of American Society of Reproductive Medicine (ASRM), Salt Lake City, UT, USA.

4 Leeners, B., Stein, P. (2016, June). Digital Women’s Health based on Wearables and Big Data (supported by Bayer Healthcare), Symposium conducted at the Annual Meeting of Swiss Society of Gynecology and Obstetrics (SGGG), Interlaken, Switzerland.

5 Stein, P., Falco, L., Kuebler, F., Annaheim, S., Lemkaddem, A., Delgado-Gonzalo, R., Verjus, C., Leeners, B. (2016, October), Digital women’s health based on wearables and big data – new findings in physiological changes throughout the menstrual cycle, Poster presented at the Annual Meeting of Germany Society of Gynecology and Obstetrics (DGGG), Stuttgart, Germany.

Heart rate variability

Heart rate variability
HRV is the physiological phenomenon of variation in the time interval between heartbeats. There are various established parameters based on HRV:

HRV SDNN is the standard deviation of the intervals in between the pulses and is typically calculated for a period of 5 minutes. It reflects all the cyclic components responsible for variability in the period of recording.

HRV Ratio belongs to the frequency domain methods, which are often applied to understand the effect of the nervous system onto cardiac control. HRV Ratio calculates the ratio between the amount of intervals with higher frequency variation and lower frequency variation. In scientific literature it is well documented that HRV Ration correlates with Stress and the sympathetic nervous system activities.

Dishman et al. showed that there was an inverse relationship between perceived emotional stress during the past week and the normalized HF (high frequency) component of HRV1. Similar findings are coming from Cinaz et al.2 , Brosschot et al.3 and Mellman et al.4.

1 Dishman RK, Nakamura Y, Garcia ME, Thompson RW, Dunn AL, Blair SN. Heart rate variability, trait anxiety, and perceived stress among physically fit men and women. Int J Psychophysiol. 2000;37(2):121-133. doi:10.1016/S0167-8760(00)00085-4.

2 Cinaz B, La Marca R, Arnrich B, Tröster G. Monitoring of mental workload levels. Proc IADIS Int Conf e-Health 2010, EH, Part IADIS Multi Conf Comput Sci Inf Syst 2010, MCCSIS 2010. 2010:189-193.

3 Brosschot JF, Van Dijk E, Thayer JF. Daily worry is related to low heart rate variability during waking and the subsequent nocturnal sleep period. Int J Psychophysiol. 2007;63(1):39-47. doi:10.1016/j.ijpsycho.2006.07.016.

4 Mellman TA, Knorr BR, Pigeon WR, Leiter JC, Akay M. Heart rate variability during sleep and the early development of posttraumatic stress disorder. Biol Psychiatry. 2004;55(9):953-956. doi:10.1016/j.biopsych.2003.12.018.

SLEEP

Sleep
The American Academy of Sleep Medicine classifies sleep into the following phases: NREM (Non-Rapid Eye Movement) 1, NREM 2, NREM 3 and REM. NREM 1 and NREM 2 are the lighter sleep when an individual is more easily awaken. NREM 3 is the slow wave sleep or deep sleep which is restful for the body and characterized by very little movement. During REM sleep muscles are mostly paralyzed and heart and breathing rate as well as body temperature are less regulated. The sleeper may dream during this phase.

The correlation between sleep and the menstrual cycle states that timing and composition of sleep stays largely the same throughout the cycle1. Driver et al. reported that REM sleep underwent minor, yet significant, variation across the menstrual cycle. The share of REM sleep was 4.5% higher in the late luteal phase compared to the early follicular phase2 which is not consistent with Baker et al who found a minor decrease in the luteal phase. Both research groups found an increase in spindle frequency of the EEG (electroencephalography) measures during the luteal phase.

Ava uses the classification of nightly sleep into different phases for filtering the other signals.

1 Baker FC, Driver HS. Circadian rhythms, sleep, and the menstrual cycle. Sleep Med. 2007;8(6):613-622. doi:10.1016/j.sleep.2006.09.011.

2 Driver HS, Dijk DJ, Werth E, Biedermann K, Borbély AA. Sleep and the sleep electroencephalogram across the menstrual cycle in young healthy women. J Clin Endocrinol Metab. 1996;81(2):728-735.

PERFUSION

Perfusion
Perfusion describes how well blood is delivered to the tissues. Ava uses an optical sensor to measure how much blood is flowing through the different layers of the skin. Both Estrogen and Progesterone influence perfusion. Gerhardt et al. observed that increased estradiol levels are associated with both increased capillary blood flow and decreased microvascular resistance1. In addition, Bartelink et al. found that baseline forearm muscle blood flow varied significantly within one menstrual cycle, with lower values in the menstrual phase compared with the other phases2.

1 Gerhardt U, Hillebrand U, Mehrens T, Hohage H. Impact of estradiol blood concentrations on skin capillary Laser Doppler flow in premenopausal women. Int J Cardiol. 2000;75(1):59-64.

2 Bartelink ML, Wollersheim H, Theeuwes A, van Duren D, Thien T. Changes in skin blood flow during the menstrual cycle: the influence of the menstrual cycle on the peripheral circulation in healthy female volunteers. Clin Sci (Lond). 1990;78(5):527-532.

BREATHING RATE

Breathing rate
Ava estimates the breathing rate based on the optical sensor and acceleration measurements. Earlier studies demonstrated that there is an increases in minute ventilation in the luteal phase when estradiol and progesterone levels are high, but they did not find a significant increase in breathing rate . Brodeur et al. observed that the respiratory frequency of rats treated with estrogen significantly increased from an average of 862 3 to 93 breaths per minute after estrogen treatment .1

1 Brodeur P, Mockus M, McCullough R, Moore LG. Progesterone receptors and ventilatory stimulation by progestin. J Appl Physiol. 1986;60(2):590-595.

2 Slatkovska L, Jensen D, Davies GAL, Wolfe LA. Phasic menstrual cycle effects on the control of breathing in healthy women. Respir Physiol Neurobiol. 2006;154(3):379-388. doi:10.1016/j.resp.2006.01.011.

3 Regensteiner JG, Woodard WD, Hagerman DD, et al. Combined effects of female hormones and metabolic rate on ventilatory drives in women. J Appl Physiol. 1989;66(2):808-813.

MOVEMENT

Movement
Although correlation between agitation and fertility in other species like cattle is well documented1 no correlation between movement and fertility has been reported in humans. Ava uses the acceleration measurements as one predictor in the sleep classifier and and for compensating signals from the other sensors with movement artifacts. The team will continue researching movement signals for correlations with fertility.

1 Roelofs JB, Van Eerdenburg FJCM, Soede NM, Kemp B. Pedometer readings for estrous detection and as predictor for time of ovulation in dairy cattle. Theriogenology. 2005;64(8):1690-1703. doi:10.1016/j.theriogenology.2005.04.004.

Ava’s Algorithm

Data processing steps

After the synchronization of the bracelet data with the back-end server, the incoming data is checked for quality. In this step, insufficient or corrupted data is identified. The user receives a feedback notification about the data quality based on this check. In the next step, tens of features are extracted from the measured physiological parameters. Afterwards, the derived features are used in the algorithm which estimates the status of the cycle. This information is then relayed back to the user’s smartphone.

Self-learning for individualization

The algorithm has different self-learning parts, which continuously adapt it to the individual user. One self-learning part is about the physiology of the individual user: as hormonal changes induce relative changes to physiological parameters, it is important for Ava to understand individual baselines of the signals. Another area of individualization is based on the retrospective cycle characteristics. The Ava algorithms analysis every complete cycle retrospectively to add the information about the previously observed patterns for a better prediction in the future.

Algorithm performance

The algorithm was validated based on clinical data from a trial conducted by University Hospital Zurich / Switzerland. It showed the following performance in identifying fertile days in real time:

Accuracy: 89%
Sensitivity: 77%
Specificity: 92%
Average detected fertile days: 5.3

The findings on the algorithm performance were presented in the Annual Meeting of ASRM (American Society of Reproductive Medicine)1, SGGG (Swiss Society of Gynecology and Obstetrics)2 and DGGG (German Society of Gynecology and Obstetrics)3.

1 Stein, P., Falco, L., Kuebler, F., Annaheim, S., Lemkaddem, A., Delgado-Gonzalo, R., Verjus, C., Leeners, B. (2016, October), Digital Women’s Health based on Wearables and Big Data, Poster presented at the Annual Meeting of American Society of Reproductive Medicine (ASRM), Salt Lake City, UT, USA.

2 Leeners, B., Stein, P. (2016, June). Digital Women’s Health based on Wearables and Big Data (supported by Bayer Healthcare), Symposium conducted at the Annual Meeting of Swiss Society of Gynecology and Obstetrics (SGGG), Interlaken, Switzerland.

3 Stein, P., Falco, L., Kuebler, F., Annaheim, S., Lemkaddem, A., Delgado-Gonzalo, R., Verjus, C., Leeners, B. (2016, October), Digital women’s health based on wearables and big data – new findings in physiological changes throughout the menstrual cycle, Poster presented at the Annual Meeting of German Society of Gynecology and Obstetrics (DGGG), Stuttgart, Germany.

Physiological measurements

Ava’s wearable device contains different sensors
1. Temperature sensors
  • Ava’s sensor bracelet contains two NTC (negative temperature coefficient) resistors for measuring skin temperature and the temperature of outer housing of the pod.
  • This allows to estimate the heat loss going away from the arm.
2. Accelerometer
  • Movement is measured with a 3-axis accelerometer in the sensor bracelet. The measurement is important for identifying the different states of sleep and to compensate the other signals with movement artefacts.
3. Photoplethysmograph
  • The optical sensor module in the Ava bracelet is a 2 wavelengths photoplethysmograph. It works with an optical measurement in the visible spectrum (green) and one in the infrared enabling the detection of changes in different depths of the skin. This makes it possible to measure pulses with single millisecond mean average error for heart rate variability (HRV) calculations, pulse rate, breathing rate, and perfusion measurements.

Quality

The Ava Fertility Tracker is CE marked and listed with the FDA.
Declaration of conformity
By continuing to use the site, you agree to the use of cookies. more information Accept

This site is using first and third party cookies to be able to adapt the advertising based on your preferences. If you want to know more or modify your settings, click here. By continuing to use the site, you agree to the use of cookies.

Close
Track Your Cycle with Ava order now