The Ava sensor bracelet is a physiological parameter 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.
1Stein, 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.
2Leeners, 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.
3Stein, 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 doubling the chances to conceive compared with untimed intercourse once per week. If only live birth is considered the researching team estimates the probability to be 0.25 with daily intercourse, 0.22 with intercourse 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.
1Weinberg CR, Wilcox AJ. A model for estimating the potency and survival of human gametes in vivo. Biometrics. 1995; 51:405–412.
2Wilcox 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.
3Andrews 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
The temperature of your skin at your wrist.
Skin temperature is one of the parameters Ava uses to identify your fertile window. It rises by about one half of a degree after ovulation, and remains elevated until your next period begins. During pregnancy, temperature remains elevated. If you’ve ever tracked your basal body temperature orally, you’ll notice that Ava’s temperature reading is several degrees lower than your oral temperature. It’s normal for skin temperature to be lower than oral temperature, but we found that it exhibits the typical biphasic pattern during the cycle.
Average skin temperature readings (when taken at a room temperature of 64.5 – 77 degrees Fahrenheit) are between 90.5 – 98.2 degrees Fahrenheit.
For Celsius:
Average skin temperature readings (when taken at a room temperature of 18 – 25 degrees Celsius) are between 32.5 – 36.8 degrees Celsius.
How often your heart beats per minute at rest.
Scientific literature shows that resting pulse rate is lower during the follicular phase than the luteal phase. Ava’s clinical research partner, the University Hospital of Zurich, identified further variation in resting pulse rate throughout the menstrual cycle: resting pulse rate rose by about 2.1 beats per minute at the beginning of the fertile window.
During pregnancy, resting pulse rate remains elevated.
Typical resting pulse rates are between 40 and 80 bpm. If you are very physically active, your resting pulse rate may be even lower than 40 bpm. Stress, illness, and alcohol can cause temporary increases in resting pulse rate.
Rate of respiration per minute.
Scientific literature shows that breathing rate is higher in the luteal phase than in the follicular phase. Breathing rate can vary widely during the course of a day due to your activities, but typical breathing rates during sleep are much more stable, and range from 10 – 25 bpm.
The lower your HRV ratio, the less stressed you are.
HRV is the variation in the time interval from one heartbeat to the next. It can be used as an indicator of physiological stress: when there is a lot of variation in the time interval between heartbeats—high HRV—it means you are more resilient and less stressed. Ava measures the ratio between low frequency and high frequency waves in your heart rate. Because Ava measures HRV using this ratio, a lower number means you are less stressed.
Normal HRV ratio varies widely from person to person, but by looking for an increase or decrease from your baseline HRV ratio, you can learn about your body’s physiological stress level.
The process of supplying blood to the tissues of your body.
As blood flows through your capillaries, it delivers nutrients to the tissues and helps sweep away waste. Then, the blood flows back to the heart, and begins the process all over again.
If you’ve ever had an elastic band around your finger and felt the blood flow being cut off, you’re already familiar with the process of perfusion. While you can limit perfusion with an elastic band, perfusion can also change naturally for different reasons. For example, your perfusion changes in order to keep you warm or cool you down. Perfusion also changes in relation to the menstrual cycle: it is higher in the fertile days and lower during the luteal phase.
Ava tracks your movement with an accelerometer.
This parameter allows Ava to distinguish between light and deep + REM sleep.
Bioimpedance measures the resistance of body tissue to tiny electric voltages.
This parameter provides information about the skin, including hydration and sweating patterns. As you have probably observed throughout your life, reproductive hormones have an impact on your skin. Your skin can change at different phases of the menstrual cycle, during puberty, and during pregnancy.
Heat loss is closely related to the onset of sleep.
As you lose heat through your hands and feet, your skin temperature increases and your core body temperature decreases.
Heat loss is also related to your metabolic rate. The mechanism for the maintenance of the higher temperature during the luteal phase is still a matter of scientific discussion. Some researchers believe that reduced heat loss is responsible, while others believe that higher internal heat production (increased metabolic rate) is the cause.
Total sleep hours and ratio of light to deep + REM sleep.
The quality and quantity of sleep you’re getting each night are important parameters to track for your fertility. Your menstrual cycle can affect your sleep, and your sleep, in turn, can affect your menstrual cycle. Pregnancy can also influence sleep.
Ava records the amount of sleep you get each night. Additionally, Ava tracks the percentage of combined deep and REM sleep. Deep sleep is important for feeling rested the next morning, while REM sleep is important for learning and storing memories.
Typical sleep cycles for adults include 50 – 65 percent light sleep and 35 – 50 percent deep sleep + REM.
Ava must be worn for at least four hours per night with three hours of sleep in order to work properly.
Ava measures the physiological changes that happen when your body is completely at rest. It takes at least four hours for these parameters to stabilize and for Ava to get an accurate reading. If Ava recorded less than four hours, it won’t use the data from that night in calculating your fertility.
If you wore Ava for more than four hours but are still seeing “data quality poor,” it could mean the battery died during the night or that the sensors lost contact to your skin. Make sure Ava is fully charged when you put it on. This is indicated by a green light on the top of the bracelet.
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.
1Stein, 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.
2Leeners, 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.
3Stein, 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. Bioimpedance sensor module
- The bioimpedance sensor allows to measure the impedance of the skin at the wrist with different excitation frequencies and extract the reactances and resistances.
- These measurements can be used to estimate different properties of the skin including skin hydration, inter- and extracellular water and others.
2. Temperature sensors
- Ava’s sensor bracelet contains two NTC (negative temperature coefficient) resistors for measuring skin temperature and the temperature of the outer housing of the pod.
- This allows estimating the heat loss going away from the arm.
3. Accelerometer
- Movement is measured with a 3-axis accelerometer in the sensor bracelet. The measurement is important for identifying the different stages of sleep and to compensate the other signals with movement artifacts.
4. 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.