Hillel's Tech Corner: Embryonics: When IVF meets AI

Embryonics uses bleeding edge technology to increase the success rate of in vitro fertilization (IVF).

Embryonics (photo credit: Courtesy)
(photo credit: Courtesy)
 A couple of years ago, mid 2019, I got a random email from the contact form on my website. The email read “I got your name from Miri Berger from IBM, I would like to speak about my start-up. thanks and shavua tov:).” The email was from a woman named Yael Gold-Zamir. I replied and offered to help in any way I can. We set up a meeting. Within moments, I was blown away by both her and her company, Embryonics.
Embryonics uses bleeding edge technology to increase the success rate of in vitro fertilization (IVF). More precisely, Embryonics is developing and applying data-driven solutions to improve the journey and the success rates of fertility treatments.
Gold-Zamir is founder and CEO of Embryonics. She is an MD who graduated from the Hebrew University, then became a researcher in an IVF laboratory as a result of her increased interest in the science behind fertility.
Gold-Zamir’s partner, David Silver studied math and biology under the auspices of the Rothschild Excellence Program of the Technion and undertook a fellowship at the prestigious Microsoft PhD program in Cambridge, the UK. His previous role prior to joining Embryonics was as a machine learning researcher at Apple.
Embryonic’s third cofounder, Alex Bronstein, is a professor of Computer Science and head of the Center for Intelligent Systems in the Department of Computer Science at the Technion. Bronstein is an IEEE Fellow (of the Institute of Electrical and Electronics Engineers) and is a recognized expert in machine learning and computer vision with hundreds of publications and patents in the field. Bronstein also stands behind several successful companies that exited and were acquired by Intel, Philips and more.
The company is still in early stages and so far, in a pilot involving 11 women ranging in age from 20 to 40 years old, six of whom are enjoying successful pregnancies: the other five are awaiting results.
The global in vitro fertilization market is expected to grow from roughly $18.3 billion in 2019 to nearly double that number in the next five years. Yet the tens of thousands of women who undergo IVF each year have long faced costs of anywhere from $10,000 to $15,000 per cycle, along with long-shot odds that grow worse with age.
Embryonics was officially founded in 2018 and is based in Haifa, Israel. They have 14 full-time employees, and raised $4 million in pre-seed funding from the Schusterman Family Investment Office, the Israeli Innovation Authority and other investors.
Embryonics received regulatory approval in Europe last week. This will enable it to sell its software to fertility clinics across the continent. The team says their product can recognize patterns of successful or failed embryos significantly better than a human.
EVERY WOMAN who goes through IVF or fertility preservation goes through the process. It involves getting injected with hormones from eight to 14 days in order to induce their ovaries to produce as many mature eggs as possible while minimizing side effects.
The process still involves a lot of trial and error. Through geometric deep learning, Embryonics thinks it can begin to understand both the right mix of hormones each individual should be taking as well as the different times they should be taken, and it can give recommendations for personalized stimulation protocols.
Embryonics’ goal is to provide a holistic solution that addresses all steps of the process. For 40 years, many IVF clinics worldwide have simply assessed embryo health by looking at days-old embryos on a petri dish under a microscope to assess their cell multiplication and shape. Using AI and machine learning, this company has the potential to revolutionize fertility treatments as a whole.
Embryonics’ technology, called Ubar (the Hebrew word for fetus), outperformed a group of embryologists in predicting which embryos will result in pregnancy by approximately 20%, the company said. It also outperformed human experts by nearly 30% in recommending which embryos not to use, which can lead to significant cost savings and prevent miscarriages.
The reason this company excites me so much, beyond the hyper-talented team, is that similar to many of the biggest companies out there, Embryonics is taking a highly primitive and archaic market and disrupting it using technology. If you think about it, that’s what Uber did to transportation, Airbnb to hospitality, Facebook to communication, and so on.
Of course, with COVID-19, Embryonics wants to use geometric deep learning to predict which patients will need to be put on ventilators, which needs to be kept in the hospital and which can be treated at home. The start-up has began working with Shaare Zedek Medical Center to get access to its database of novel coronavirus-stricken patients. The idea is to build new predictive software based on the same geometric deep-learning tools it uses for personalizing hormonal treatments for IVF patients.
Working with the hospital will allow the company to adapt its embryo-selecting algorithm so it will be able to examine hospital data, looking at patients’ characteristics, from whether they are smokers to where they live, their age, diseases and other clinical parameters to make predictions about their outcomes: When will their illness peak? Will their illness be easier on them than for others?
Embryonics has developed two algorithms. One is a commercially available patented AI-technology that enables trawling through healthcare databases, studying tens of thousands of embryos and their implant-success rate, and then predicting which embryos will be the most likely to succeed.
The other analyzes clinical data using newly invented geometric deep learning technology to personalize hormonal treatments for anyone going through fertility treatments.
Geometric deep learning is a new field of machine learning that can gain insights from complex data, like graphs and multidimensional points, and, according to the company, “has shown big promise in other areas as it outperforms the classical widely used AI algorithms.”
Having several friends who went through the IVF process, I know just how devastating it can be when it fails. The thought of using technology to increase the chances of success will surely enhance millions of lives and make the world that much better.