Hello,

We noticed you're browsing in private or incognito mode.

To continue reading this article, please exit incognito mode or log in.

Not an Insider? Subscribe now for unlimited access to online articles.

Rewriting Life

Algorithms Calculate a Couple's Chances of Having a Baby via IVF

A California startup says its at-home test could help couples decide if the fertility treatment is worth trying.

Most fertility doctors still rely on age as the primary determinant of whether or not a woman is likely to get pregnant though in vitro fertilization (IVF). But age is only a tiny piece of the puzzle, says Mylene Yao, cofounder and CEO of Univfy, a Los Altos, California-based startup that recently began marketing a home test that ties together dozens of metrics related to health and lifestyle to predict a woman’s chances of getting pregnant with IVF.

On Wednesday, Univfy will present a study at the American Society of Reproductive Medicine conference in San Diego that shows that its technology is 36 percent more accurate than age alone when it comes to determining fertility, Yao says.

According to the study, 42 percent of women who received the test were told they had a 45 percent chance of succeeding with IVF. “If you use [just] age, nobody—zero percent—will even know they have that high a chance,” Yao says. “Age is so misleading. It’s almost like not telling them anything.”

It could be valuable to more accurately predict the likelihood of success with IVF because the treatment costs tens of thousands of dollars and is often not covered by insurance. Some fertility specialists believe the test could help couples who would like to know about their chances of conceiving before even seeing a doctor. “For the layperson, it’s a good tool,” says Allen Morgan, a fertility specialist and assistant professor at the University of Medicine and Dentistry of New Jersey.

Univfy began selling the test, called PreIVF, online in July for $250. It asks women to reveal such factors as their body mass index, history of smoking, other health conditions, and previous experiences with pregnancy and fertility treatments. They are also asked to provide data from blood and semen tests. Yao says these results can be obtained easily from primary care doctors.

Univfy uses machine-learning algorithms to predict IVF success based on the experiences and characteristics of thousands of couples who were treated at three IVF centers in the United States, Canada, and Spain.

Univfy was launched in 2009 based on technology that Yao and her cofounder, Wing Wong, developed at Stanford University. They initially collected data from 5,000 IVF cycles performed at Stanford over five years, used it to create a predictive model, and then tailored the model to individual fertility centers, using data from those clinics to predict, for example, patients’ chances of having multiple births with IVF.

Univfy now sees an opportunity to sell a universal test that women could take at home. “For most patients, IVF is the most effective treatment, but it’s very much underutilized,” Yao says. For example, there are seven million women in the U.S. struggling with infertility, yet only 150,000 IVF cycles are performed each year, she says.

Get stories like this before anyone else with First Look.

Subscribe today
Already a Premium subscriber? Log in.

Uh oh–you've read all of your free articles for this month.

Insider Premium
$179.95/yr US PRICE

More from Rewriting Life

Reprogramming our bodies to make us healthier.

Want more award-winning journalism? Subscribe to Insider Online Only.
  • Insider Online Only {! insider.prices.online !}*

    {! insider.display.menuOptionsLabel !}

    Unlimited online access including articles and video, plus The Download with the top tech stories delivered daily to your inbox.

    See details+

    What's Included

    Unlimited 24/7 access to MIT Technology Review’s website

    The Download: our daily newsletter of what's important in technology and innovation

/
You've read all of your free articles this month. This is your last free article this month. You've read of free articles this month. or  for unlimited online access.