February 9, 2023 — Are you planning to begin or expand a family by 2033? Thanks to recent technologies within the in vitro fertilizationConceiving a toddler within the near future might look more like something out of a science fiction movie than it does today.
Artificial intelligence already plays a job in complex laboratory processes and is predicted for use much more. Precise 3D printing and modern microscopes could also help discover embryos which are more more likely to result in a healthy pregnancy.
“I can’t believe how far we have come in the four decades I have been doing this,” says Dr. David Gardner, chief scientific officer at Melbourne IVF in East Melbourne, Victoria, Australia. “But what really excites me is [is] where the subsequent 5 to 10 years will lead. I feel like we're on the verge of something monumental.”
Here is an insight into the IVF technology of tomorrow.
Help for embryo “craftsmen”
Deciding which embryo to implant into a patient’s uterus is like judging a beauty contest, says Denny Sakkas, PhD, chief scientific officer at Boston IVF in Waltham, MA, who together with Gardner wrote an article on the future of IVF in the journal Fertility and sterility.
An experienced embryologist can recognize a good-looking specimen at first glance. Could AI do the same – in less time and for less money?
“You can use artificial intelligence to mathematically teach software to look at characteristics of an embryo that resulted in pregnancy in comparison with an embryo that didn't change into pregnant,” says Sakkas. He compares the technology to the facial recognition function of a smartphone: “We hope to have the opportunity to do that with images or videos of embryos.”
Even two embryologists in the same lab can evaluate the same embryo differently. How do you teach a machine to perform a subjective task?
Current algorithms use only a portion of the data collected by a time-lapse incubator – a device that takes real-time images of an embryo's development – and are therefore unable to paint a complete picture of its health.
As scientists explore the extent to which artificial intelligence can compete with embryologists, Gardner and Sakkas argue that combining human and machine intelligence in embryo selection could be key not only to maximizing successful pregnancies, but also to shortening the time to conception in people with infertility.
Automating even part of the process could help alleviate the predicted shortage of embryologists, whom Gardner calls “craftsmen,” as demand for IVF increases. IVF is a type of assisted reproductive technology, or ART. According to the CDCThis is a rise of about 60,200 in 2009In a previous article within the magazine Reproductive Biomedicine OnlineGardner asked, “Where will all the highly qualified embryologists and doctors come from that are needed for this growth?”
Another goal of automation is to make IVF cheaper and more geographically accessible to prospective parents. In the United States, a single IVF cycle costs an average of $10,000 to $15,000, according to the Society for Assisted Reproductive Technology. Only 14 states require insurance to cover at least part of the procedure—which means many people have to pay out of pocket. In 2013, about 40% of women of childbearing age nationwide—more than 25 million—lived in areas with limited or no access to ART clinics.
Even without these barriers, IVF is a physically and emotionally demanding process, says Sakkas.
“Our research is more aimed at facilitating that experience,” he says. “Currently, only a very small percentage of couples with infertility are actually treated.”
From 2015 to 2019, about 13% of girls ages 15 to 49 had difficulty becoming pregnant or carrying a baby, in keeping with the CDC. National Survey on Family GrowthLess than 1% had ever received ART treatment.
However, machine learning brings with it various other problems, says Dr. Aaron Levine, bioethicist and associate dean for research and outreach on the Georgia Tech Institute's Ivan Allen College of Liberal Arts in Atlanta. The technology is simply nearly as good because the people behind it.
“Anyone developing AI for IVF needs to make sure that their algorithms are trained on and work for patients from a wide range of backgrounds,” says Levine. “We know, for example, that black and Hispanic patients in the US are often poorer access to IVF care and worse outcomes when they do access this care. It would be very unfortunate if the integration of AI into IVF practices were to exacerbate these already problematic inequalities.”
Artificial fallopian tubes and “egg cups”
Reproductive medicine has made great progress since Louise Brown. the world’s first “test tube baby”, was born in England in 1978. But some things haven't modified.
“We grow the embryos in a polystyrene dish – just like in tissue culture – and they sit in a drop of medium,” says Gardner. “It's a static system; nothing happens. The embryo sits there and grows, and it's been that way for over 40 years.”
In contrast, a naturally conceived embryo is continuously moving, exchanging biochemical signals with its parent on its journey from the fallopian tube to the uterus.
That's where microfluidics and 3D printing are available in. Researchers have tested devices sufficiently small to carry a single embryo, in regards to the size of a pinhead, Gardner says.
“Instead of leaving an embryo in a microdroplet, we can now put it in a 'nest,'” he says. “Then we can expose it to continuous environments and receive messages from it, so it becomes a more interactive culture – just like in the womb.”
Microfabrication also affects sperm and unfertilized eggs.
Scientists in Canada and Australia experimented with such a tool that mimics the 1000's of folds of tissue within the fallopian tubes that guide sperm to an egg. The device allowed researchers to not only select high-quality sperm, but additionally accomplish that 3 times faster than the normal method, in keeping with a 2021 study within the journal Laboratory on a chip.
Gardner expects similar technology will absorb the needle stress when a single sperm is inserted into an egg, in a process called intracytoplasmic sperm injection. ICSI.
“ICSI is very invasive; we are developing chambers that basically work like an egg cup to hold the egg more securely,” says Gardner. Such 3D-printed tools “are not yet clinically available – that's the future.”
Even younger couples without known fertility problems could at some point profit from these technologies, write Gardner and Sakkas. Their goal is to freeze the healthiest embryos possible for later use.
The future is (almost) now
Despite the promise of those and other IVF innovations – including sophisticated microscopes this might help make clear the event of an embryo Metabolic health — Roadblocks remain in place.
“It's a very difficult path,” says Sakkas. “Not all technologies will be successful.”
First of all, IVF doesn't receive as much funding as other areas of medical research. Last yr National Institute of Health Cancer research was funded at an estimated $7.6 billion, in comparison with $618 million for contraception and reproductive research.
Jennifer Kawwass, MD, medical director at Emory Reproductive Center in Atlanta is optimistic in regards to the long-term use of AI for all the things from follicle measurement to the timing of the shot. But to date, relevant studies haven't shown a transparent advantage over existing methods, she says.
“There is a fine line between rapidly adopting new technologies and adopting them before their benefits are proven,” says Kawwass. “Continuous innovation with cautious adoption when their benefits are proven will certainly play a role in the fertility space in the years to come.”
Gardner also controls his excitement through patience.
“Automation will come,” he says. “But I think it will probably take another 5 to 10 years.”