Artificial Intelligence has the ability to create and optimize many things. Using data as its ‘fuel,’ machine-learning algorithms can predict future outcomes, automate tasks, and empower robotics to do things we never imagined possible by anyone other than humans. Now, an organization in Sydney says it can use AI to help women become pregnant through IVF. Developed by IVFAustralia, the Ivy AI system can predict how likely an embryo is to develop, enabling an embryologist to select the best embryo for transfer into a woman’s uterus.
Part of what makes Ivy such a powerful tool in IVF, is its ability to expediently sort through enormous amounts of information. “Ivy can review a massive amount of data, far more than any human could ever process, including hundreds of images from each embryo,” Ivy’s website states. “By completely objective analysis of the images, Ivy has taught itself to identify the embryo with the greatest likelihood of developing as far as a fetal heart. The embryo with the highest score, and therefore the highest potential for leading to a viable fetus, can then be selected for transfer.”
IVFAustralia is currently conducting a randomized controlled trial of the process and says it hopes to roll out the technology to clinics once the trial has concluded. Currently, embryo selection is done by a human who assesses and grades each embryo under a microscope. Choosing the most viable embryo is vital to maximizing a woman’s chance of conception, and saves time, money and the emotional toll of not becoming pregnant as quickly as possible. While the clinic is not currently using Ivy to help patients get pregnant because the trial being underway, the website states that currently in patients under 30 years 35% of embryo transfers lead to a live birth. There is significant room for improvement in the IVF process.
IVF success rates in the U.K and the U.S. tell a similar story. The average birth rate for an IVF embryo in the UK was just 23% in 2018. The CDC provides statistics for assisted reproductive technology (ART). “Based on CDC’s 2017 Fertility Clinic Success Rates Report, there were 284,385 ART cycles performed at 448 reporting clinics in the United States during 2017, resulting in 68,908 live births (deliveries of one or more living infants) and 78,052 live-born infants,” the CDC states. Also of significance, is the growing popularity of IVF in the U.S. The demand has doubled over the past decade, and approximately 1.7% of all infants born in the United States every year are conceived using ART according to the CDC.
Nature magazine published an article last year on how deep learning can enable ‘robust assessment and selection of human blastocysts after in vitro fertilization.’ That study undertaken by researchers at Cornell supports the belief that AI can assess embryo quality and be of use in IVF. “Our analysis shows that the chance of pregnancy based on individual embryos varies from 13.8% (age ≥41 and poor-quality) to 66.3% (age <37 and good-quality) depending on automated blastocyst quality assessment and patient age,” the publication reads. For reference, an embryo develops into a blastocyst around day 5 or 6 after being implanted into the uterus. These results similarly highlight the enormous range of success in transferring embryos and the importance of choosing the healthiest of those that are available. “In conclusion, our AI-driven approach provides a reproducible way to assess embryo quality and uncovers new, potentially personalized strategies to select embryos,” the Cornell paper concludes.
An ‘AI Enhanced Fertility’ technology called Life Whisperer is already authorized for sale in the UK, Europe, Australia, New Zealand, Canada, India, Japan, Hong Kong, Singapore, and Vietnam according to its website. Scientists involved in Life Whisperer published a paper in the Oxford University Press earlier this year that details the use of an ‘artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy.’ The advantage of Life Whisperer is that it is a web-based product that clinics can upload pictures of embryos to and does not require clinics to invest in additional medical equipment. Life Whisperer is pushing the frontiers of AI even further, noting that it is now working on another product that could identify genetic abnormalities in embryos. “Some of our early results show that there’s a very clear association between the physical features that we can detect in the embryo using AI, and the severity of genetic changes,” Life Whisperer co-founder Dr. Michelle Perugini told Medical Device Network this month.
While genetic testing on embryos is currently an optional part of the IVF process, it is done using a sequencing technique called preimplantation genetic testing, not AI. The work Life Whisperer is doing illustrates that not only can AI help to create life in women that turn to IVF to become pregnant, but it may soon also help determine the genetic quality of children of the future. The frontiers of science continue to push forward.
Artificial Intelligence is being implemented in industries all over the world and is a central theme of the research undertaken at UCIPT. Our work in the HOPE study is using data to assess and shift behavioral outcomes among HIV and other populations.