Artificial intelligence technology can now select the most promising embryo during IVF and increase the chances of pregnancy.
The AI technology is already being used in Europe, Asia and South America, and could be in the US “very soon,” according to the Tel Aviv-based company that pioneered the technology in Israel.
The software detects the most viable embryos by scoring them based on characteristics that correlate with different outcomes, such as genetic abnormalities or implantation, that cannot be seen with the human eye. Clinics using the algorithm have reported a 30 percent increase in IVF success rates.
IVF, or in vitro fertilization, involves removing an egg from a woman’s ovaries and fertilizing it with male sperm in a laboratory. If the fertilized egg shows signs of growing into an embryo, a doctor implants it into the woman’s uterus, hopefully resulting in a pregnancy.
But the process is expensive — averaging more than $12,000 per session — and not guaranteed, with success rates of about 24 percent across all age groups, meaning women often need more than one attempt.
It’s not the first time AI has been used to increase pregnancy rates. Last month, scientists in California developed a “sperm health test” algorithm that scans swimmers for their shape and how they move to choose the best one for fertilizing an egg.
Dr. Gilboa, co-founder and CEO of AIVF, the reproductive technology company developing the algorithm, said: “The AI is trained to detect embryonic features that correlate with different outcomes – such as genetic abnormalities, implantation or gender – that cannot be seen with the human eye’
Dr. Daniella Gilboa, an embryologist who is the co-founder and CEO of AIVF, the reproductive technology company developing the algorithm, told Fox News digital that embryo selection is one of the most crucial decisions during the IVF process.
Until now, human doctors had to make that choice.
Dr. Gilboa said, “Imagine being an embryologist looking at multiple embryos in a hectic lab environment, and you have to decide which one has the best potential to become a baby.
‘You may have eight, ten or twelve embryos that all look the same – and sometimes you have to make that crucial decision yourself. It’s actually you and the embryos under the microscope.’
Clinicians choose an embryo by its appearance to determine its quality, but Dr Gilboa added: “That’s based on subjective human analysis that doesn’t really quantify the actual chances of getting pregnant.”
EMA, AVIF’s AI-driven embryo evaluation software, processes large amounts of data that the human eye cannot perceive to aid the selection process.
Dr Gilboa said: ‘The AI is trained to detect embryonic features that correlate with different outcomes – such as genetic abnormalities, implantation or sex – that cannot be seen by the human eye.’
The algorithm gives each embryo a numerical score and the doctor can make the final decision.
The AI also works much faster than humans and can evaluate embryos in a fraction of the time, meaning doctors can see more patients and keep up with demand.
According to Dr. Gilboa, only 20 percent of the demand for IVF in the US is met by existing clinics.
The AI software was trained using hours of footage from time-lapse videos of developing embryos to learn which were successful and which were not viable.
Some ethicists worry that using AI to select embryos based on their sex could quickly open the floodgates for designer babies, eugenics and legal problems that our society may not be able to solve.
Dr. Gilboa said the algorithm is not intended to replace doctors, as people will always have the last call.
She added that she expects the technology to be in the US “very soon”.
The software can also reduce costs for the patients if they can get pregnant faster.
Traditional IVF takes an average of three to five treatments for women to conceive, but with AVIF the average is 1.6 treatments, Dr. Gilboa said.