Artificial intelligence (AI) has been shown to identify cancer, locate cavities and provide medical information. Now, you can help fertility specialists choose the best embryo for in vitro fertilization (IVF).
According to the Centers for Disease Control and Prevention (CDC), one in five adult married women in the United States is still unable to conceive after one year of trying. As a result, many turn to IVF for help. 1% to 2% of all births in the nation are the result of fertility treatments.
The American Society for Reproductive Medicine estimates that the procedure costs an average of more than $12,000 per session and is not guaranteed. Also, most women need more than one try.
The odds are bound to be improved by AIVF, a reproductive technology company based in Tel Aviv, Israel.
Its AI-powered EMA software, which is used to evaluate embryos, aims to analyze huge volumes of data to simplify the embryo selection process.
According to Daniella Gilboa, embryologist and co-founder of AIVF, “IVF is one of the most important medical developments of the last 50 years, but it’s not good enough.”
Only one in five pregnancies occurs because success rates are only 23% to 25% across all age groups.
The inability of IVF facilities to meet the growing demand, according to Gilboa, is one of the main problems.
The need for IVF is increasing, but the supply is limited as more and more women freeze their eggs to delay pregnancy and focus on their careers.
Only 20% of the need is met in the United States, therefore 80% of those women are giving up on having children.
Embryo choice is one of the most important decision-making steps in the IVF process, according to Gilboa.
Traditionally, human doctors have been tasked with making that decision on their own.
Imagine being an embryologist and having to choose which embryo in a hectic lab environment has the best chance of becoming a baby, he added.
“You can have eight, ten or twelve identical embryos, and from time to time you have to decide which one to keep. In essence, you are looking at the embryos under a microscope.
Using the EMA software for IVF, an AI model assists the clinician by evaluating the embryos and using its sophisticated algorithm to select the best prospects for a healthy pregnancy.
“The AI has been trained to detect embryonic characteristics that correlate with different outcomes, such as genetic abnormalities, implantation or gender, that cannot be seen with the human eye,” Gilboa said.
Each embryo receives a numerical score. The final choice could then be made by the doctor.
Gilboa said that without AI, doctors would have to rely on the appearance of the embryo to assess its quality, “but that’s based on subjective human analysis that doesn’t really quantify the actual chances of getting pregnant,” he added.
“AI enables the physician to reduce uncertainties and generate accurate and understandable information.”
He added that AI is also significantly faster, examining embryos in a small fraction of the time it takes a human, allowing clinics to treat more patients and handle a higher volume of demand.
Numerous time-lapse videos of developing embryos were used to train EMA’s AI program, which ultimately learned which embryos would and would not survive.
Gilboa added: “You need a lot of data. “Building a model that was good enough to start using it took a long process, with many durations.”
Dr. Shahin Ghadir, a California-based Trimly fertility coach and double-board-certified infertility specialist, said AI technology like AIVF could be “helpful and useful.” (Trimly is an Internet resource for health care advice.)
According to Fox News Digital’s Ghadir, “The field of reproductive and fertility medicine has experienced significant growth constraints due to the lack of manpower and experience available to work in this industry.”
“This technology would be highly appreciated because there are very few embryologists and it is difficult to train them.”
Embryologists are still needed in the labs, he continued, but fusing their insights with artificial intelligence could go a long way.
Gilboa stressed that while the EMA helps simplify and speed up the embryo selection process, it does not claim to take the position of medical professionals.
“At the end of the day, it’s the human being who makes the decision, not the AI,” he said. It is simply a tool to help in the evaluation of the embryos by the doctor, the consultation with the patient and the improvement of the IVF service.
It’s “humans with AI”, not “humans against AI”.
Ghadir stressed that before it is implemented, artificial intelligence must be “examined under meaningful criteria”, although he supports the evaluation of its potential.
“Some of the risks and limitations of artificial intelligence in an IVF environment and laboratory include errors in the classification of the embryos that could affect the results,” said the expert.
The advice for using AI in this situation is to compare it against expert evaluations in parallel over a period of time, until there is absolute certainty that the AI is just as accurate.
The idea of using AI in embryo selection can potentially involve some ethical issues, which may have an impact on the individual choices made by patients and their families.
AIVF’s technology, which is currently used in Europe, Southeast Asia and South America, is expected to be available in the United States “very soon,” according to Gilboa.
Feedback from clinics that have purchased and are using the software has been favourable.
Studies have shown that IVF success rates in clinics have increased by 30%, Gilboa added.
He stated that because the technology could lead to successful pregnancies in fewer sessions, it could also potentially reduce the cost to the patient.
According to her, pregnancy typically requires three to five standard IVF cycles, but only an average of 1.6 with IVF.
Gilboa continued: “Through advanced AI, patients who want a child can participate in the IVF procedure with full laboratory transparency.”
Subscribe to our latest newsletter
To read our exclusive content, sign up now. $5/month, $50/year
Categories: Technology
Source: vtt.edu.vn