One in four couples in developing countries is affected by infertility. Around 48.5 million couples experience infertility around the world.
Today, infertility is fast becoming an epidemic. Likewise, the COVID-19 pandemic brought effects on male reproductive health. In the words of the doctor Eduardo González Quintanilla, academic at the UNAM Faculty of Medicine, It has been found that men who have had the disease with moderate to severe symptoms can have effects on their sperm quality and have low testosterone levels (hypogonadism). Therefore, “When the testosterone level decreases and sperm production decreases, it obviously has an impact on fertility.”
In vitro fertilization (IVF) is a technique that helps people with fertility problems to have a baby. Despite the potential of IVF, the results are unpredictable. To make matters worse, access to fertility care is abysmal. However, artificial intelligence for use in fertility clinics, can help shape a future where more people have a better chance of starting families at lower cost than today and with a higher rate of success. Many researchers are looking to take advantage of technology to increase the reliability, affordability, and availability of IVF.
The use of AI in IVF processes has the potential to improve the efficacy of the technique. However, reliance on AI algorithms in such a sensitive medical area could lead to skepticism among potential patients.
IVF begins with a doctor’s evaluation of the cause of the infertility, then moves to the stimulation phase where the doctor determines the best protocol for ovarian stimulation. This is commonly followed by egg and sperm collection, fertilization of eggs using sperm to create embryos, embryo culture in the clinic, embryo transfer to the mother, and a live birth months later. As people go through this process, success rates drop significantly at each stage. In the laboratory, embryologists make various judgments by interpreting images about oocytes (developing eggs), sperm, and blastocysts.
Today, embryo grading is performed by embryologists who manually inspect images for a set of visually detectable features.
Artificial intelligence uses computer vision algorithms to augment this process and predict the likely effectiveness of implantations. AI algorithms are trained on a dataset of more than 200,000 embryo videos and more than 5 million clinical data points drawn from diverse patient demographics. This gives AI models the power to analyze tiny features that are often undetectable by even the most experienced embryologists.
IVF prevalence is expected to grow with greater success and fewer cost barriers to care. In addition, early detection tools are envisioned to alert patients that they may be experiencing declines in fertility, unlike today where patients end up with unrecoverable fertility potential. With increased visibility about their fertility, patients could take early action by freezing sperm, oocytes, or embryos.
Additionally, smartphones will be one of the biggest and most significant improvements in the delivery of fertility services.
