AI Helps Couple Get Pregnant After Trying For 18 Years

A couple trying to conceive a baby for 18 years finally managed to get pregnant thanks to the use of artificial intelligence (AI). The unnamed couple had undergone multiple rounds of in vitro fertilisation, or IVF, across the globe, but to no avail. The IVF attempts were unsuccessful due to azoospermia, a rare condition in which no measurable sperm is present in the male partner's semen. In a typical healthy semen sample, there are millions of sperm cells per millilitre.

Having knocked on every door, the couple turned to the Columbia University Fertility Center (CUFC) to try a novel approach, according to a report in CNN. Using the STAR (Sperm Tracking and Recovery) method, which uses AI to identify hidden sperm in men, the couple had their lucky breakthrough.

Researchers at the fertility centre examined the semen sample with the AI-powered system and managed to find the hidden sperm. After recovering the sperm, it was used to fertilise the wife's egg via IVF, and she became the first-ever woman to conceive using the STAR method.

"It took me two days to believe I was actually pregnant," the woman said. "I still wake up in the morning and can't believe if this is true or not. I still don't believe I am pregnant until I see the scans."

Also Read | 9-Year-Old US Girl Dies After Mother Intentionally Leaves Her In Hot Car To Work 8-Hour Shift

The STAR method

The STAR method was developed after a five-year research by Dr Zev Williams, director of the CUFC and his colleagues. The team was left amazed as well after the method yielded results in real life.

"A patient provided a sample, and highly skilled technicians looked for two days through that sample to try to find sperm. They didn't find any. We brought it to the AI-based STAR System. In one hour, it found 44 sperm. So right then, we realised, 'Wow, this is really a game-changer. This is going to make such a big difference for patients,' " said Mr Williams, who led the research team.

After a semen sample is placed on a specially designed chip under a microscope, the STAR system uses high-powered imaging to scan the entire semen sample and capture over eight million images in under an hour. AI, which has been trained to identify sperm cells, then steps in and spots the reproductive cell.