AI Miracle: First-ever pregnancy using breakthrough infertility tech

Developed over five years, the AI-powered system uses imaging and microfluidics to detect rare signs of male infertility-ushering in a leap for reproductive medicine

Imagine trying to have a baby for nearly 20 years, going through 15 IVF cycles — only to hit roadblock after roadblock. That’s exactly the story of a couple from New York, who just had a life-changing breakthrough thanks to a cutting-edge AI system.

 

A Columbia University team, led by Dr Zev Williams, has launched STAR (Sperm Track and Recovery), an AI-powered platform that identifies rare sperm in azoospermia cases.

 

“If you can look into a sky that’s filled with billions of stars and try to find a new one, or the birth of a new star, then maybe we can use that same approach to look through billions of cells and try to find that one specific one we are looking for,” says Dr Williams. In this case, STAR is trained to pick up “really, really, really rare sperm,” he says. “I liken it to finding a needle hidden within a thousand haystacks. But it can do that in a couple of hours—and so gently that the sperm that we recover can be used to fertilise an egg.”

 

 

What is Azoospermia?

One of the biggest hurdles in male infertility is called azoospermia — a condition where no sperm is detectable in a semen sample. It can be “obstructive,” where there is a blockage preventing sperm from entering the ejaculate, or “nonobstructive” when it is due to decreased sperm production by the testis. Azoospermia affects nearly 1% of the male population and about 10–15% of all males with infertility. Before STAR, the only options were invasive procedures or using donor sperm.

 

Possible causes of azoospermia

• Genetic conditions
• Medical treatments — such as chemotherapy or radiation
• Recreational drug use
• Varicoceles (enlarged veins in the scrotum)
• Absence of the vas deferens (on one or both sides)
• Vasectomy

Other less understood causes, including poor testicular development during fetal or childhood stages, or exposure to environmental toxins

 

How does STAR work?

This system uses:

• An AI-powered algorithm
• A microfluidic chip that filters semen
• A scanner that processes millions of images per hour to identify even the rarest sperm

 

Dr Williams and his team spent five years building a new system that uses AI to find sperm in samples where none can be seen. The process involves a special chip that moves the semen through a tiny tube. If the AI spots a sperm cell, it redirects that small part of the sample into a separate tube so it can be collected. The few sperm found this way can then be frozen, stored, or used to fertilise an egg.

 

The breakthrough moment

Technicians scanned samples for 48 hours straight and found virtually nothing. But in just one hour, STAR identified 44 viable sperm samples — enough for IVF.

 

The couple had done everything: overseas experts, surgery, chemical treatments. Nothing helped. The husband’s azoospermia had defied treatment via surgery, overseas experts, and chemical prep. However, STAR proved there were sperm, just hidden deep. They used it during a regular IVF cycle, and by March 2025, it resulted in a successful fertilisation. For the couple, using STAR did not require any additional testing or procedures; their successful cycle in March proceeded no differently than any of the other IVF cycles they had experienced.

 

A wider future for AI in fertility care

STAR isn’t just a one-time solution — it opens doors for AI to revolutionise fertility diagnostics and treatments.

 

Dr Williams adds that azoospermia is only one of many infertility issues that AI could address. “There are things going on that we are blind to right now. But with the introduction of AI, we are being shown what those things are. The dream is to develop technologies so that those who are told ‘you have no chance of being able to have a child’ can now go on to have healthy children.”

 

For more health updates, follow #HealthWithBS