A groundbreaking artificial intelligence tool developed by researchers at Columbia University has enabled doctors to identify sperm cells in men previously diagnosed with azoospermia, potentially offering new parenthood opportunities for some couples. This development was reported by the BBC.
Dubbed Star (Sperm Track and Recovery), this innovative method from Columbia University’s Fertility Center employs artificial intelligence to examine semen or tissue samples, detecting extremely rare sperm cells that typically evade standard laboratory techniques. This advancement may provide men once deemed infertile with the possibility of utilizing their own sperm for fertility treatments.
Azoospermia, a condition characterized by the absence of detectable sperm in conventional tests, affects roughly 10% of all men experiencing infertility and about 1% of the male population overall. The AI-driven Star approach was first revealed in 2025, integrating imaging technology, artificial intelligence, and robotics to locate sperm cells.
During the process, samples are passed through microfluidic chips—tiny devices with etched channels comparable in size to a human hair that manage fluid flow precisely. An imaging system captures approximately 300 images per second as samples traverse these channels, while a machine learning algorithm analyzes the imagery in real time to pinpoint sperm amidst cellular debris.
Researchers highlight that a robot swiftly isolates sperm within milliseconds, circumventing centrifugation—a method known for damaging fragile cells—and allowing doctors to utilize the retrieved sperm in in vitro fertilization (IVF), where egg fertilization occurs outside the body.
This announcement coincides with increasing AI adoption in medical fields. In April, OpenAI’s clinical version of ChatGPT surpassed human physicians in specific tasks, and Mayo Clinic researchers unveiled an AI model capable of early pancreatic cancer detection through subtle scan changes.
Zev Williams, director at Columbia University Fertility Center, noted that the Star method identified sperm in nearly 30% of tested patients previously informed they had no viable sperm. He added that this technique discovered 40 times more sperm than manual searches by skilled technicians, achieving a perfect sensitivity rate.
“Everyone was just jumping up and down with joy,” Williams told the BBC. “There are so few things where the reward for all the effort that was put into it is something as wonderful and special as this. Now there’s a baby girl and hopefully, God willing, many more to come.”
The first pregnancy using the Star method was confirmed in 2025 involving Samuel and Penelope, who had struggled with conception for over two years due to Klinefelter syndrome—a genetic condition causing males to have an extra X chromosome, often resulting in minimal or nonexistent sperm production.
“It’s starting to feel really real now, especially because I’m feeling movement,” Penelope shared with the BBC. “We had our anatomy scan, and everything is just looking so great.”