After nearly two decades of unsuccessful attempts to start a family, a couple at Columbia University Fertility Center has become the first to get pregnant thanks to a groundbreaking AI system designed to find even the rarest sperm. The couple, identified as 38-year-old Rosie and her husband, had spent nearly 19 years trying to conceive and underwent 15 unsuccessful IVF attempts, reports Time. They finally found success with a new technology that offers hope to those facing male infertility caused by azoospermia—a condition where no sperm is detectable in semen.
The AI tool, called STAR (Sperm Track and Recovery), uses an algorithm paired with a fluidic chip that screens samples, searching for rare sperm cells invisible to even experienced embryologists. The approach, developed by Dr. Zev Williams and his team, borrows from astrophysics, where AI scans for new stars among billions in the sky; here, it scans millions of cells for scarce sperm. Once found, the sperm can be preserved or used in fertilization. Prior to STAR, men with azoospermia had few options besides using donor sperm or trying invasive and sometimes risky procedures. For Rosie and her husband, STAR found sperm in samples where manual searches found none.
"The embryologists really worked hard to find sperm, since they didn't want to be outshone by a machine," Williams tells Time. "In one of the samples they analyzed for two days and found no sperm, STAR found 44 in an hour." Rosie's successful pregnancy in March 2025 did not require any extra IVF testing or steps. Sperm collected with STAR was used immediately to fertilize Rosie's eggs. Now four months along, Rosie reports the experience still feels unreal after years of disappointment. Dr. Williams sees broader potential for AI in tackling other infertility challenges, noting that it may reveal biological details previously missed. (This content was created with the help of AI. Read our AI policy.)
,
uBlock 
,
and
Ghostery 
)
