First AI-Enabled Pregnancy Helps Couple Realize Dream After 18 Years

AI can help with everyday tasks like writing emails or making grocery lists—but for the first time, it’s had a direct hand in something far more meaningful: helping a couple conceive.

Last year Columbia Fertility pioneered a new AI method to identify and isolate sperm cells in men with low sperm counts. Known as the STAR method (Sperm Tracking and Recovery), the innovative technology brought hope to men diagnosed with azoospermia, a condition where sperm is often undetectable in semen samples.

Now, for the first time, the STAR Method has led to pregnancy. After 18 years of trying, one couple is now 12 weeks along, marking what may be the world’s first baby conceived with the direct help of AI. While AI has supported fertility decisions in the past, this is the first time it has physically done the work—finding the sperm that made pregnancy possible.

How the Technology Works

Inspired by the high-tech processes astrophysicists use to discover distant galaxies, the STAR method allows fertility specialists to locate and isolate rare sperm cells. “We’re using the same technologies that are used to search for life in the universe to help create new life right here on Earth," Zev Williams, MD, PhD, director of the Columbia University Fertility Center, explained.

In a typical healthy semen sample, there are millions of sperm cells per milliliter, yet for men with azoospermia, even a single sperm cell may be rare. According to Williams, the STAR method overcomes the obstacles in detecting viable sperm by using high-powered imaging to scan the entire semen sample and capture over 8 million images in under an hour. AI then steps in to quickly and accurately identify sperm cells.

Once located, the team isolates sperm cells using a tiny microfluidic chip. This chip gently directs the portion of the sample containing sperm cells into a designated area, reducing the risk of damaging the delicate cells. Then, a specially programmed robot precisely removes each sperm cell within milliseconds, avoiding conventional processes like centrifugation that can harm cell viability.

“Imagine searching for a single needle hidden among a thousand haystacks scattered across ten football fields—and finding it in under two hours," Williams told The Bump. "That’s the level of precision and speed delivered by the STAR system. Using AI, microfluidics, and robotics, it combs through a seemingly lifeless semen sample to identify and isolate a single viable sperm cell, making the impossible possible for men once told they had no chance of biological fatherhood.”

How It’s Changing The Game

The STAR method marks a substantial improvement over previous methods, such as surgical sperm extraction or manually scanning centrifuged samples. These traditional approaches are not only costly and sometimes painful but also come with risks of inflammation and reduced testosterone. By contrast, the AI-assisted STAR method is noninvasive and maintains the sperm’s viability without exposing it to harsh treatments.

“By avoiding centrifugation, lasers, dyes or other harsh systems, the STAR system provides a gentler environment that minimizes stress on sperm cells, giving them the best possible chance of being identified and maintaining their viability," Williams explains. After extraction, the sperm cell can either be used immediately for IVF or frozen for future use. With IVF, even one healthy sperm cell can fertilize an egg, making this breakthrough particularly meaningful. “With our method, many men who were previously told they have no chance of having a biological child now have that chance,” Williams hopefully added.

The STAR Method is being used on hundreds of patients exclusively at Columbia University Fertility Center and they plan on expanding access soon. You can learn more about the new technology and other fertility treatments at ColumbiaDoctors.org.