Doctors Report the First Pregnancy Using a New AI Procedure
Doctors at Columbia University Fertility Center have reported what they are calling the first pregnancy using a new AI system, in a couple that had been trying to start a family for nearly two decades.
The pregnancy was possible due to an advance developed by the Columbia team, led by Dr. Zev Williams, director of the center, to address azoospermia, or a lack of detectable sperm in the ejaculate. Male factors account for about 40% of infertility in the U.S., and azoospermia is responsible for about 10% of those cases. Until recently, there was little doctors could do to address the lack of sperm needed to fertilize an egg, other than using donor sperm.
While to the naked eye, a sperm sample from a man with azoospermia might look normal, the microscope tells a different story, Williams says. Highly trained technicians rarely find any sperm in these samples, which are often filled with other debris. Add to that the fact that sperm are the smallest cell in the body, and it's not surprising that even the best fertility technicians rarely find sperm in azoospermia samples.
That's where AI comes in. Williams and his team spent five years developing a system that combined an AI algorithm for detecting sperm with a fluidic chip that passed the semen sample through a tiny tubule on a plastic chip. If the AI picked up sperm, that tiny portion of semen would be directed to a separate tubule and collected. The few sperm isolated in this way could then be stored, frozen, or used to fertilize an egg.
Called STAR, for Sperm Track and Recovery, the system was inspired by similar approaches that astrophysicists use to enlist AI to detect new stars and planets. '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 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 fertilize an egg.'
Read More: IVF Patients Say a Test Caused Them to Discard Embryos. Now They're Suing
STAR is distinct from AI systems that have been developed to scan and detect specific features, Williams says, because it combines that analysis with the ability to also actively isolate the target in question—in this case, any sperm found in a semen sample. The system can scan eight million images in about an hour, and Williams remembers the moment when he was convinced that STAR could become a powerful tool for treating certain forms of infertility. 'To test the system, before we discarded samples where embryologists could not find any sperm, we decided to run those samples through the system. The embryologists really worked hard to find sperm, since they didn't want to be outshone by a machine. In one of the samples they analyzed for two days and found no sperm, STAR found 44 in an hour.'
Rosie and her husband became the first couple to get pregnant using STAR in March 2025. The couple spent nearly 19 years trying to get pregnant, and Rosie—who asked to use a pseudonym to protect her privacy—says their Orthodox Jewish faith kept them hopeful during 15 unsuccessful IVF cycles. Prior to the pregnancy, they had explored multiple options to address her husband's azoospermia, including surgery and enlisting an expert from overseas to manually analyze and isolate sperm from his samples. They also researched efforts to extract sperm that were more controversial because they involved using chemicals that could potentially be detrimental to the quality of sperm.
'There really was nothing else out there,' says Rosie, 38, of their options before learning about STAR. 'Especially because I am running quite a few years ahead of where we should be [for fertility]. I'm not that old, but in fertility years—egg-wise—I was reaching my end.'
They were introduced to Williams and his fertility program through a community group and learned everything they could about the system. 'We knew exactly what it was, and knew what they were trying to do,' says Rosie. 'If they could get sperm in a more natural way without chemicals and hopefully chose the good ones—if the program was able to do that, we knew we had a better chance.'
Read More: Why It's So Hard to Have Your Fertility Tested
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. 'We were keeping our hopes to a minimum after so many disappointments,' says Rosie. 'We came in, did what we had to do for the cycle, knowing there was probably a very small chance of anything happening. Why should this be any different from every other time?'
Usually in an IVF cycle, there are far more sperm than eggs, says Williams, but in cases of azoospermia, the opposite is true. So to ensure that a couple has the best chance of a pregnancy, Williams and his team collect several batches of sperm using STAR and freeze them. Then they coordinate the mother-to-be's ovulation cycle on IVF, and on the day they retrieve her eggs, they collect a fresh semen sample, run it through STAR, and use any sperm collected to fertilize any available eggs. The frozen sperm serve as backup in case no fresh sperm can be found.
Within two hours after collecting her husband's sperm that March, they learned that Rosie's eggs had been successfully fertilized and were ready to be transferred to her uterus a few days later. 'After the transfer, it took me two days to believe I was actually pregnant,' says Rosie.
Now four months along, Rosie is receiving standard obstetric care, and all indications are that her pregnancy is proceeding well. 'I still wake up in the morning and can't believe if this is true or not,' she says. 'And I still don't believe [I'm pregnant] until I see the scans.'
Williams says 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.'
Contact us at letters@time.com.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
The Hill
2 days ago
- The Hill
Trump's megabill hits more trouble as Senate conservatives demand changes
The Senate version of legislation to enact President Trump's agenda is hitting new turbulence as conservatives led by Sens. Ron Johnson (R-Wis.), Rick Scott (R-Fla.) and Mike Lee (R-Utah) are demanding deeper spending cuts to address the nation's $2.2 trillion annual deficit. Senate Majority Leader John Thune (R-S.D.) has focused this week on addressing the concerns of Senate GOP colleagues such as Sens. Josh Hawley (Mo.) and Lisa Murkowski (Alaska), who raised alarms about cuts to federal Medicaid spending. But Thune has to worry about his right flank as Johnson and his allies are threatening to hold up the bill unless GOP leaders agree to deeper cuts to federal Medicaid spending and a faster rollback of the renewable energy tax credits enacted under former President Biden. Johnson, Lee and Scott are threatening to vote as a bloc against the bill next week unless it undergoes significant changes. Thune plans to bring the bill to the floor Wednesday or Thursday next week, but he may not have enough votes to proceed on the legislation, say Republican senators. 'There's no way I vote for this thing next week,' Johnson told reporters. 'I don't want to go the Nancy Pelosi route, 'You got to pass this bill to know what's in it,'' he added, referring to the Democratic Speaker emerita who represents California. Johnson noted that senators are taking a closer look at a proposal offered by Scott to significantly reduce the Federal Medical Assistance Percentage (FMAP), or the federal government's share of Medicaid spending, in states that expanded the program under former President Obama's Affordable Care Act (ACA). Lee is pushing for a fuller phaseout of the renewable energy subsidies enacted by Democrats in the Inflation Reduction Act (IRA). 'Mike is handling the IRA provisions of this, Rick Scott is handling the Medicaid. You need to satisfy those two, too. All three of us have to be yes or none of us are yes,' Johnson said. Scott, who founded the Columbia Hospital Corp. and went on to run Columbia/HCA Healthcare Corp., one of the world's largest health care companies, wants to dramatically cut the 90 percent federal match for states that expanded Medicaid under the ACA. 'The focus should be on how do we take care of what Medicaid's original purpose was? It's children and the chronically ill,' he said. Scott argues that able-bodied low-income adults are drawing far too much of Medicaid spending in states that expanded the program, such as California and New York. 'Half the people, half the adults that are on Medicaid under the expanded FMAP are not working,' he said, adding that these people are not disabled. 'We're running $2 trillion deficits.' Scott says Medicaid shouldn't pay out more than Medicare and that states should not be eligible for expanded federal Medicaid payments for new enrollees after two years. He also wants to further crack down on states' use of health care provider taxes to increase their share of federal Medicaid spending. That sets up a fight next week with Senate Republican colleagues who have balked at the cuts to Medicaid spending unveiled Monday by Senate Finance Committee Chair Mike Crapo (R-Idaho). The current Senate bill would reduce the maximum permitted provider tax rate from 6 percent to 3.5 percent by 2031. The Florida senator said colleagues such as Hawley and Sen. Susan Collins (R-Maine), who are worried about limiting health care provider taxes, have a 'legitimate concern' about the fate of rural hospitals. But he argued that the high rate of Medicaid spending won't solve their problems. Collins has proposed a 'provider-relief fund' to the bill to help offset Medicaid cuts for rural hospitals, nursing homes and community health centers. Lee, the Utah Republican, meanwhile is calling for a more rapid and complete phaseout of renewable energy subsidies in the bill and for tougher language to keep tax benefits from going to immigrants who entered the country illegally. 'Green New Deal subsidies that don't terminate by 2028 will effectively become permanent. If you don't want them to be permanent, tell your senators!' Lee posted on social platform X. Language released Monday by the Senate Finance Committee would extend tax credits for hydropower, nuclear and geothermal energy into the 2030s. A faster and broader phaseout of clean energy subsidies would be opposed by Republican senators such as Murkowski, Jerry Moran (Kan.), John Curtis (Utah) and Thom Tillis (N.C.), who warn that a sudden termination of federal support would disrupt the renewable fuel industry, cost jobs and strand billions of dollars in investment. Yet Senate conservatives are ready for a showdown, arguing the deficit poses a major threat to the U.S. economy. 'The deficit will eat us alive if we don't get it under control. If not us, who? If not now, when?' Lee posted Thursday on X. Johnson said Trump promised to balance the budget but argued 'the bill before us does not do it' and will instead worsen deficits over the next decade. He said while the spending cuts in the legislation are 'the most spending reduction we've had ever,' the 'spending increase is unprecedented, 10 times more.' 'Look at the numbers,' he said. The Congressional Budget Office unveiled a new projection that the House-passed bill to enact Trump's agenda would add $3.4 trillion to the debt.
Los Angeles Times
4 days ago
- Los Angeles Times
‘We are still here, yet invisible.' Study finds that U.S. government has overestimated Native American life expectancy
Official U.S. records dramatically underestimate mortality and life expectancy disparities for Native Americans, according to a new, groundbreaking study published in the Journal of the American Medical Association. The research, led by the Boston University School of Public Health, provides compelling evidence of a profound discrepancy between actual and officially reported statistics on the health outcomes of American Indian and Alaska Native (AI/AN) populations in the U.S. The study, novel in its approach, tracks mortality outcomes over time among self-identified AI/AN individuals in a nationally representative cohort known as the Mortality Disparities in American Communities. The researchers linked data from the U.S. Census Bureau's 2008 American Community Survey with official death certificates from the Centers for Disease Control and Prevention's National Vital Statistics System from 2008 through 2019, and found that the life expectancy of AI/AN populations was 6.5 years lower than the national average. They then compared this to data from the CDC's WONDER database, and found that their numbers were nearly three times greater than the gap reported by the CDC. Indeed, the study found that the life expectancy for AI/AN individuals was just 72.7 years, comparable to that of developing countries. The researchers also uncovered widespread racial misclassification. The study reports that some 41% of AI/AN deaths were incorrectly classified in the CDC WONDER database, predominantly misrecorded as 'White.' These systemic misclassifications drastically skewed official statistics, presenting AI/AN mortality rates as only 5% higher than the national average. When they adjusted the data to account for those misclassifications, the researchers found that the actual rate was 42% higher than initially reported. The issue of racial misclassification 'is not new for us at all,' said Nanette Star, director of policy and planning at the California Consortium for Urban Indian Health. The recent tendency for journalists and politicians to use umbrella terms like 'Indigenous' rather than the more precise 'American Indian and Alaska Native' can obscure the unique needs, histories and political identities of AI/AN communities, Star noted, and contribute to their erasure in both data and public discourse. 'That is the word we use — erasure — and it really does result in that invisibility in our health statistics,' she said. Issues related to racial misclassification in public records persist across the entire life course for AI/AN individuals, from birth to early childhood interventions to chronic disease and death. Star noted that in California, especially in urban regions like Los Angeles, Native individuals are frequently misidentified as Latino or multiracial, which profoundly distorts public health data and masks the extent of health disparities. 'It really does mask the true scale of premature mortality and health disparities among our communities,' Star said. Further, said Star, the lack of accurate data exacerbates health disparities. 'It really is a public health and justice issue,' she said. 'If you don't have those numbers to support the targeted response, you don't get the funding for these interventions or even preventative measures.' According to U.S. Census data, California is home to the largest AI/AN population in the United States. That means it has a unique opportunity to lead the nation in addressing these systemic issues. With numerous federally and state-recognized tribes, as well as substantial urban AI/AN populations, California can prioritize collaborative and accurate public health data collection and reporting. Star noted that current distortions are not always malicious but often stem from a lack of training. She suggested that California implement targeted training programs for those charged with recording this data, including funeral directors, coroners, medical doctors and law enforcement agents; allocate dedicated resources to improve the accuracy of racial classification on vital records; and strengthen partnerships with tribal leaders. The study authors suggest similar approaches, and there are numerous examples of successful cases of Indigenous-led health partnerships seen across Canada and the U.S. that have helped reduce health disparities among AI/AN communities that could be used as a template. These efforts would not only help to move toward rectifying historical inaccuracies, but also ensure that AI/AN communities receive equitable health resources and policy attention. 'When AI/AN people are misclassified in life and in death, it distorts public health data and drives inequities even deeper,' said Star. 'Accurate data isn't just about numbers — it's about honoring lives, holding systems accountable and making sure our communities are seen and served.'
Yahoo
5 days ago
- Yahoo
Scientists Discover Startling Trick to Defeat Insomnia
Insomnia is a curse we wouldn't wish on our worst enemy — and scientists have discovered a startlingly simple lifestyle change that appears to be very statistically effective at preventing it. In a new study published in the journal Sleep Health, researchers from Columbia and the University of Chicago report that eating a full day's serving worth of fruits and vegetables strongly appears to help people sleep more soundly throughout the night. Interrupted sleep, which is known as "sleep fragmentation" to researchers, has been found to induce a litany of grim health outcomes ranging from heart failure to diabetes and cognitive problems to cognitive dysfunction. One major culprit might be a familiar one to many participants in our industrial food system: poor nutrition lacking in fresh fruits and veggies. The researchers recruited 34 healthy young adults with an average age of 28 years old who had no known sleep issues before. The participants were tasked with tagging their food input into an app for 201 days, and wore wrist monitors that tracked their sleep throughout. After analyzing the data from the app and wrist monitors with statistical modeling, the researchers found that sleep quality can improve up to a staggering 16 percent after eating five cups of fruit and vegetables — the Centers for Disease Control and Prevention's definition of a full day's serving — as compared to a diet that lacks produce. What's more, the effects were effectively instantaneous: sleep improvements took place the very same nights that participants reported eating lots of fruits and vegetables. "It's remarkable that such a meaningful change could be observed within less than 24 hours," explained UChicago sleep expert Esra Tasali said in the school's press release. Though 16 percent may not seem like much, Tasali characterized it as a "highly significant difference." It's possible, per Columbia's statement on the study, that the amino acid tryptophan — the same one cited in anecdata about getting sleepy post-Thanksgiving turkey — might be responsible. Fruits and vegetables contain carbohydrates that help the brain absorb tryptophan, Columbia explains, which in turn helps aid the production of the sleepy hormone melatonin. Though you can purchase synthetic melatonin supplements at the store, it's tastier and healthier to get your brain to produce it for you by eating produce. Five cups may seem a bit daunting, but the researchers insist that eating more fruits and vegetables in general can help you sleep better even if you don't reach that full serving. "People are always asking me if there are things they can eat that will help them sleep better," author Marie-Pierre St-Onge, the director of Columbia's sleep center, said in the school's press release. "Small changes can impact sleep. That is empowering — better rest is within your control." More on sleep: You Can See When Elon Musk Actually Sleeps by Analyzing His Tweets, and It's Terrifying
