&w=3840&q=100)
AI Miracle: First-ever pregnancy using breakthrough infertility tech
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.'
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
The Hindu
2 days ago
- The Hindu
Study compares industrialised, indigenous groups, finds inflammation not always linked with ageing
Inflammation may not always be related to ageing and appears to be a consequence of industrialised lifestyles, researchers said, after they found high levels of inflammation in two indigenous populations, which neither increased with age nor led to chronic conditions. The findings, published in the journal Nature Aging, challenge current notions around persistent inflammation related to ageing -- or "inflammaging", the authors said. "These results point to an evolutionary mismatch between our immune systems and the environments we now live in. Inflammaging may not be a direct product of ageing, but rather a response to industrialised conditions," lead author Alan Cohen, associate professor of environmental health sciences at Columbia University, US, said. They added that a holistic approach, looking at culture, environment and lifestyle factors, needs to be taken while studying ageing processes. "In industrialised settings, we see clear links between inflammaging and diseases like chronic kidney disease," Cohen said. "But in populations with high infection rates, inflammation appears more reflective of infectious disease burden than of ageing itself," the lead author said. The researchers looked at four populations -- two industrialised ones from Italy and Singapore and two indigenous, non-industrialised communities, called the 'Tsimane' of the Bolivian Amazon and the 'Orang Asli' of peninsular Malaysia. Inflammation levels due to ageing were found to be similar between the two industrialised populations studied, but did not hold in the indigenous groups, where inflammation was found to be driven largely by infection rather than age. Further, the inflammation seen in the native communities did not increase with age and also did not result in chronic diseases -- such as diabetes, heart disease and Alzheimer's -- a regular feature of modern, industrialised societies, the researchers said. "Infammaging, as measured in this manner in these cohorts, thus appears to be largely a byproduct of industrialised lifestyles, with major variation across environments and populations," the authors wrote. They added that chronic diseases are rare or even absent among native populations, meaning that even when the young in these communities have profiles that look similar on the surface to those of older industrialised adults, they do not lead to disease. "These findings really call into question the idea that inflammation is bad per se. Rather, it appears that inflammation – and perhaps other aging mechanisms too – may be highly context dependent," Cohen said. "On one hand, that's challenging, because there won't be universal answers to scientific questions. On the other, it's promising, because it means we can intervene and change things," the author said. The study analysed a group of 19 cytokines -- proteins created during immune and inflammatory responses -- and found patterns in line with ageing among the Italian and Singaporean individuals, but not among the 'Tsimane' and 'Orang Asli'. The immune systems of the indigenous populations were shaped by persistent infections and distinct environmental exposures, the researchers said.
India.com
2 days ago
- India.com
How AI Helped A Woman Get Pregnant After 19 Years Despite Her Husband's Infertility
For nearly two decades, a couple from New York chased the dream of becoming parents. They tried everything, 15 rounds of IVF, multiple surgeries, top fertility clinics across the world, and still, no success. Doctors gave them the harsh truth: their chances of having a biological child were virtually zero. The reason? The husband suffered from azoospermia, a rare male fertility condition where no sperm is found in the ejaculate. It's a diagnosis that closes the door on natural conception and even complicates assisted reproductive techniques. But just when they were about to give up hope, a game-changing AI technology called STAR (Sperm Track and Recovery) turned their story around. Not only did it find viable sperm that conventional tests couldn't detect, but it also helped the couple achieve what they thought was impossible: a successful IVF cycle. Today, after 19 years, they're expecting their first baby. What Is Azoospermia And Why It's So Hard to Treat? Azoospermia affects about 1 in 100 men and accounts for up to 15% of male infertility cases. It comes in two forms: 1. Obstructive Azoospermia: Blockages prevent sperm from entering semen. 2. Non-Obstructive Azoospermia: The body doesn't produce enough (or any) sperm at all. Causes range from genetics and hormonal imbalances to chemotherapy, radiation, drug use, and exposure to environmental toxins. For years, the only options for couples dealing with azoospermia were donor sperm or highly invasive surgical retrieval, both emotionally and physically taxing alternatives. But now, that narrative is changing. How AI Detected Hidden Sperm in Just One Hour The couple's journey took a turn when they connected with Dr Zev Williams, a leading fertility specialist at Columbia University. He and his team had spent five years developing STAR, a cutting-edge AI tool designed to detect microscopic, previously undetectable sperm in semen samples. 'It's like finding a needle in a thousand haystacks,' Dr Williams said. 'But STAR can do it, and quickly.' Here's how STAR works: 1. Microfluidic chips filter the semen sample. 2. A high-speed scanner captures millions of images per hour. 3. An AI algorithm sifts through every image to spot sperm cells missed by the human eye. The STAR system doesn't just find these sperm, it preserves their quality so they can be used in IVF. And that's exactly what happened in this case. Despite 48 hours of manual examination by lab technicians yielding nothing, STAR found 44 viable sperm in just one hour. That small number was all the couple needed. A Successful IVF Without Additional Procedures Unlike previous IVF cycles that ended in heartbreak, this time the process moved forward with a new sense of optimism. The couple underwent an IVF cycle in March 2025, using the sperm retrieved by STAR. And the result? A successful pregnancy, without needing additional invasive treatments, surgeries, or donor sperm. emphasising the significance, Dr Williams said, "This technology gives hope to people who have been told they have no options. For many, it's life-changing." A Glimpse Into the Future of Fertility Experts are calling this more than just a medical miracle, it's the dawn of a new era in fertility care. AI tools like STAR are poised to transform how we detect, treat, and even understand infertility, especially male-factor cases that have long been overlooked. Dr Williams says, 'There are biological processes we've been blind to. But with AI, we're starting to see the unseen.' With infertility affecting 1 in 6 people globally, according to the World Health Organization, the implications of this breakthrough are massive. Especially for couples who've faced repeated disappointment and felt out of options. From 'No Hope' to New Life The New York couple's story is a powerful reminder that technology and persistence can bring light into even the darkest corners of fertility struggles. AI isn't just transforming machines, it's reshaping human possibility.
India.com
24-06-2025
- India.com
The New Prime Code: How Two Mathematicians Found A Hidden Pattern In Numbers
New Delhi: In a development that has stirred the mathematical world, two researchers have taken a route to unlock hidden patterns in prime numbers – one that blends old wisdom with unexpected tools. Ben Green of the University of Oxford and Mehtaab Sawhney from Columbia University recently presented a technique that brings a new lens to how primes can be grouped, especially those falling under rare formulas like p² + 4q². Their work revives long-standing mathematical curiosities but does so through a fresh window – additive combinatorics. Their approach does not chase primes in the usual ways. Instead, it borrows from methods typically used to understand how seemingly random number sets behave. At the centre of it is an analytical tool called the Gowers norm – a kind of structure detector that can distinguish noise from patterns in sequences. Green and Sawhney are not the first to ask if prime numbers obey higher-order rules, but their combination of tools suggests some may fall in line more predictably than once assumed. Earlier work in this field hinted at such possibilities, but most equations involving strict prime conditions proved too stubborn for current methods. Their result – that infinitely many primes can be expressed as p² + 4q², with both p and q prime – builds a bridge between classical number theory and new-age combinatorics. The mathematical community has taken notice, with people like Joni Teräväinen, a Finnish expert on number structures, saying how rare it is to push primes through such tight forms. While the proof is not universally applicable to every type of prime puzzle, it does crack open a path that might evolve with time. Some skepticism remains. Techniques that rely heavily on the Gowers norm rest on assumptions that still need testing against broader types of prime behavior. As promising as it is, the method will have to show adaptability to tougher problems ahead. Beyond its theoretical appeal, the research matters for other reasons too. Primes form the building blocks of modern encryption. Better understanding their tendencies can strengthen digital security or reshape how algorithms handle data. The story also reminds us how curiosity and cross-pollination can lead to breakthroughs. Drawing from distant corners of mathematics, Green and Sawhney have made it easier to explore questions that once looked unapproachable. Their work might not end here. Echoes of similar methods are already being discussed by other researchers, some of whom believe these techniques could influence how we think about randomness itself – both in math and the technologies that depend on it. Whether or not their result stands as a turning point remains to be seen. But it is already proving that big questions in math still have room for surprising answers.
