A Denver company has received federal approval to market an artificial intelligence program it says can predict when babies will arrive based on their ultrasounds, raising the possibility of flagging premature births.<\/p>\n
Delivery Date AI predicts when a baby will be born, with an 11-day margin of error in either direction, based on second- and third-trimester ultrasounds.<\/p>\n
While the U.S. Food and Drug Administration doesn\u2019t allow maker Ultrasound AI<\/a> to advertise the product as a premature birth detector, an earlier-than-expected predicted birth date would signal to parents and their doctor that the baby might arrive sooner than is optimal.<\/p>\n The FDA process<\/a> for approving relatively low-risk medical devices requires the manufacturer to show that it works as promised and to collect data about any adverse effects when providers begin using it. Companies don\u2019t have to prove that patients treated with it fared better than those who weren\u2019t.<\/p>\n About one in 10 Colorado babies is born prematurely, which is in line with the national average, according to the March of Dimes<\/a>. Black and Native American women are at higher risk, even if they are healthy.<\/p>\n Babies born prematurely are at an elevated risk of lung problems and infections<\/a> in their first months of life. They also have increased odds of disabilities as they grow, including hearing or vision problems.<\/p>\n The American College of Obstetricians and Gynecologists defines<\/a> a full-term pregnancy as 39 to 40 weeks, dated from the mother\u2019s last\u00a0menstrual period before conception. With current technology, babies have a slim chance of survival at 21 weeks<\/a>, with the odds that they\u2019ll live to go home rising as they get closer to full-term.<\/p>\n The AI was trained on millions\u00a0of ultrasound images<\/a> from the University of Kentucky that had information about how long the pregnancy lasted, with the patients\u2019 personal data removed.<\/p>\n Eventually, it found eight measures that correlated with how long a pregnancy would last, including seven that human experts hadn\u2019t previously linked to preterm birth, founder Robert Bunn said. Those included abnormalities in the mother\u2019s placenta, uterus and ovaries, as well as the fetus\u2019s kidneys and heart rate, he said.<\/p>\n One of the problems, an unusually fast fetal heart rate, specifically correlated with early induced births because the mothers developed high blood pressure during pregnancy<\/a>, known as preeclampsia, Bunn said. While it isn\u2019t approved to predict preeclampsia at this point, the AI could eventually help flag which patients need more monitoring or preventive treatment, such as low-dose aspirin, he said.<\/p>\n \u201cWe\u2019re going to save the lives of mothers in the future, too,\u201d he said.<\/p>\n Obstetricians already check for the eighth measure, which is the length of the bottom of the uterus, or cervix. The cervix shortens and opens as birth approaches<\/a>, so doctors sometimes use a stitch to keep it closed in patients at high risk for premature birth.<\/p>\n A tool that could reliably predict when babies will be born would be extremely valuable in obstetrics care, said Dr. Nicholas Behrendt, who works in the neonatal intensive care unit and treats mothers carrying babies with relatively rare high-risk conditions<\/a> at Children\u2019s Hospital Colorado. He isn\u2019t sure if the AI is ready for routine clinical use as-is, but thinks its predictions will keep improving over time.<\/p>\n Now, providers go down a list of common risk factors to identify which pregnancies need more monitoring, but they aren\u2019t perfect predictors, Behrendt said. Patients with many risk factors may have uneventful pregnancies, while others who seem perfectly healthy have dangerously early deliveries, he said.<\/p>\n \u201cWe know it\u2019s more complicated than a cervix issue,\u201d he said.<\/p>\n Doctors can only delay a preterm birth by a day or two, but that allows them to give the mother steroids, which speed up the fetus\u2019s lung development, Behrendt said. It can also buy time for families that live in areas without a neonatal intensive care unit to transfer to a hospital that can give the baby their best shot at survival and good outcomes, he said.<\/p>\n \u201cIf we can get better at predicting (preterm birth), we can potentially improve neonatal outcomes,\u201d he said.<\/p>\n Providers may not immediately have treatments specific to the newly flagged risk factors, but knowing about them will open up research opportunities, Bunn said. Right now, the primary recommendations for preventing preterm birth<\/a> are getting checked for certain infections and avoiding smoking, alcohol and other drugs \u2014 not terribly useful to patients who\u2019ve had a premature birth despite a healthy lifestyle.<\/p>\n The FDA approval allows providers to use the AI with adult patients between 14 and 37 weeks of pregnancy with a single fetus that doesn\u2019t have any known anomalies, such as an irregular number of chromosomes. For a typical patient, the AI scan would cost $100 to $200, Bunn said.<\/p>\n The product is new enough that insurers likely haven\u2019t decided whether to cover it.<\/p>\n Typically, doctors don\u2019t attempt to predict a baby\u2019s birth date, beyond the \u201cdue date\u201d of 40 weeks past the mother\u2019s last period. A study from Australia found about one in 20 babies arrives on their due date<\/a>, though more than half make their debut within a week before or after the expected date.<\/p>\n They often check the cervix<\/a> for signs that labor is near as the anticipated end of pregnancy approaches, but those also aren\u2019t a perfect indicator. Some women give birth within a few days of an exam that finds no evidence their cervixes are starting to open.<\/p>\n Bunn had previously used AI to search for new sources of oil underground, but pivoted to medical work after his wife had a series of miscarriages. They\u2019ve since had five children.<\/p>\n When he started a decade ago, doctors didn\u2019t think ultrasounds could offer meaningful information about premature birth, though they started to come on board and help improve the AI after it found risk factors they hadn\u2019t expected, he said.<\/p>\n \u201cHumans can\u2019t sit there and learn from millions and millions of images\u201d in the way that AI can, he said.<\/p>\n Risk factors for preterm birth include:<\/p>\n Previous early deliveries Source: National Institute of Child Health and Human Development<\/a><\/p>\n
\nCarrying twins or triplets
\nHaving a short cervix (the lower portion of the uterus)
\nConceiving via in-vitro fertilization
\nCertain infections, including sexually transmitted ones
\nHigh blood pressure or blood-clotting problems
\nHaving obesity or being underweight at the start of pregnancy
\nConceiving again within six months of a birth
\nHaving diabetes
\nBeing younger than 18 or older than 35
\nSkipping prenatal care
\nSmoking
\nDrinking alcohol
\nUsing illicit drugs
\nExperiencing domestic violence
\nWorking a physically demanding job
\nHaving exposure to unsafe chemicals or radiation
\nExperiencing high levels of stress<\/p>\n