About 10% of all babies born in the United States in 2021 were preterm — meaning they were delivered before 37 weeks of pregnancy, according to the Centers for Disease Control and Prevention (CDC).
Premature birth also makes up about 16% of infant deaths.
Now, researchers at Washington University in St. Louis, Missouri, are looking to improve through these odds Use of artificial intelligence.
They developed a deep learning model that could predict preterm birth by analyzing the electrical activity in a woman’s uterus during pregnancy — then they tested the model in a study that was published in PLOS One.
“The key takeaway is that it’s possible to take data as early as week 31 and predict preterm birth as early as week 37” — which surprised researchers, says Aray Nehorai, Ph.D., professor of electrical engineering. Washington University in St. LouisFox News Digital said.
“The AI/Deep Learning automatically learns the most informative features from the data that are relevant to preterm birth prediction,” he added.
Additionally, the results indicate that preterm birth is an abnormal physiological condition, not just one A pregnancy that ended earlyDr. Nehorai.
During the study, researchers performed electrohysterograms (EHGs), which use abdominal electrodes to record electrical activity in the uterus.
They took recordings of these electrical currents from 159 pregnant women who were at least 26 weeks pregnant and “trained” the AI model on that data.
They combined this information with medical information such as the woman’s age and weight, fetal weight, and any bleeding experienced during the first or second trimester.
About 19% of women in the study delivered preterm. In theory, data from those women could be used as a benchmark to predict preterm birth.
“The advantage of our method is that it is cheaper to construct,” said Nehorai of the new study. “Our model was effective in prediction with short EHG recordings, which may make the model easier to use, more cost-effective in the clinical setting, and possibly usable in the home setting.”
Looking ahead, the researchers believe that hospitals and obstetricians should adopt this method as part of women’s routine pregnancy tests. This will then allow pregnant women to take care and make lifestyle changes as needed to protect their baby’s health.
“Our work contributes to the goal of using EHG measuring devices to accurately predict preterm birth.”
“A device dedicated to implementing our method should be developed for this purpose,” Nehorai said
It’s hard to say how long it might be before such tests become widely available, the researchers said.
“There are already some EHG measuring devices on the market – however, predicting preterm birth from EHG data has been challenging,” said Uri Goldstajn, a PhD candidate in the Department of Biomedical Engineering who works under Prof. Nehorai’s supervision at Washington. university
New AI ‘Cancer Chatbot’ Provides 24/7 Support to Patients and Families: ‘Empathetic Perspective’
“Our work contributes to the goal of using devices that measure EHG to accurately predict preterm birth,” he told Fox News Digital.
EHG measurements typically take between 30 and 60 minutes, with additional time needed to set the device on the mother’s abdomen, Goldstadson noted.
“We showed that predictions can be made based on short EHG measurements, less than five minutes, without greatly reducing the accuracy of predictions,” he told Fox News Digital. “This finding is significant, since the long duration of EHG measurement is an important limitation for its adoption in clinical settings.”
The ‘promise’ of deep learning – but caveats
Dr. Suzy Lipinski is a board-certified OB/GYN at Pediatrics Medical Group In Denver, ColoradoWas not involved in the research but shared his input on whether deep learning technology could help solve the problem of premature births in the US
“Being able to predict who is at risk before delivery would be extremely beneficial,” Lipinski told Fox News Digital. “The use of a deep learning model appears to hold promise; however, this study included a relatively small number of patients, so its applicability to the larger population cannot be determined.”
“Previous studies using AI It has not shown great reliability, so further studies and a larger patient population are needed before this method can be used,” he added.
Another potential limitation is that very few places use EHG measurements, the doctor noted.
“The standard in most hospitals and offices is to use a tocodynamometer, which measures pressure, not electricity,” he explained.
Ozempic, Wegovi and pregnancy risks: what you need to know about the issue
If EHG becomes the way to evaluate preterm births, hospitals, birth centers and offices will need to purchase new equipment, which could delay adoption in low-resource areas such as rural and inner cities, Lipinski said.
“A higher rate of preterm birth in this study than the national average also calls into question the applicability,” he told Fox News Digital. “There’s no demographics given about the patient population, so there’s no way to see how this reflects the population of the country as a whole.”
“Being able to predict who is at risk before they go into labor would be extremely beneficial.”
There is also the potential for false positives, Lipinski noted.
“Although this method predicts better than our current method, there are still many patients who would be identified as at risk who may not have had a previous birth,” he said. “These false positive results will create a greater burden of stress on the patient, as well as increase its use Healthcare resources“
If and when this becomes the new standard of care, Lipinski said, preterm labor will require improved treatment.
“Our problems with preterm births are twofold: our prognosis is poor, but the options for prevention after 26 weeks are also poor,” he added.
The researchers share the main limitations of the study
According to Goldsgen, the study has two main limitations.
“First, we developed our work using about 160 samples from two public datasets,” he said. “Although this amount of data was sufficient for our initial investigation, much larger datasets will be required for the development and validation of a medical product.”
A second limitation comes from the nature of deep learning, which can produce accurate results but is usually difficult to interpret, Goldstadson said.
“In other words, understanding how the algorithm makes predictions is challenging,” he explained.
Click here to sign up for our health newsletter
In a discussion of the results in the medical journal, the authors noted that “although machine learning algorithms can contribute to improving healthcare and many studies are making progress in this area, important challenges remain.”
“Development and validation of medical products will require much larger datasets.”
Among those challenges: It can be difficult to identify the reasons behind the algorithm’s predictions, the researchers wrote.
Click here to get the Fox News app
“In our case, although our predictions may influence pregnancy management, our predictions need to be supplemented with additional clinical trials to determine which therapies are most likely to reduce the risk of preterm birth and improve its outcomes,” the researchers added.
Where we collect the information from Source link
Disclaimer:- We include in each post a link to where each content on our website is collected from.If there is a complaint against any post please contact us directly.
Email: post-support.dailyfastnews24.com
You can also write on the popular online news portal dailyfastnews24.com. Writing topics feature, travel, lifestyle, career, IT, agriculture and nature. Send your entry today to [email protected]
advertisement:-If you would like to advertise on our website please contact us here.Our Ads team will contact you very soon.
Email: [email protected]
The cost of advertising:- 1 Post 100 USD Lifetime.
Thank you very much for visiting our website. Have a good day.