Researchers at Stanford (Calif.) Medicine have developed an AI model that can predict which premature infants are likely to develop serious medical complications.
Researchers analyzed blood samples from 13,536 newborns born more than 10 weeks early in California between 2005 and 2010, according to a Jan. 21 news release. Using AI, the team used blood samples collected during routine newborn screenings to identify patterns in molecules linked to four major prematurity complications: brain bleeding, lung disease, intestinal injury and eye disease. The model was validated using data from 3,299 preterm infants in Ontario, Canada, the release said.
The findings, published Jan. 21 in Science Translational Medicine, showed the AI-generated metabolic index predicted these complications with more than 85% accuracy. The tool outperformed traditional risk factors such as gestational age and birth weight. Researchers said it could help personalize neonatal care, improve outcomes and guide hospital transfers.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.