A Stanford-led study shows AI can accurately predict which preterm infants will suffer complications based on metabolite patterns in newborn blood samples.
Key Details
- 1AI model used dried blood spot samples from 13,536 premature infants in California, born more than 10 weeks early.
- 2Validated the algorithm on 3,299 preterm infants from Ontario, Canada.
- 3AI identified six key blood measurements, forming a metabolic health index.
- 4Combined with clinical data (gestational age, birth weight, sex, Apgar scores), the index predicted four major complications (intestinal, eye, lung, brain) with over 85% accuracy.
- 5Research published in Science Translational Medicine (DOI: 10.1126/scitranslmed.adv4942).
Why It Matters
This approach enables much more precise risk stratification for preemies, paving the way for personalized neonatal care, early intervention, and potentially reduced morbidity through targeted resource use. It represents a significant advance in applying AI to high-impact clinical prediction using routine biomedical data.
Source
EurekAlert
Related News
•EurekAlert
AI Model BIOPREVENT Predicts Complications in Stem Cell Transplant Patients
A new AI tool, BIOPREVENT, predicts serious post-transplant complications months before symptoms appear using blood biomarkers and clinical data.
•EurekAlert
New Review Explores Cancer-Inflammation Link and Imaging AI in Precision Therapy
A recent review highlights inflammation’s dual role in cancer progression and how emerging tools like AI and imaging biomarkers are enhancing personalized immunotherapy.
•EurekAlert
CNN-Based AI Enhances Lung Nodule Detection on CT Scans
A CNN-based system achieved high accuracy in detecting and classifying pulmonary nodules using LIDC-IDRI CT data.