Metabolic health index outperformed other machine learning algorithms and clinical risk variable-based models
TUESDAY, Jan. 27, 2026 (HealthDay News) — Very premature newborns can be risk-stratified based on metabolic features obtained from routine newborn screening (NBS), according to a study published in the Jan. 21 issue of Science Translational Medicine.
Noting that standard gestational age and birthweight-based classifications of prematurity inadequately capture the variation in newborns” health outcomes, Alan L. Chang, Ph.D., from the Stanford University School of Medicine in California, and colleagues examined whether the metabolic profiles of newborn infants capture additional risk information. An NBS-based metabolic health index was developed using 13,536 NBS blood spot tests from preterm infants in California with linked clinical outcomes of prematurity. Using a deep learning model that provided a single index score in conjunction with subgroup discovery to identify individuals with the strongest metabolite biomarker signals for adverse outcomes of prematurity, the NBS metabolic health index stratified preterm infants at risk for bronchopulmonary dysplasia, intraventricular hemorrhage, necrotizing enterocolitis, and retinopathy of prematurity.
The researchers found that the metabolic health index captured risk signals that differed from gestational age and birthweight; for stratifying at-risk individuals for adverse outcomes of prematurity, the metabolic health index outperformed other machine learning algorithms and clinical risk variable-based models. The index was validated externally in an independent retrospective cohort of very premature newborns in Ontario, Canada, including 2,117 cases and 1,182 controls.
“Using biological measurements collected at birth, we were able to come up with a new definition for prematurity that is based on the actual outcomes of these babies,” co-senior author Nima Aghaeepour, Ph.D., also from the Stanford University School of Medicine, said in a statement.
One author disclosed ties to the biotechnology industry.
Abstract/Full Text (subscription or payment may be required)
Bacterial Vaginosis Linked to Tripled Odds of STI Coinfection 
Glyphosate Exposure During Pregnancy Linked to Preterm Birth 
AI Can Accurately Detect Left Ventricular Dysfunction From Electrocardiograms 
Eosinophilic Esophagitis Prevalence May Be Higher Than Thought in Pediatric Patients With Asthma 
Exacerbation Risk Profiles Vary With House Dust Mite Sensitization in Pediatric Asthma 
Metabolic Dysfunction-Associated Steatotic Liver Disease Linked to Higher Odds of Eosinophilic Esophagitis 
Female Emergency Medicine Physicians Order More Tests, Admit More Patients 
Greater Physician Knowledge Linked to Lower Use of Low-Value Services 
