Machine learning demonstrates normal fetal Doppler velocimetry associated with reduced risk of necrotizing enterocolitis among preterm infants with growth restriction

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Normal UA Dopplers heavily weighted in classifying infants unlikely to develop NEC

• Primary Outcome: Development of necrotizing enterocolitis (NEC)

• Nnt Or Sensitivity: Sensitivity 15%, Specificity 95% for normal UA Dopplers predicting absence of NEC

• Confidence Interval: Not reported

Clinical Application

UA Doppler assessment is standard prenatal care; machine learning model would require validation and implementation Relevant to Australian NICUs managing FGR preterm infants; aligns with RANZCOG guidelines for fetal surveillance but requires validation in Australian population Preterm infants <33 weeks gestation with fetal growth restriction

Abstract

BackgroundNecrotizing enterocolitis (NEC) is an intestinal ischemic disease that affects preterm infants with fetal growth restriction (FGR). The role of fetal Dopplers in stratifying risk for developing NEC is unclear but the innovative use of machine learning technology may aid in identifying their contribution.MethodsThis is a single center retrospective cohort of 164 infants born before 33 weeks' gestation with FGR from 2016 to 2019. We used machine learning to classify NEC and to evaluate the predictive values of gestational age (GA), birth weight (BW), and the presence of abnormal umbilical artery (UA) Dopplers before delivery.ResultsEarly GA and lower BW strongly predicted NEC. The presence of normal fetal UA Dopplers was heavily weighted in classifying infants unlikely to develop NEC. Fetal UA Dopplers had a 95% specificity (15% sensitivity) for NEC.ConclusionsIf validated, normal fetal UA Doppler studies may identify infants with FGR at low risk for NEC who may avoid conservative NEC-prevention strategies.