Predicting gestational age at birth in the context of preterm birth from multi-modal fetal MRI
Researchers have developed a machine learning pipeline to predict gestational age at birth using multi-modal fetal MRI data. The system, evaluated on 333 control and 93 preterm birth cases, achieved an R2 score of 0.13 and a mean absolute error of 2.74 weeks. Key features identified for prediction include cervical length and placental T2* values. This work represents a proof of concept for predicting gestation at birth, with future plans to expand the cohort size for more detailed stratification within preterm births. AI
IMPACT Potential to improve preterm birth prediction and care through advanced medical imaging analysis.