Predicting gestational age at birth in the context of preterm birth from multi-modal fetal MRI

2026-06-18

AI Summary

This study addresses the challenge of accurately predicting gestational age at delivery using multimodal fetal MRI to optimize perinatal management and mitigate risks associated with preterm birth. Moving beyond conventional classification approaches, the work formulates preterm prediction as a continuous gestational age regression problem and introduces a tailored machine learning pipeline incorporating customized data imputation, feature selection, and regression modeling. The model integrates multimodal MRI features, including placental T2* imaging and cervical length, and is rigorously evaluated via stratified 10-fold cross-validation and ablation studies. In a cohort of 426 subjects, the approach achieves an R² of 0.13 and a mean absolute error of 2.74 weeks; when dichotomized into preterm versus term delivery, it yields an accuracy of 0.77 (sensitivity: 0.59, specificity: 0.82), demonstrating its feasibility and clinical potential.

Abstract

Preterm birth is associated with significant mortality and a risk for lifelong morbidity. The complex multifactorial aetiology hampers accurate prediction and thus optimal care. A pipeline consisting of bespoke machine learning methods for data imputation, feature selection, and regression models to predict gestational age (GA) at birth was developed and evaluated from comprehensive multi-modal morphological and functional fetal MRI data from 333 control cases and 93 preterm birth cases. The GA at birth predictions were classified into term and preterm categories and their accuracy, sensitivity, and specificity were reported. An ablation study was performed to further validate the design of the pipeline. Performance was evaluated using stratified 10-fold cross-validation. The pipeline achieves an R2 score of 0.13 and a mean absolute error of 2.74 weeks. It also achieves a 0.77 accuracy, 0.59 sensitivity, and 0.82 specificity across folds. The predominant features selected by the pipeline include cervical length and statistics derived from placental T2* values. The confluence of fast, motion-robust and multi-modal fetal MRI techniques and machine learning prediction allowed the prediction of the gestation at birth. This information is essential for any pregnancy. To the best of our knowledge, preterm birth had only been addressed as a classification problem in the literature. Therefore, this work provides a proof of concept. Future work will increase the cohort size to allow for finer stratification within the preterm birth cohort. Our code is available at https://github.com/dfajardorojas/ml-for-preterm-birth-.

Problem

• preterm birth
• gestational age prediction
• fetal MRI
• multi-modal imaging
• pregnancy outcome

Innovation

• multi-modal fetal MRI
• gestational age prediction
• machine learning pipeline
• preterm birth regression
• feature selection