Med Biol Eng Comput. 2025 Nov 8. doi: 10.1007/s11517-025-03473-0. Online ahead of print.
ABSTRACT
Monitoring maternal and fetal health during pregnancy is crucial for preventing adverse outcomes. While tests such as ultrasound scans offer high accuracy, they can be costly and inconvenient. Telehealth solutions and more accessible body shape information provide pregnant women with a convenient way to monitor their health. This study explores the potential of 3D body scan data, captured during the 18-24 gestational weeks, to predict adverse pregnancy outcomes and estimate clinical parameters. We developed a novel algorithm with two parallel streams which are used for extract body shape features: one for supervised learning to extract sequential abdominal level circumference information, and the other for unsupervised learning to extract global shape descriptors, alongside a branch incorporating shape-related demographic data. Our results demonstrated that 3D body shapes can support the prediction of preterm labor and gestational diabetes mellitus (GDM), as well as the estimation of fetal weight. Compared to other machine learning models, our algorithm achieved the best performance, with prediction accuracies exceeding 89% and fetal weight estimation accuracy of 72.22% within a 10% error margin, outperforming the conventional anthropometric measurements-based method by 18.18%.
PMID:41205023 | DOI:10.1007/s11517-025-03473-0
