Maternal and Fetal Health Status Assessment by Using Machine Learning on Optical 3D Body Scans

2025-04-08

AI Summary

This study investigates optical 3D body scanning at 18–24 weeks’ gestation as a non-invasive, low-cost alternative to ultrasound for predicting adverse pregnancy outcomes—including preterm birth, gestational diabetes mellitus, and gestational hypertension—as well as estimating fetal weight. Method: We propose a novel dual-stream feature extraction architecture: a supervised stream modeling temporal dynamics of abdominal girth using LSTM/TCN, and an unsupervised stream learning global body-shape representations via autoencoders; both streams are fused with demographic covariates and jointly optimized in a multimodal framework. Contribution/Results: This is the first systematic validation of 3D anthropometric data for multi-condition pregnancy risk prediction. Experiments demonstrate prediction accuracies exceeding 88% for all three complications. Fetal weight estimation achieves ≤10% error in 76.74% of cases—improving upon conventional anthropometry by 22.22%. The approach establishes a scalable, remote, and radiation-free paradigm for prenatal monitoring.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

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 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 circumference information, and another for unsupervised learning to extract global shape descriptors, alongside a branch for demographic data. Our results indicate that 3D body shape can assist in predicting preterm labor, gestational diabetes mellitus (GDM), gestational hypertension (GH), and in estimating fetal weight. Compared to other machine learning models, our algorithm achieved the best performance, with prediction accuracies exceeding 88% and fetal weight estimation accuracy of 76.74% within a 10% error margin, outperforming conventional anthropometric methods by 22.22%.

Problem

• Predict adverse pregnancy outcomes using 3D body scans
• Estimate fetal weight via machine learning algorithms
• Improve maternal health monitoring with accessible telehealth methods

Innovation

• Machine learning on 3D body scans
• Parallel streams for feature extraction
• Combines supervised and unsupervised learning