🤖 AI Summary
This study addresses the challenge of early cesarean section (CS) risk assessment in resource-limited or home-based prenatal settings. We propose an interpretable predictive framework integrating self-reported late-pregnancy clinical data with portable 3D optical body scanning. Methodologically, we introduce MvBody—a novel multi-view Transformer architecture that jointly models 3D geometric body shape features (particularly head-shoulder morphology) and clinical variables for the first time. To enhance generalization under limited sample sizes, we incorporate metric learning; interpretability is ensured via Integrated Gradients, yielding clinically actionable feature attributions. Evaluated on an independent test set, our method achieves 84.62% accuracy and an AUC-ROC of 0.724. Results validate 3D body shape as a low-cost, non-invasive biomarker for CS risk prediction and establish a new paradigm for scalable, explainable antenatal risk stratification in primary care.
📝 Abstract
Accurately assessing the risk of cesarean section (CS) delivery is critical, especially in settings with limited medical resources, where access to healthcare is often restricted. Early and reliable risk prediction allows better-informed prenatal care decisions and can improve maternal and neonatal outcomes. However, most existing predictive models are tailored for in-hospital use during labor and rely on parameters that are often unavailable in resource-limited or home-based settings. In this study, we conduct a pilot investigation to examine the feasibility of using 3D body shape for CS risk assessment for future applications with more affordable general devices. We propose a novel multi-view-based Transformer network, MvBody, which predicts CS risk using only self-reported medical data and 3D optical body scans obtained between the 31st and 38th weeks of gestation. To enhance training efficiency and model generalizability in data-scarce environments, we incorporate a metric learning loss into the network. Compared to widely used machine learning models and the latest advanced 3D analysis methods, our method demonstrates superior performance, achieving an accuracy of 84.62% and an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.724 on the independent test set. To improve transparency and trust in the model's predictions, we apply the Integrated Gradients algorithm to provide theoretically grounded explanations of the model's decision-making process. Our results indicate that pre-pregnancy weight, maternal age, obstetric history, previous CS history, and body shape, particularly around the head and shoulders, are key contributors to CS risk prediction.