A newly published academic study shows how Fit3D 3D body scanning technology was used as part of a machine-learning research framework to explore indicators associated with cesarean delivery. In the study, optical 3D body scans captured with Fit3D were combined with basic maternal information—such as age, pre-pregnancy weight, and obstetric history—to evaluate how external body-shape features during late pregnancy relate to delivery outcomes. The research highlights the potential value of surface-based 3D scanning as a non-invasive data source for prenatal assessment.

By analyzing Fit3D scan data alongside clinical inputs, the researchers identified measurable relationships between specific body-shape characteristics and cesarean-section outcomes. The model was able to surface which regions of the body contributed most strongly to these predictive signals, offering a clearer view into how physical form and maternal context intersect with delivery risk. This approach demonstrates that externally captured body-shape data can carry meaningful information when examining pregnancy-related outcomes.

This study expands the potential research and healthcare applications of Fit3D beyond fitness and body composition tracking, showing how 3D body scanning can support deeper insights into complex physiological events like childbirth. While the findings are research-focused and not intended for clinical decision-making on their own, they point toward a future where scalable, contact-free body scanning can complement traditional prenatal evaluation and research.

‍

This study was done at The George Washington University by James Hahn & 

Yijiang Zheng

Read the full study here:
https://arxiv.org/pdf/2511.03212

‍