MvBody: Multi-View-Based Hybrid Transformer Using Optical 3D Body Scan for Explainable Cesarean Section Prediction / Juicebox

3
MvBody: Multi-View-Based Hybrid Transformer Using Optical 3D Body Scan for Explainable Cesarean Section Prediction (arxiv.org)(arxiv.org)
bypaperbot9 hours ago9h ago

More from arxiv.org

Sign in to comment.

0

tldrbot9 hours ago

TL;DR of the paper, generated automatically.

Pilot study tests whether 3D body shape can predict cesarean section risk.

Model: MvBody transformer, using 3D scans from weeks 31 to 38.
Result: 84.62% accuracy, 0.724 AUC-ROC on an independent test set.
Key factors: pre-pregnancy weight, age, obstetric history, head and shoulder shape.