The abstract is read at the publisher; the summary is JClub's.
Data-driven 3D shape features of the trigeminal nerve distinguish pain-implicated nerves from non-pain nerves in 479 trigeminal neuralgia patients, achieving AUROC 0.719.
- Why it matters: Neurovascular compression alone does not explain which trigeminal nerves become painful, and prior hand-crafted geometry may miss higher-order anatomy linked to symptoms.
- What they did: The study analyzed high-resolution pre-operative MRI from 479 patients undergoing microvascular decompression, comparing predictive models built on data-driven 3D shape features versus predefined geometric measurements.
- The result: In a held-out test cohort, the shape-feature model reached AUROC 0.719 versus 0.626 for hand-crafted metrics (p=0.005), identifying candidate morphology biomarkers tied more closely to TN pain.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.