Statistical and Image-Based Deep Learning Modeling to Predict Hearing Preservation in Vestibular Schwannoma Surgery

Researchers have attempted to predict hearing preservation for vestibular schwannoma (VS) patients, with preoperative hearing scores and tumor size identified as useful predictors for hearing preservation. However, prior studies have not directly included magnetic resonance (MR) images in their predictive models, instead using secondary imaging measurements and other clinical features....

Continue reading at PubMed →

Preliminary evidence that deep learning models using preoperative hearing scores and tumor size can predict hearing preservation in vestibular schwannoma surgery; not yet validated for clinical use but warrants monitoring as an emerging decision-support tool.

Reliable preoperative prediction of hearing preservation outcomes could meaningfully improve surgical planning and informed consent for vestibular schwannoma patients.

1. 01Combined statistical and image-based deep learning models to predict hearing preservation after vestibular schwannoma surgery.
2. 02Key predictive variables included preoperative hearing scores and tumor size.
3. 03Deep learning applied to MRI or imaging data alongside clinical metrics.
4. 04If validated, models could support surgical approach selection and patient counseling.
5. 05Published in Journal of Neurological Surgery Part B.

PMID

42979419

DOI

10.1055/a-2793-1232.

Journal

Journal of Neurological Surgery Part B

Publication type

research_article

Evidence level

4

Population

Patients undergoing vestibular schwannoma surgery

Intervention

Statistical and image-based deep learning models for preoperative prediction

Comparator

Statistical models alone