Prediction of Aspiration Risk by Using Vocal Biomarkers: Machine Learning Development and Validation Study
Otolaryngology (ear, nose, and throat) patients at high risk for aspiration have quantifiable voice characteristics that significantly differ from those who are at a low risk for aspiration, as detected by an ML model trained to analyze sustained phonation and tested on an independent cohort.
Authors
- Visar Berisha (ORCID: https://orcid.org/0000-0001-8804-8874)
- Sara Charney (ORCID: https://orcid.org/0000-0003-0755-9280)
- Julie Liss (ORCID: https://orcid.org/0000-0001-8782-2901)
- Rebecca L. Pittelko
- Abdelmohaymin Abdalla (ORCID: https://orcid.org/0000-0003-4566-9325)
- Jianwei Zhang (ORCID: https://orcid.org/0000-0001-7726-5638)
- Stacy Holyfield
- CYRIL VARGHESE
- Hunter Stearns
- Lindsay Rigelman
- Elizabeth Reeves
- Adam Brown
- David Lott
- Diana Orbelo
- Nan Zhang
- Victor Ortega
- Michelle Higgins
Institutions
- Mayo Clinic in Arizona (US)
- Mayo Clinic Hospital (US)
- Mayo Clinic in Florida (US)
- Arizona State University (US)
Publication Details
- Journal
- JMIR Formative Research
- Published
- 2026-02-04
- DOI
- https://doi.org/10.2196/86069
- Primary Topic
- Dysphagia Assessment and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00