Leveraging large language models for automated detection of velopharyngeal dysfunction in patients with cleft palate
This study demonstrates the effectiveness of the Whisper-based model for hypernasality detection. By providing a reliable pretest probability, the Whisper model can serve as a triaging mechanism to prioritize patients for further evaluation, reducing diagnostic delays and optimizing resource allocation.
Authors
- Maria Powell (ORCID: https://orcid.org/0000-0002-6643-8991)
- Roberto A. Guzman (ORCID: https://orcid.org/0000-0003-1623-6336)
- Matthew E. Pontell (ORCID: https://orcid.org/0000-0002-2329-9899)
- Noah Alter (ORCID: https://orcid.org/0009-0004-7233-3450)
- Andrea R. Hiller (ORCID: https://orcid.org/0000-0001-6965-7818)
- Claiborne Lucas
- Amy L. Stone (ORCID: https://orcid.org/0000-0003-3153-151X)
- Catherine Dang
- Andrew James (ORCID: https://orcid.org/0009-0007-8825-7124)
- Hanlin Chen
- J. Silvia Cho
- Myranda Uselton Shirk
- Lily Hofstetter
- Jack Bijur
Institutions
- Prisma Health (US)
- Monroe Carell Jr. Children's Hospital (US)
- Vanderbilt University (US)
- Vanderbilt University Medical Center (US)
Publication Details
- Journal
- Frontiers in Digital Health
- Published
- 2025-03-28
- DOI
- https://doi.org/10.3389/fdgth.2025.1552746
- Citations
- 9
- Primary Topic
- Cleft Lip and Palate Research
- Type
- article
- Field-Weighted Citation Impact
- 16.36