EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Leveraging large language models for automated detection of velopharyngeal dysfunction in patients with cleft palate

Myranda Uselton Shirk, Catherine Dang, Jaewoo Cho, Hanlin Chen, Lily Hofstetter, Jack Bijur, Claiborne Lucas, Andrew James, Ricardo-Torres Guzman, Andrea Hiller, Noah Alter, Amy Stone und 2 weitere

Frontiers in Digital Health · 28.03.2025 · 7

DOI: 10.3389/fdgth.2025.1552746 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Digital Health, online erschienen am 28.03.2025. Verfasst von Myranda Uselton Shirk und 13 weiteren Autor:innen. Beteiligte Einrichtung: Data Science Institute, Vanderbilt University, Nashville, TN, United States. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Hypernasality, a hallmark of velopharyngeal insufficiency (VPI), is a speech disorder with significant psychosocial and functional implications. Conventional diagnostic methods rely heavily on specialized expertise and equipment, posing challenges in resource-limited settings. This study explores the application of OpenAI's Whisper model for automated hypernasality detection, offering a scalable and efficient alternative to traditional approaches.

Methods

The Whisper model was adapted for binary classification by replacing its sequence-to-sequence decoder with a custom classification head. A dataset of 184 audio recordings, including 96 hypernasal (cases) and 88 non-hypernasal samples (controls), was used for training and evaluation. The Whisper model's performance was compared to traditional machine learning approaches, including support vector machines (SVM) and random forest (RF) classifiers.

Results

The Whisper-based model effectively detected hypernasality in speech, achieving a test accuracy of 97% and an F1-score of 0.97. It significantly outperformed SVM and RF classifiers, which achieved accuracies of 88.1% and 85.7%, respectively. Whisper demonstrated robust performance across diverse recording conditions and required minimal training data, showcasing its scalability and efficiency for hypernasality detection.

Conclusion

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.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligence (AI)cleft palatehypernasality detectionmachine learning (ML)speech diagnosticsvelopharyngeal dysfunction (VPD)

Autor:innen und Institutionen

  • Data Science Institute, Vanderbilt University, Nashville, TN, United States.
  • Department of General Surgery, Prisma Health Greenville, Greenville, SC, United States.
  • Department of Plastic Surgery, Vanderbilt University Medical Center, Nashville, TN, United States.
  • Department of Otolaryngology, Vanderbilt University Medical Center, Nashville, TN, United States.
  • Division of Pediatric Plastic Surgery, Monroe Carell Jr. Children's Hospital, Nashville, TN, United States.

Zitieren

APA

Shirk, M. U., Dang, C., Cho, J., Chen, H., Hofstetter, L., Bijur, J., Lucas, C., James, A., Guzman, R. T., Hiller, A., Alter, N., Stone, A., Powell, M., & Pontell, M. E. (2025). Leveraging large language models for automated detection of velopharyngeal dysfunction in patients with cleft palate. Frontiers in Digital Health, 7. https://doi.org/10.3389/fdgth.2025.1552746

Vancouver

Shirk MU, Dang C, Cho J, Chen H, Hofstetter L, Bijur J, et al. Leveraging large language models for automated detection of velopharyngeal dysfunction in patients with cleft palate. Frontiers in Digital Health. 2025;7. doi:10.3389/fdgth.2025.1552746

BibTeX
@article{Shirk2025,
  author = {Shirk, Myranda Uselton and Dang, Catherine and Cho, Jaewoo and Chen, Hanlin and Hofstetter, Lily and Bijur, Jack and Lucas, Claiborne and James, Andrew and Guzman, Ricardo-Torres and Hiller, Andrea and Alter, Noah and Stone, Amy and Powell, Maria and Pontell, Matthew E},
  title = {Leveraging large language models for automated detection of velopharyngeal dysfunction in patients with cleft palate},
  journal = {Frontiers in Digital Health},
  year = {2025},
  volume = {7},
  doi = {10.3389/fdgth.2025.1552746}
}
Kostenlos starten →