EUVIMEDEUVIMED entdecken
Crossref

Machine Learning of Acoustic Voice Outcomes in Idiopathic Subglottic Stenosis

Ioan A Lina, Raymond J So iD, Kevin M Motz iD, Samuel Collins, Anthony Law, Alexander T Hillel iD

The Laryngoscope · 2026-07 · 136 (7) · 2931-2937

DOI: 10.1002/lary.70459 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Laryngoscope, online erschienen am 05.03.2026. Verfasst von Ioan A Lina und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology-Head and Neck Surgery, University of Colorado, Denver, Colorado, USA. Hauptthemen laut MEDLINE: Laryngostenosis, Machine Learning, Voice Quality. Die Arbeit nennt 33 Literaturangaben. Gefördert von: NIDCD NIH HHS, National Institute on Deafness and Other Communication Disorders, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

There are no objective reliable non‐invasive screening tools to identify disease severity in patients with idiopathic subglottic stenosis (iSGS), a debilitating and life‐threatening disease where scar tissue narrows the airway. This study aims to identify objective voice measures that characterize iSGS disease severity.

Methods

Voice recordings of the Rainbow Passage (RP) were obtained in patients with severe iSGS ( n = 10) immediately prior to endoscopic balloon dilation (ED), 2 weeks post‐treatment ( n = 6), and in healthy age‐matched volunteers ( n = 10). CT neck was obtained before and after ED, and the luminal area was measured relative to cricoid as a percent stenosis. Quantitative voice analysis was performed using VoiceLab, an automated voice analysis program. Unsupervised machine learning was performed using principal component analysis (PCA), and a simple linear regression compared composite voice outcome to luminal airway stenosis.

Results

Patients with severe iSGS had increased RP duration ( p = 0.013) and decreased speech rate ( p = 0.012), articulation rate ( p = 0.017), and average syllable duration ( p = 0.0096) compared to healthy controls. Isolated recorded breathing samples during RP in severe iSGS patients showed increased cepstral peak prominence ( p < 0.0001), mean breath count ( p = 0.0039), mean breath duration ( p < 0.0001), and time spent breathing ( p = 0.0002) compared to controls. PCA analysis showed complete separation between normal and severe iSGS, with post‐ED iSGS intervening the two groups. Linear regression of the composite principal component 1 strongly correlated with luminal airway caliber.

Conclusions

Objective voice analysis using machine learning provides a novel, non‐invasive biomarker which can be used to quantify iSGS disease severity in advance of surgical intervention. Level of Evidence 4.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LaryngostenosisMachine LearningVoice QualityHumansFemaleMaleMiddle AgedSeverity of Illness IndexAdultAgedCase-Control Studies

Stichwörter der Autor:innen

acoustic analysisiSGSidiopathic subglottic stenosislaryngotracheal stenosismachine learningsubglottic stenosisvoice outcomes

Autor:innen und Institutionen

  • Department of Otolaryngology-Head and Neck Surgery, University of Colorado, Denver, Colorado, USA.
  • Department of Otolaryngology-Head and Neck Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
  • Department of Otolaryngology-Head and Neck Surgery, Emory University School of Medicine, Atlanta, Georgia, USA.

ORCID-Profile: Raymond J So, Kevin M Motz, Alexander T Hillel

Förderung

  • NIDCD NIH HHS
  • National Institute on Deafness and Other Communication Disorders
  • National Institutes of Health

Zitieren

APA

Lina, I. A., So, R. J., Motz, K. M., Collins, S., Law, A., & Hillel, A. T. (2026). Machine Learning of Acoustic Voice Outcomes in Idiopathic Subglottic Stenosis. The Laryngoscope, 136(7), 2931-2937. https://doi.org/10.1002/lary.70459

Vancouver

Lina IA, So RJ, Motz KM, Collins S, Law A, Hillel AT. Machine Learning of Acoustic Voice Outcomes in Idiopathic Subglottic Stenosis. The Laryngoscope. 2026;136(7):2931-2937. doi:10.1002/lary.70459

BibTeX
@article{Lina2026,
  author = {Lina, Ioan A and So, Raymond J and Motz, Kevin M and Collins, Samuel and Law, Anthony and Hillel, Alexander T},
  title = {Machine Learning of Acoustic Voice Outcomes in Idiopathic Subglottic Stenosis},
  journal = {The Laryngoscope},
  year = {2026},
  volume = {136},
  number = {7},
  pages = {2931--2937},
  doi = {10.1002/lary.70459}
}
Kostenlos starten →