Predicting Therapeutic Response to Hypoglossal Nerve Stimulation Using Deep Learning.

Autor: Alapati R; Department of Otolaryngology-Head and Neck Surgery, University of Kansas, Kansas City, Kansas, U.S.A., Renslo B; Department of Otolaryngology-Head and Neck Surgery, Thomas Jefferson University, Philadelphia, Pennsylvania, U.S.A., Jackson L; University of Kansas School of Medicine, Kansas City, Kansas, U.S.A., Moradi H; University of Kansas School of Medicine, Kansas City, Kansas, U.S.A., Oliver JR; Department of Otolaryngology-Head and Neck Surgery, University of Kansas, Kansas City, Kansas, U.S.A., Chowdhury M; Toronto Metropolitan University, Toronto, Ontario, Canada., Vyas T; Toronto Metropolitan University, Toronto, Ontario, Canada., Bon Nieves A; Department of Otolaryngology-Head and Neck Surgery, University of Kansas, Kansas City, Kansas, U.S.A., Lawrence A; Department of Otolaryngology-Head and Neck Surgery, University of Kansas, Kansas City, Kansas, U.S.A., Wagoner SF; Department of Otolaryngology-Head and Neck Surgery, University of Kansas, Kansas City, Kansas, U.S.A., Rouse D; Department of Otolaryngology-Head and Neck Surgery, University of Kansas, Kansas City, Kansas, U.S.A., Larsen CG; Department of Otolaryngology-Head and Neck Surgery, University of Kansas, Kansas City, Kansas, U.S.A., Wang G; Toronto Metropolitan University, Toronto, Ontario, Canada., Bur AM; Department of Otolaryngology-Head and Neck Surgery, University of Kansas, Kansas City, Kansas, U.S.A.
Jazyk: angličtina
Zdroj: The Laryngoscope [Laryngoscope] 2024 Dec; Vol. 134 (12), pp. 5210-5216. Date of Electronic Publication: 2024 Jun 27.
DOI: 10.1002/lary.31609
Abstrakt: Objectives: To develop and validate machine learning (ML) and deep learning (DL) models using drug-induced sleep endoscopy (DISE) images to predict the therapeutic efficacy of hypoglossal nerve stimulator (HGNS) implantation.
Methods: Patients who underwent DISE and subsequent HGNS implantation at a tertiary care referral center were included. Six DL models and five ML algorithms were trained on images from the base of tongue (BOT) and velopharynx (VP) from patients classified as responders or non-responders as defined by Sher's criteria (50% reduction in apnea-hypopnea index (AHI) and AHI < 15 events/h). Precision, recall, F1 score, and overall accuracy were evaluated as measures of performance.
Results: In total, 25,040 images from 127 patients were included, of which 16,515 (69.3%) were from responders and 8,262 (30.7%) from non-responders. Models trained on the VP dataset had greater overall accuracy when compared to BOT alone and combined VP and BOT image sets, suggesting that VP images contain discriminative features for identifying therapeutic efficacy. The VCG-16 DL model had the best overall performance on the VP image set with high training accuracy (0.833), F1 score (0.78), and recall (0.883). Among ML models, the logistic regression model had the greatest accuracy (0.685) and F1 score (0.813).
Conclusion: Deep neural networks have potential to predict HGNS therapeutic efficacy using images from DISE, facilitating better patient selection for implantation. Development of multi-institutional data and image sets will allow for development of generalizable predictive models.
Level of Evidence: NA Laryngoscope, 134:5210-5216, 2024.
(© 2024 The American Laryngological, Rhinological and Otological Society, Inc.)
Databáze: MEDLINE
Externí odkaz: