Predicting Therapeutic Response to Hypoglossal Nerve Stimulation Using Deep Learning.
deep learning
obstructive sleep apnea
upper airway stimulation
Journal
The Laryngoscope
ISSN: 1531-4995
Titre abrégé: Laryngoscope
Pays: United States
ID NLM: 8607378
Informations de publication
Date de publication:
27 Jun 2024
27 Jun 2024
Historique:
revised:
24
05
2024
received:
11
03
2024
accepted:
17
06
2024
medline:
27
6
2024
pubmed:
27
6
2024
entrez:
27
6
2024
Statut:
aheadofprint
Résumé
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. 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. 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). 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. N/A Laryngoscope, 2024.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : NIGMS NIH HHS
ID : P20GM130423
Pays : United States
Informations de copyright
© 2024 The American Laryngological, Rhinological and Otological Society, Inc.
Références
Arzt M, Young T, Finn L, Skatrud JB, Bradley TD. Association of sleep‐disordered breathing and the occurrence of stroke. Am J Respir Crit Care Med. 2005;172(11):1447‐1451. https://doi.org/10.1164/rccm.200505-702OC
Gottlieb DJ, Punjabi NM. Diagnosis and Management of Obstructive Sleep Apnea: a review. Jama. 2020;323(14):1389‐1400. https://doi.org/10.1001/jama.2020.3514
Senaratna CV, Perret JL, Lodge CJ, et al. Prevalence of obstructive sleep apnea in the general population: a systematic review. Sleep Med Rev. 2017;34:70‐81. https://doi.org/10.1016/j.smrv.2016.07.002
Sawyer AM, Gooneratne NS, Marcus CL, Ofer D, Richards KC, Weaver TE. A systematic review of CPAP adherence across age groups: clinical and empiric insights for developing CPAP adherence interventions. Sleep Med Rev. 2011;15(6):343‐356. https://doi.org/10.1016/j.smrv.2011.01.003
Vanderveken OM. Drug‐induced sleep endoscopy (DISE) for non‐CPAP treatment selection in patients with sleep‐disordered breathing. Sleep Breath. 2013;17(1):13‐14. https://doi.org/10.1007/s11325-012-0671-9
Inspire System Implant Manual. Accessed 23 June 2023, www.accessdata.fda.gov/cdrh_docs/pdf13/P130008d.pdf
Kezirian EJ, Hohenhorst W, de Vries N. Drug‐induced sleep endoscopy: the VOTE classification. Eur Arch Otorhinolaryngol. 2011;268(8):1233‐1236. https://doi.org/10.1007/s00405-011-1633-8
Ong AA, Ayers CM, Kezirian EJ, et al. Application of drug‐induced sleep endoscopy in patients treated with upper airway stimulation therapy. World J Otorhinolaryngol Head Neck Surg. 2017;3(2):92‐96. https://doi.org/10.1016/j.wjorl.2017.05.014
Altintaş A, Yegin Y, Çelik M, Kaya KH, Koç AK, Kayhan FT. Interobserver consistency of drug‐induced sleep endoscopy in diagnosing obstructive sleep apnea using a VOTE classification system. J Craniofac Surg. 2018;29(2):e140‐e143. https://doi.org/10.1097/scs.0000000000003876
Kezirian EJ, White DP, Malhotra A, Ma W, McCulloch CE, Goldberg AN. Interrater reliability of drug‐induced sleep endoscopy. Arch Otolaryngol–Head Neck Surg. 2010;136(4):393‐397. https://doi.org/10.1001/archoto.2010.26
Fernandes AFA, Dórea JRR, Rosa GJM. Image analysis and computer vision applications in animal sciences: an overview. Front Vet Sci. 2020;7:551269. https://doi.org/10.3389/fvets.2020.551269
Zhang T, Bur AM, Kraft S, et al. Gender, smoking history, and age prediction from laryngeal images. J Imaging. 2023;9(6):109. https://doi.org/10.3390/jimaging9060109
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognitio (pp. 770–778). 2016.
Tan M, Le Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. presented at: Proceedings of the 36th International Conference on Machine Learning; 2019; Proceedings of Machine Learning Research. https://proceedings.mlr.press/v97/tan19a.html
Huang G, Liu Z, Maaten LVD, Weinberger KQ. Densely connected convolutional. Networks. 2017;2261‐2269. https://doi.org/10.1109/CVPR.2017.243
Simonyan K, Zisserman A. Very deep convolutional networks for large‐scale image recognition. arXiv preprint arXiv:14091556. 2014.
Russakovsky O, Deng J, Su H, et al. Imagenet large scale visual recognition challenge. Int J Comput Vis. 2015;115:211‐252.
Thaler E, Schwab R, Maurer J, et al. Results of the ADHERE upper airway stimulation registry and predictors of therapy efficacy. Laryngoscope. 2020;130(5):1333‐1338. https://doi.org/10.1002/lary.28286
Strollo PJ Jr, Soose RJ, Maurer JT, et al. Upper‐airway stimulation for obstructive sleep apnea. N Engl J Med. 2014;370(2):139‐149. https://doi.org/10.1056/NEJMoa1308659
Alapati R, Wagoner SF, Nieves AB, Lawrence A, Rouse D, Larsen C. Upper airway stimulation device failure: a 7‐year single center experience. Am J Otolaryngol. 2023;45(2):104153. https://doi.org/10.1016/j.amjoto.2023.104153
Bellamkonda N, Shiba T, Mendelsohn AH. Adverse events in hypoglossal nerve stimulator implantation: 5‐year analysis of the FDA MAUDE database. Otolaryngol Head Neck Surg. 2021;164(2):443‐447. https://doi.org/10.1177/0194599820960069
Safari S, Baratloo A, Elfil M, Negida A. Evidence based emergency medicine part 2: positive and negative predictive values of diagnostic tests. Emerg (Tehran). 2015;3(3):87‐88.
Coman AC, Borzan C, Vesa CS, Todea DA. Obstructive sleep apnea syndrome and the quality of life. Clujul Med. 2016;89(3):390‐395. https://doi.org/10.15386/cjmed-593
Knauert M, Naik S, Gillespie MB, Kryger M. Clinical consequences and economic costs of untreated obstructive sleep apnea syndrome. World J Otorhinolaryngol Head Neck Surg. 2015;1(1):17‐27. https://doi.org/10.1016/j.wjorl.2015.08.001
Yook S, Kim D, Gupte C, Joo EY, Kim H. Deep learning of sleep apnea‐hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity. Sleep Med. 2024;114:211‐219. https://doi.org/10.1016/j.sleep.2024.01.015
Li Z, Jia Y, Li Y, Han D. Automatic prediction of obstructive sleep apnea event using deep learning algorithm based on ECG and thoracic movement signals. Acta Otolaryngol. 2024;144(1):52‐57. https://doi.org/10.1080/00016489.2024.2301732
Hanif U, Kiaer EK, Capasso R, et al. Automatic scoring of drug‐induced sleep endoscopy for obstructive sleep apnea using deep learning. Sleep Med. 2023;102:19‐29. https://doi.org/10.1016/j.sleep.2022.12.015