Deep Learning–Assisted Diagnosis of Middle Ear Diseases in Otoendoscopy Across Clinician Experience Levels: Retrospective Reader Study
JMIR Medical Informatics · 2026-10-30 · 14 · e96134-e96134
DOI: 10.2196/96134 ↗At a glance
Journal article in JMIR Medical Informatics, published online on 2026-10-30. Written by Se Eun Yi and 5 co-authors. Institution: Department of Otorhinolaryngology-Head and Neck Surgery, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-g…. Major MEDLINE topics: Deep Learning, Ear Diseases, Endoscopy, Ear, Middle. 22 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Accurate diagnosis of middle ear diseases remains challenging due to the specialized nature of otoscopic interpretation and the global shortage of otolaryngologists.
Objective
We aimed to evaluate the impact of a deep learning–based AI support system on the diagnostic performance of clinicians with varying levels of expertise, specifically focusing on its ability to bridge the gap between trainees and experts.
Methods
In this retrospective reader study, a deep learning model (EfficientNet-B4) was developed using a large-scale dataset of 7335 endoscopic images. The model was designed for multi-class classification, simultaneously identifying primary categories (chronic otitis media, otitis media with effusion, or none [indicating the absence of the first two]) and secondary features (attic retraction, myringitis, otomycosis, and ventilation tube). To assess clinical impact, diagnostic performance was compared among 3 otology professors, 5 senior residents, and 5 junior residents using an independent clinical assessment set of 100 images. Participants performed diagnoses both with and without AI-generated predictions, with a time constraint of 1 minute per image to simulate real-world clinical pressure.
Results
In 5-fold cross-validation, the deep learning model achieved 94.8% accuracy for the primary classification. The stand-alone AI achieved diagnostic accuracies ranging from 94.0% to 99.0% in the clinical assessment set. AI support significantly enhanced diagnostic accuracy across all groups for primary classification, with improvements of 11.0% for otology professors, 28.8% for senior residents, and 32.2% for junior residents ( P
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Otorhinolaryngology-Head and Neck Surgery, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, Republic of Korea, 82 2-3010-3717, 82 2-489-2773.
- Department of Medical Science, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
- Department of Biomedical Engineering, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
Cite
APA
Yi, S. E., Chae, J., Park, K., Choi, Y. J., Kweon, J., & Ahn, J. H. (2026). Deep Learning–Assisted Diagnosis of Middle Ear Diseases in Otoendoscopy Across Clinician Experience Levels: Retrospective Reader Study. JMIR Medical Informatics, 14, e96134-e96134. https://doi.org/10.2196/96134
Vancouver
Yi SE, Chae J, Park K, Choi YJ, Kweon J, Ahn JH. Deep Learning–Assisted Diagnosis of Middle Ear Diseases in Otoendoscopy Across Clinician Experience Levels: Retrospective Reader Study. JMIR Medical Informatics. 2026;14:e96134-e96134. doi:10.2196/96134
BibTeX
@article{Yi2026,
author = {Yi, Se Eun and Chae, Jihye and Park, Keunwoo and Choi, Yeon Joo and Kweon, Jihoon and Ahn, Joong Ho},
title = {Deep Learning–Assisted Diagnosis of Middle Ear Diseases in Otoendoscopy Across Clinician Experience Levels: Retrospective Reader Study},
journal = {JMIR Medical Informatics},
year = {2026},
volume = {14},
pages = {e96134--e96134},
doi = {10.2196/96134}
}
EUVIMED