Diagnostic Accuracy of a Deep Learning–Assisted System for Middle Ear Diseases Compared with Otolaryngologists: Prospective Observational Study (Preprint)
Authors:
- Se Eun YiSYSe Eun Yi
- Jihye ChaeJCJihye Chae
- Keunwoo ParkKPKeunwoo Park
- Yeon Joo ChoiYCYeon Joo Choi
- Jihoon KweonJKJihoon Kweon
- Joong Ho AhnJAJoong Ho Ahn
Preprint
- 25 March 2026
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
Abstract
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 artificial intelligence (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 A deep learning model (EfficientNet-B4) was developed using a large-scale dataset of 7,335 endoscopic images. The model was designed for multi-class classification, simultaneously identifying primary categories (Chronic Otitis Media, Otitis Media with Effusion, or Normal) and secondary features (attic retraction, myringitis, otomycosis, and ventilation tube). To assess clinical impact, diagnostic performance was compared among three otology professors (OP), five senior residents (SR), and five junior residents (JR) using a clinical assessment set of 100 images. Participants performed diagnoses both with and without AI-generated predictions, with a time constraint of one minute per image to simulate real-world clinical pressure. RESULTS AI support significantly enhanced diagnostic accuracy across all groups for primary classification, with improvements of 11.0% for OP, 28.8% for SR, and 32.2% for JR (p < 0.001). Notably, the accuracy gap between the most experienced (OP) and least experienced (JR) groups was reduced from 24.3% to 3.1%. For secondary categories, significant improvements were observed in diagnosing attic retraction and myringitis among residents, with some performances even surpassing the standalone AI accuracy. CONCLUSIONS Our findings demonstrate that deep learning-based AI support substantially improves the diagnostic accuracy of middle ear diseases, particularly for less experienced clinicians. By narrowing the performance gap between trainees and experts, this system shows high potential as a valuable adjunct for clinical decision-making and medical education in otology. CLINICALTRIAL This study complies with the Declaration of Helsinki and received research approval from the Institutional Review Board of the Asan Medical Center with a waiver of research consent (IRB no. 2021–0837).Keywords
This publication has 11 references indexed in Scilit:
- Deep learning-aided decision support for diagnosis of skin disease across skin tonesNature Medicine, 2024
- Automated multi-class classification for prediction of tympanic membrane changes with deep learning modelsPLOS ONE, 2022
- Differential Biases and Variabilities of Deep Learning–Based Artificial Intelligence and Human Experts in Clinical Diagnosis: Retrospective Cohort and Survey StudyJMIR Medical Informatics, 2021
- Machine Learning for Accurate Intraoperative Pediatric Middle Ear Effusion DiagnosisPediatrics, 2021
- Automatic detection of tympanic membrane and middle ear infection from oto-endoscopic images via convolutional neural networksNeural Networks, 2020
- Presenting the Board of RespirationRespiration, 2020
- Otitis Media Diagnosis for Developing Countries Using Tympanic Membrane Image-AnalysisEBioMedicine, 2016
- Otoscopy simulation training in a classroom setting: A novel approach to teaching otoscopy to medical studentsThe Laryngoscope, 2014
- Survey of ENT services in Africa: need for a comprehensive interventionGlobal Health Action, 2009
- Diagnosis, Natural History, and Late Effects of Otitis Media With Effusion: Volume 1. Evidence Report and Evidence Tables: Evidence Report/Technology Assessment, Number 552003