Related Experiment Video
Updated: May 16, 2026
Murine Oropharyngeal Aspiration Model of Ventilator-associated and Hospital-acquired Bacterial Pneumonia
Published on: June 28, 2018
An artificial intelligence model for the diagnosis of otitis media with effusion in children
Kitirat Ungkanont1, Akadej Udomchaiporn2, Nopavit Sriphoonga2
1Department of Otorhinolaryngology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand.
Insights
An artificial intelligence (AI) model accurately diagnoses otitis media with effusion (OME) in children. This AI tool shows moderate agreement with otolaryngologists, aiding preliminary diagnosis and telemedicine.
Area of Science:
- Pediatric Otolaryngology
- Medical Artificial Intelligence
- Diagnostic Imaging Analysis
Background:
- Diagnosing otitis media with effusion (OME) in children demands specialized otoscopic examination skills.
- Current diagnostic methods rely heavily on experienced clinicians, presenting potential variability.
Purpose of the Study:
- To develop and evaluate an artificial intelligence (AI) model for predicting OME diagnosis in pediatric patients.
- To assess the AI model's diagnostic accuracy and its agreement with expert otolaryngologists.
Main Methods:
- A convolutional neural network (CNN), specifically InceptionV4, was trained on otoendoscopic images of pediatric tympanic membranes.
- Expert-labeled diagnostic features and surgical findings served as the ground truth for model training and validation.
- The model was trained using Adaptive Moment Estimation optimizer for 100 epochs, distinguishing between OME and normal tympanic membranes.
Main Results:
- The AI model achieved high accuracy (94.7%) and an F1 score of 96% in diagnosing OME.
- The area under the ROC curve was 0.98, indicating excellent discriminatory power.
- The model demonstrated moderate agreement with experienced otolaryngologists, with a kappa value of 0.627.
Conclusions:
- The developed AI model exhibits strong diagnostic performance for OME in children.
- The AI demonstrates potential as a valuable tool for preliminary OME diagnosis, supporting telemedicine and educational initiatives.
- Further integration of AI can enhance diagnostic consistency and accessibility in pediatric otology.
Background:
The diagnosis of otitis media with effusion (OME) requires substantial training and experience in otoscopic examination of children.
Objective:
This study developed an artificial intelligence (AI) model to predict OME diagnosis in children.
Methods:
The source data were images of pediatric patients' tympanic membranes obtained by otoendoscopy. A convolutional neural network was used in machine learning. The diagnostic features of the tympanic membrane, as labelled by the experts, and the surgical findings served as the ground truth. InceptionV4 built the final model. The model was trained using the Adaptive Moment Estimation optimizer with an initial learning rate of 0.0001 and a total duration of 100 epochs. The batch size was 32. The Categorical Cross-Entropy loss function was employed for the internal validation. The outcome was to distinguish between OME and normal tympanic membrane. A confusion matrix was used to assess the model's performance. The model was tested for agreement with otolaryngologists and implemented as a web application.
Results:
The initial sample size was 320 pictures. For OME, the model achieved an accuracy of 94.7% (95% CI 0.88, 1). The F1 score was 96% (95% CI 0.89, 1), and the area under the receiver operating characteristic curve was 0.98 (95% CI 0.93, 1). The kappa agreement between AI and experienced otolaryngologists was 0.627 (p < 0.001).
Conclusion:
An AI diagnostic model for otitis media with effusion had good accuracy and moderate agreement with otolaryngologists. The model should be helpful for preliminary diagnosis, telemedicine, or educational purposes.