A machine learning approach for diagnosing otitis media with effusion in pediatric patients
By
Kitirat Ungkanont
Akadej Udomchaiporn
Nopavit Sriphoonga
Thanakrit Wannarong
Thaweewat Rugsujrit
Tachasit Chueprasert
Archwin Tanphaichitr
Vannipa Vathanophas
May 8, 2026
Objective: To develop an AI model for predicting the diagnosis of otitis media with effusion (OME) in children.
Key Findings: AI model developed using CNN achieved high accuracy in diagnosing OME. Characteristic features of the TM, such as color and transparency, were critical for diagnosis. Expert otolaryngologists had varying accuracy in diagnosing OME, which improved with training. Interpretation: The AI model serves as a preliminary diagnostic tool, potentially aiding less experienced clinicians in diagnosing OME in pediatric patients.
Limitations: The study was conducted at a single tertiary care center, which may limit generalizability. The model's performance needs validation in diverse clinical settings. Conclusion: The developed AI model shows promise in improving the diagnosis of OME in children, addressing challenges faced by clinicians.
