Related Experiment Video
Updated: Jun 26, 2025
Robot-Assisted Transcanal Endoscopic Ear Surgery for Congenital Cholesteatoma
Published on: December 15, 2023
Pediatric tympanostomy tube assessment via deep learning
K M Chang1, S S Surapaneni2, N Shaikh3
1Tufts University School of Medicine, Boston, MA, United States of America.
Insights
An artificial intelligence algorithm accurately detects tympanostomy tubes (TTs) in children
Area of Science:
- Otolaryngology
- Medical Artificial Intelligence
- Pediatric Surgery
Background:
- Tympanostomy tube (TT) placement is a common pediatric surgery.
- Post-operative follow-up for TT checks incurs significant family costs.
- Current follow-up methods require in-person clinical visits.
Purpose of the Study:
- To evaluate an AI algorithm's efficacy in determining tympanostomy tube presence.
- To compare AI-based TM evaluation with clinical staff assessment.
- To explore AI's potential in reducing follow-up visit burdens.
Main Methods:
- Prospective study of children (10 months-10 years) with a history of TTs.
- Smartphone otoscope used to capture tympanic membrane (TM) images.
- Deep learning algorithm trained and tested on TM images, compared to clinician assessment.
Main Results:
- The AI algorithm achieved 97.7% overall classification accuracy.
- High precision and recall rates for detecting TM with or without tubes.
- AI demonstrated strong performance in identifying tympanostomy tube presence.
Conclusions:
- A deep learning algorithm shows promise for classifying ear tube presence using otoscope images.
- AI can potentially be used by laypersons with accessible otoscopes.
- Future research aims to develop AI for assessing tube patency and extrusion.
Purpose:
Tympanostomy tube (TT) placement is the most frequently performed ambulatory surgery in children under 15. After the procedure it is recommended that patients follow up regularly for "tube checks" until TT extrusion. Such visits incur direct and indirect costs to families in the form of days off from work, copays, and travel expenses. This pilot study aims to compare the efficacy of tympanic membrane (TM) evaluation by an artificial intelligence algorithm with that of clinical staff for determining presence or absence of a tympanostomy tube within the TM.
Methods:
Using a digital otoscope, we performed a prospective study in children (ages 10 months-10 years) with a history of TTs who were being seen for follow up in a pediatric otolaryngology clinic. A smartphone otoscope was used by study personnel who were not physicians to take ear exam images, then through conventional otoscopic exam, ears were assessed by a clinician for tubes being in place or tubes having extruded from the TM. We trained and tested a deep learning (artificial intelligence) algorithm to assess the images and compared that with the clinician's assessment.
Results:
A total of 123 images were obtained from 28 subjects. The algorithm classified images as TM with or without tube in place. Overall classification accuracy was 97.7 %. Recall and precision were 100 % and 96 %, respectively, for TM without a tube present, and 95 % and 100 %, respectively, for TM with a tube in place.
Discussion:
This is a promising deep learning algorithm for classifying ear tube presence in the TM utilizing images obtained in awake children using an over-the-counter otoscope available to the lay population. We are continuing enrollment, with the goal of building an algorithm to assess tube patency and extrusion.
