Algorithm-Driven Tele-otoscope for Remote Care for Patients With Otitis Media.

Area of Science:

• Medical Technology
• Artificial Intelligence
• Otolaryngology

Background:

• The COVID-19 pandemic increased demand for telemedicine.
• Telemedicine, AI, and image processing can support remote otitis media (OM) care.
• Wireless transmission is key for remote diagnostic tools.

Purpose of the Study:

• To develop and validate an AI-driven tele-otoscope system for diagnosing OM.
• To integrate Wi-Fi transmission and a cloud-based diagnostic algorithm.
• To assess the system's accuracy in differentiating OM from normal cases.

Main Methods:

• A prospective, cross-sectional diagnostic study was conducted at a tertiary academic medical center.
• A tele-otoscope (Otiscan) with digital imaging, Wi-Fi, and an AI algorithm was designed.
• Two convolutional neural network models analyzed 1137 otoscopic images for OM classification.

Main Results:

• The tele-otoscope produced images with 1280 × 720 resolution.
• The system achieved 94% classification accuracy in differentiating OM.
• Specific diagnostic performance included 80% sensitivity and 96% specificity.

Conclusions:

• The developed tele-otoscope demonstrates acceptable accuracy for OM diagnosis.
• This system can aid healthcare professionals in early OM detection.
• The tele-otoscope facilitates continuous remote monitoring to mitigate OM consequences.