Image of an eardrum with acute otitis media (right) captured by the new smartphone app. Credit: Alejandro Hoberman
Key points:
- A new cellphone app uses artificial intelligence (AI) to accurately diagnose ear infections, or acute otitis media (AOM).
- Researchers used videos to teach two different AI models to detect AOM by examining tympanic membrane features such as shape, position, color, and translucency.
- Both models were accurate and achieved sensitivity and specificity values of greater than 93%, meaning that they were more accurate than many clinicians.
A new cellphone app uses artificial intelligence (AI) to accurately diagnose ear infections, or acute otitis media (AOM). This method, outlined in JAMA Pediatrics, could help decrease unnecessary antibiotic use in young children.
The new AI tool makes an AOM diagnosis by assessing a short video of the ear drum captured by an otoscope connected to a cellphone camera. The team developed their tool by first building and annotating a training library of 1,151 videos of the tympanic membrane from 635 children. Two experts in AOM research reviewed the videos and made a diagnosis of AOM or not AOM.
Researchers used 921 videos to teach two different AI models to detect AOM by examining tympanic membrane features such as shape, position, color, and translucency. They used the remaining videos to test the models’ performance.
Both models were accurate and achieved sensitivity and specificity values of greater than 93%—indicating that they had low rates of false negatives and false positives. This diagnostic accuracy of AOM was greater than many clinicians, which typically have an accuracy ranging from 30% to 84% depending on type of healthcare provider, training level, and age of children being examined.
“The findings suggest that our tool is more accurate than many clinicians,” explained study author Alejandro Hoberman, professor at the University of Pittsburgh. “It could be a gamechanger in primary health care settings to support clinicians in stringently diagnosing AOM and guiding treatment decisions.”
The researchers hope their simple and effective technology could be implemented across health care provider offices. This widespread use would enhance accurate diagnosis and support appropriate treatment decisions.
“We can show parents and trainees what we see and explain why we are or are not making a diagnosis of ear infection,” said Hoberman. “It is important as a teaching tool and for reassuring parents that their child is receiving appropriate treatment.”
