AI smartphone app can detect ear infections


Artificial Intelligence (AI) could soon be used to diagnose ear infections in children, commonly susceptible to such illnesses, thanks to a new app aimed at helping to reduce antibiotic use in minors and improve diagnostic accuracy.

Acute otitis media (AOM) is one of the most common childhood infections but can normally only be detected by a skilled healthcare worker such as a doctor, as it is hard to distinguish from other similar conditions.

The AI tool, developed by US healthcare company UPMC and the University of Pittsburgh, makes a short video of the eardrum using an otoscope connected to a smartphone camera, and then uses this to make a diagnosis.

“Acute otitis media is often incorrectly diagnosed,” said app developer Alejandro Hoberman, professor of pediatrics and president of UPMC children’s community pediatrics.

He added: “Underdiagnosis results in inadequate care and overdiagnosis results in unnecessary antibiotic treatment, which can compromise the effectiveness of currently available antibiotics. Our tool helps get the correct diagnosis and guide the right treatment.”

UPMC says that AOM is often confused with other conditions, such as fluid behind the ear, a condition that generally does not involve bacteria and, therefore, does not benefit from antimicrobial treatment.

Hoberman and other app developers used 921 videos from a training library to teach two AI models to detect AOM by looking at features of the eardrum, including shape, position, color, and translucency. Then, they used another 230 to test how the models performed.

UPMC says both models were highly accurate to a rate of more than 93%, meaning that they had low occurrences of false negatives and positives.

Hoberman cited previous clinical studies that found diagnostic accuracy of AOM ranging between 30% and 84%, depending on the type of healthcare provider, level of training, and the age of the child being examined.

“These findings suggest that our tool is more accurate than many clinicians,” said Hoberman. “It could be a gamechanger in primary health care settings to support clinicians in stringently diagnosing AOM and guiding treatment decisions.”

He also believes the app can help train medical students and improve communication between doctors and parents of children being treated.

“Another benefit of our tool is that the videos we capture can be stored in a patient’s medical record and shared with other providers,” said Hoberman. “We can also show parents and trainees – medical students and residents – what we see and explain why we are or are not making a diagnosis of ear infection. It is important as a teaching tool and for reassuring parents that their child is receiving appropriate treatment.”

Hoberman says he expects the app – which Cybernews understands has yet to be officially named – to be rolled out to healthcare providers soon.


More from Cybernews:

Carmakers must bring back physical controls to get a 5-star safety rating in Europe

Anthropic: new Claude 3 AI outperforms rivals GPT-4, Gemini 1.0

SpaceX launches Google-backed satellite to fight climate change

American Express says customer data exposed in third-party breach

Publishers seeking to paralyze pirate library LibGen

Subscribe to our newsletter



Leave a Reply

Your email address will not be published. Required fields are markedmarked