Connect with us


AI model outperforms clinicians in diagnosing child ear infections



An AI model built by researchers in the US was significantly more accurate than doctors at diagnosing paediatric ear infections in a first-of-its kind head-to-head evaluation.

According to the study, the model, called OtoDX, was more than 95 percent accurate in diagnosing an ear infection compared to 65 percent accuracy among a group of ENTs, paediatricians and primary care doctors who reviewed the same 22 images.

When tested in a dataset of more than 600 inner ear images, the AI model was shown to be more than 80 percent accurate, representing a significant improvement over the average accuracy of clinicians reported in medical literature.

The model was built from hundreds of photographs collected from children prior to undergoing surgery at Massachusetts Eye and Ear for recurrent ear infections or fluid in the ears.

The findings could lead to the development of a diagnostic tool that could be deployed to clinicians to assist doctors during patient evaluations, the authors said.

Such a tool could give paediatricians and urgent care clinics an additional test to better inform their clinical decision-making.

Lead study author Matthew Crowson, MD, an otolaryngologist and artificial intelligence researcher at Mass Eye and Ear, and assistant professor of Otolaryngology–Head and Neck Surgery at Harvard Medical School, said:

“Ear infections are incredibly common in children yet frequently misdiagnosed, leading to delays in care or unnecessary antibiotic prescriptions.

“This model won’t replace the judgment of clinicians but can serve to supplement their expertise and help them be more confident in their treatment decisions.”

Ongoing studies are seeking to validate and refine the OtoDx AI model.

OtoDx is being employed in a prototype device which is paired with a smartphone app.

The device acts as a “mini otoscope” that would fit over the phone’s camera to enable clinicians to take photos of the child’s inner-ear, upload them directly to the app and receive a diagnostic reading in seconds.

Image: Mass Eye and Ear

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Trending stories