SWITZERLAND- An artificial intelligence model has shown to be much more accurate than clinicians in diagnosing pediatric ear infections in the first head-to-head comparison of its kind.
The model was created by Mass Eye and Ear, an international center for treatment and research, and a teaching hospital of Harvard Medical School.
The latest study, which was written up in the journal Otolaryngology-Head and Neck Surgery, demonstrated that the model was 95% accurate when used to identify an ear infection using 22 test photos.
Only 65% of the cases were accurately diagnosed by a group of specialists, including ENTs, pediatricians, and primary care physicians, who looked at the same photos.
The tool, OtoDx, showed a diagnostic accuracy of 80% when it was tested further on a set of more than 600 photographs of the inner ear.
This is significantly higher than the rates of diagnoses made by clinicians as documented in the medical literature.
“Ear infections are incredibly common in children yet frequently misdiagnosed, leading to delays in care or unnecessary antibiotic prescriptions,” said Matthew Crowson, MD, lead author of the study and an otolaryngologist and artificial intelligence researcher at Mass Eye and Ear.
He added that the 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.
OtoDx is now being used by Mass General Brigham Innovation in a prototype device that is coupled with a smartphone app as the researchers work to develop a workable tool that can be widely used as a diagnostic tool at clinics to help clinicians with patient evaluation.
According to the National Institute on Deafness and Other Communication Disorders, five out of every six children will have experienced an ear infection by the time they are three years old.
A plethora of negative effects, such as hearing loss, developmental delays, and complications such as bacterial meningitis, can result from untreated inner ear infections.
Doctors with young children frequently prescribe antibiotics if an infection is suspected since ear infections are so common and have the potential to cause serious health problems if left untreated, even though clinical diagnosis accuracy is typically around 70%.
OtoDx is now being used by Mass General Brigham Innovation in a prototype device that is coupled with a smartphone app as the researchers work to develop a workable tool that can be widely used as a diagnostic tool at clinics to help clinicians with patient evaluation.
In this arrangement, the tool makes use of the smartphone’s camera to enable clinicians to snap pictures of children’s inner ears, which are then uploaded for OtoDx’s analysis to provide a reading in a matter of seconds.
The goal is for Mass General Brigham Innovation to assist in the commercialization of OtoDx when the tool is further improved after this pilot project.
Liked this article? Sign up to receive our regular email newsletters, focused on Africa and World’s healthcare industry, directly into your inbox. SUBSCRIBE HERE