Ear infections are common in children yet frequently misdiagnosed, leading to delayed care or unnecessary antibiotic prescriptions. According to the National Institute on Deafness and Other Communication Disorders, at least five out of six children in the US have had at least one ear infection before age three.
When left untreated, ear infections can lead to hearing loss, developmental delays, complications like meningitis, and death in some developing nations. At the same time, overrating children when they don’t have an ear infection can lead to antibiotic resistance and render the medications ineffective against future infections. This latter problem is of significant public health importance.
According to a new study published in Otolaryngology-Head and Neck Surgery, the model called OtoDx was more than 95% accurate in diagnosing an ear infection in a set of 22 test images compared to 65% accuracy among a group of clinicians consisting of ENTs, pediatricians and primary care doctors, who reviewed same photos.
When tested in a dataset of more than 600 inner ear images, the AI model had more than 80% diagnostic accuracy. It represented a significant leap over the average accuracy of clinicians reported in the medical literature.
The model utilizes a type of AI called deep learning and was built from hundreds of photographs collected from children before surgery at Mass Eye and Ear for recurrent ear infections or fluid in the ears. According to the authors, the results signify an important step towards developing a diagnostic tool that can one day be deployed to clinics to assist doctors during patient evaluations.
Difficulty in diagnosis
To ensure the best outcome for children, ear infections must be detected accurately and early as possible. However, previous studies suggest that the conventional diagnostic accuracy of ear infections in children from a physical exam is below 70%, even with technological innovations and clinical practice guidelines. In addition, the difficulty of evaluating a child who is struggling or crying during an exam and the general inexperience of doctors can affect the diagnostic rate.
In 2021, Dr. Crowson collaborated with Mass Eye and Ear colleagues to develop a more accurate method of diagnosing ear infections using a machine learning algorithm. An artificial neural network was trained with high-resolution photographs of tympanic membranes collected directly from patients during ear procedures where infections can be seen.
These photos represent a gold standard, “ground truth” set of data compared to AI-based tools that rely on images collected from search engines. In a proof-of-concept study published last year, the model was 84% accurate in detecting “normal” versus “abnormal” middle ears.
Human versus machine
In the new study, the researcher compared the accuracy of a refined med model against clinicians. More than 639 images of tympanic membranes from children aged 18 years or younger undergoing surgery for time placement or draining fluid from the ears were used to train the model. The images were tagged as either “normal”, “infected”, or having “liquid behind the eardrum”, as opposed to the “normal” or “abnormal” classification from the team’s earlier model. With the added segment, the model achieved a mean diagnostic accuracy of 80.8 per cent.
Bringing AI to the clinic
Ongoing studies are underway to validate and refine the AI model. More than 1000 intraoperative images of tympanic membranes have been amassed at Mass Eye and Ear. OtoDx is currently employed in a prototype device paired with a smartphone app. The device acts as a “mini otoscope” that would fit over the phone’s camera and allow clinicians to take photos of the inside of a child’s ear, upload them directly to the app and receive a diagnostic reading in seconds.
Source: indiaai.gov.in
