Using a smartphone and a paper funnel, researchers from the University of Washington have created a system that can detect fluid in the middle ear, which causes ear infections. According to a new study published by the Science Translational Medicine journal, the smartphone-based machine learning algorithm app can be used to identify pediatric patients with the condition.
Authors of the study said this this system could be a new tool for rural communities and lead to reduced costs.
“Given the ubiquity of smartphones, the system we describe may have clinically relevant applications in developing countries and rural communities where smartphone availability is rapidly growing, in primary care settings as an adjunct to visual otoscopy, or for home screening by parents as a platform to reduce health care cost,” the authors of the study wrote.
Through the smartphone’s speakers, the app sends a “soft acoustic chirp in to the ear canal.” The system then employs a machine learning model that is able to “classify these reflections and predict middle ear fluid status.”
“It’s like tapping a wine glass,” Justin Chan, a doctoral student in the Allen School and first author of the paper, told the University of Washington’s in-house news publication. “Depending on how much liquid is in it, you get different sounds. Using machine learning on these sounds, we can detect the presence of liquid.”
Researchers found that the system was able to detect middle ear fluid with 85% sensitivity and 82% specificity.
The study also found that parents were able to use the system with the same level of accuracy as providers.
HOW IT WAS DONE
Researchers examined the tool among two different cohorts of patients. The first was comprised pediatric patients aged 18 months to 17 years. The second cohort used children under the age of 18 months.
In the first cohort, researchers looked at the ears of 53 patients. Approximately half of the patients were having ear tube surgery, associated with inner ear fluid. The other half were at the hospital for a different non-ear related surgery. A clinician tested patients using both the new system and the commercial acoustics reflectometry hardware. In the second cohort researchers looked at 15 ears of younger children.
In addition to clinicians testing children, 25 non-clinical caregivers and parents used the technology.
WHAT'S THE BACKGROUND
Smartphones paired with an artificial intelligence or machine learning algorithm are becoming a popular way to detect certain conditions. The technology isn’t just used for ears but has also been used in detecting dermatological and ophthalmological conditions as well as other health-related issues.
For example, researchers at the Medras Diabetes Research Foundation determined that a smartphone-based device called Remido ‘Fundus on phone’, along with AI software, had a high sensitivity for detecting diabetic retinopathy and sight-threatening diabetic retinopathy.
Industry players have predicted that AI combined with smartphone technology could be key in helping to detect common conditions.
“We are not going to get to the point where all medical diagnoses are not requiring backup,” Dr. Eric Topol, founder and director of Scripps Research Translational Institute and professor at Scripps Research, said at the GPU Technology Conference in March. “But we may get to a point with certain things like a sore throat or ear infections or a skin rash can be done completely algorithmically — both the diagnosis and the recommendations for treatment.”
ON THE RECORD
“Fluid behind the eardrum is so common in children that there’s a direct need for an accessible and accurate screening tool that can be used at home or in clinical settings,” Dr. Sharat Raju, a surgical resident at UW School of Medicineand coauthor of the study, told the university’s in-house communications team. “If parents could use a piece of hardware they already have to do a quick physical exam that can say ‘Your child most likely doesn’t have ear fluid’ or ‘Your child likely has ear fluid, you should make an appointment with your pediatrician,’ that would be huge.”