Artificial Intelligence Diagnostic Decision Support to Reduce Antimicrobial Prescriptions in Young Children With Colds
Trial statusRecruiting
Trial phaseNot applicable
Trial typeInterventional
Biological sexAll
Age6-24
SponsorTimothy Shope
About this trial
Ear infections are common in young children with cold symptoms, but they can be difficult to diagnose due to small ear canals, child movement, and limited viewing time. In this study, investigators will take photos of the eardrums of children 6-24 months of age with upper respiratory symptoms. The photos will be reviewed by imaging software enhanced with artificial intelligence (AI app) to determine whether the AI app changes how ear infections are diagnosed and treated. The AI app has undergone rigorous study and was found to be highly accurate; but how using this technology affects the diagnosis and treatment by clinicians has not been studied. This research may help improve diagnostic accuracy for ear infections and ensure antibiotics are prescribed only for those children who have definite ear infections.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Age 6-24 months
Presence of upper respiratory infection
Disqualifiers
No upper respiratory infection
Otorrhea
Tympanostomy tubes
Currently taking antimicrobials
Trial design
Design model
Single group
Treatments tested in this trial
Standard Clinical Ear Exam
Diagnostic testThe clinician will examine the child's ear with a standard otoscope and give a clinical diagnosis and decision to treat with antibiotics.
AI app ear exam and diagnosis
Diagnostic testUsing a standard otoscope with a cell phone mounted to it, research personnel will record a video image of the tympanic membrane and send it to the cloud for analysis using AI enhanced classification software to render a diagnosis and treatment recommendation
Treatment groups
300 Participants
are divided into 1 treatment groupGroup A: AI App + Standard of care clinical examExperimental treatment 2 interventions
Trial outcomes
Primary outcomes
1
Antimicrobial prescription rate
The rate of antimicrobial prescriptions will be compared between standard care and AI app groups.
Time frame
Day 1Secondary outcomes
1
Acute otitis media diagnosis rate
The rate of diagnosis of acute otitis media will be compared between standard clinical examination and the AI app
Time frame
Day 12
Uninterpretable image rate
The rate of AI app and clinician interpretable images among enrolled participants
Time frame
Day 13
Acute Otitis Media Severity of Symptoms (AOM-SOS) Scale version 6
A validated and reliable 10-item scale for measuring AOM symptom burden. Responses for each item are scored 0-5 and the total score minimum is 0 and maximum is 50. Higher values represent more severe symptoms.
Time frame
From enrollment to 11 days after enrollment4
Acute otitis media recurrences
All participants with paired clinician and AI app images in the same ear will be followed for 3 months to assess recurrences of AOM. This will be determined from diagnostic codes entered into the electronic medical record. A new AOM diagnosis must be at least 14 days after the previous diagnosis. AOM recurrences will be expressed as total counts among participants and total counts among ears.
Time frame
From enrollment to 3 months from enrollmentSponsors and contacts
Click on the lead sponsor to view all of their trials.
Timothy Shope
Lead sponsor
University of Pittsburgh
Sponsor institution
Merck Sharp & Dohme LLC
Collaborator
Source ClinicalTrials.gov