AI-guided eardrum photos to improve diagnosis of ear infections in infants
Intelligent Medical Assessment for Guiding Ear Infection Treatment
This will test an AI app that reads photos of infants' eardrums to see if it changes how doctors diagnose ear infections and prescribe antibiotics for children 6–24 months with cold symptoms.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 300 (estimated) |
| Ages | 6 Months to 24 Months |
| Sex | All |
| Sponsor | University of Pittsburgh Academic / other |
| Locations | 2 sites (Pittsburgh, Pennsylvania and 1 other locations) |
| Trial ID | NCT06876259 on ClinicalTrials.gov |
What this trial studies
This is a 12-month, single-center, within-subject trial enrolling about 300 children aged 6–24 months who present with upper respiratory symptoms. Each child's ears will be photographed and reviewed both by a standard clinical exam and by an AI imaging app in a double-blind within-subject design, producing paired diagnoses. The primary outcome compares antimicrobial prescription rates using 150 paired image/clinician decisions, and secondary outcomes include the proportion of uninterpretable images and AOM diagnosis rates. Parents will record symptoms daily for 10 days in electronic diaries to track symptom resolution and side effects, with study staff contacting families if symptom scores rise by more than 20%.
Who should consider this trial
Good fit: Children aged 6–24 months with upper respiratory symptoms who are not currently taking antibiotics and who do not have tympanostomy tubes or purulent ear drainage are ideal candidates.
Not a fit: Children with ear tubes, visible purulent ear drainage, no upper respiratory symptoms, or those already on antimicrobials would not be eligible and are unlikely to benefit from this intervention.
Why it matters
Potential benefit: If successful, this approach could reduce unnecessary antibiotic prescriptions by improving diagnostic accuracy for ear infections in young children.
How similar studies have performed: Prior technical studies of AI eardrum classifiers have shown high diagnostic accuracy, but using such apps to change clinician prescribing in routine care remains largely untested.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age 6-24 months * Presence of upper respiratory infection Exclusion Criteria: * No upper respiratory infection * Otorrhea * Tympanostomy tubes * Currently taking antimicrobials
Where this trial is running
Pittsburgh, Pennsylvania and 1 other locations
- Children's Community Pediatrics Brentwood — Pittsburgh, Pennsylvania, United States (Recruiting)
- Children's Community Pediatrics Castle Shannon — Pittsburgh, Pennsylvania, United States (Recruiting)
Study contacts
- Principal investigator: Timothy R Shope, MD, MPH — UPMC Children's Hospital
- Study coordinator: Timothy R Shope, MD, MPH
- Email: timothy.shope@chp.edu
- Phone: 412-692-5471
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.