AI Diagnostic Support for Ear Infections

(IMAGE Trial)

Recruiting at 1 trial location

Overseen By Nader Shaikh, MD, MPH

Age: < 18

Sex: Any

Trial Phase: Academic

Sponsor: Timothy Shope

Must not be taking: Antimicrobials

Disqualifiers: No URI, Otorrhea, Tympanostomy tubes

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 2

300 Participants Needed

What You Need to Know Before You Apply

What is the purpose of 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.

Will I have to stop taking my current medications?

The trial does not specify if you need to stop taking your current medications, but if your child is currently taking antimicrobials (medications that kill or stop the growth of microorganisms), they cannot participate in the study.

Is the AI diagnostic support for ear infections safe for humans?

The research does not provide specific safety data for the AI diagnostic support for ear infections, but it focuses on improving the accuracy of diagnosing ear infections, which could reduce unnecessary treatments like antibiotics. ^{1 2 3 4 5}

How does the AI Diagnostic Support for Ear Infections treatment differ from other treatments for ear infections?

This treatment is unique because it uses artificial intelligence (AI) to assist in diagnosing ear infections by analyzing images from a smartphone-based otoscope. Unlike traditional methods that rely heavily on the examiner's experience, this AI-driven approach aims to provide more accurate and consistent diagnoses, even in mobile settings. ^{2 3 6 7 8}

What data supports the effectiveness of the AI app treatment for ear infections?

Research shows that AI models can diagnose ear infections like otitis media more accurately than clinicians, with one study reporting a 90.6% accuracy compared to 59.4% by pediatricians. This suggests that the AI app could be a helpful tool for diagnosing ear infections. ^{1 3 4 5 6}

Who Is on the Research Team?

Timothy R Shope, MD, MPH

Principal Investigator

UPMC Children's Hospital

Are You a Good Fit for This Trial?

This trial is for young children aged 6-24 months who are showing symptoms of upper respiratory infections, such as colds or swimmer's ear. The study aims to include those who may have difficulty with traditional ear exams due to small ear canals or restlessness.

Inclusion Criteria

I currently have an upper respiratory infection.

My child is between 6 to 24 months old.

Exclusion Criteria

I do not have an upper respiratory infection.

I am currently on antibiotics.

I have discharge from my ear.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

1-2 weeks

1 visit (in-person)

Enrollment and Initial Assessment

Participants undergo initial ear examination using the AI app and standard clinical exam

1 day

1 visit (in-person)

Follow-up

Participants are monitored for symptom resolution and side effects of antimicrobial use

10 days

Daily symptom monitoring (remote)

Extended Follow-up

Participants are monitored for acute otitis media recurrences

3 months

What Are the Treatments Tested in This Trial?

Interventions

• AI app

Trial Overview The trial is testing the effectiveness of an AI app in diagnosing ear infections compared to standard clinical exams. Photos of eardrums taken during visits will be analyzed by the AI to see if it changes diagnosis and treatment decisions.

How Is the Trial Designed?

Group I: AI App + Standard of care clinical exam Experimental Treatment 2 Interventions

Using a within subject design, each child's ear will be in the experimental and standard care group. Each ear will be examined by the AI app and a clinician (blinded to the AI app diagnosis) to provide a diagnosis and treatment recommendation.

Who Is Running the Clinical Trial?

Timothy Shope

Lead Sponsor

Trials

1

Recruited

300+

Merck Sharp & Dohme LLC

Industry Sponsor

Trials

4,096

Recruited

5,232,000+

Chirfi Guindo

Merck Sharp & Dohme LLC

Chief Marketing Officer since 2022

Degree in Engineering from Ecole Centrale de Paris, MBA from New York University Stern School of Business

Robert M. Davis

Merck Sharp & Dohme LLC

Chief Executive Officer since 2021

JD from Northwestern University Pritzker School of Law, MBA from Northwestern University Kellogg Graduate School of Management, Bachelor's in Finance from Miami University

Published Research Related to This Trial

A new handheld optical coherence tomography (OCT) system can non-invasively assess middle ear infections by detecting effusions and bacterial biofilms, improving upon traditional subjective diagnostic methods.

The integration of a real-time machine learning classifier allows for consistent and accurate categorization of middle ear conditions, making the OCT system more user-friendly and effective for diagnosing infections in clinical settings.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Handheld Briefcase Optical Coherence Tomography with Real-Time Machine Learning Classifier for Middle Ear Infections. Won, J., Monroy, GL., Dsouza, RI., et al.[2021]

Citations

1. England pubmed.ncbi.nlm.nih.gov

Smartphone-based artificial intelligence using a transfer learning algorithm for the detection and diagnosis of middle ear diseases: A retrospective deep learning study. [2022]

2. United States pubmed.ncbi.nlm.nih.gov

OTITIS MEDIA VOCABULARY AND GRAMMAR. [2021]

3. England pubmed.ncbi.nlm.nih.gov

AI Model Versus Clinician Otoscopy in the Operative Setting for Otitis Media Diagnosis. [2023]

4. United States pubmed.ncbi.nlm.nih.gov

Intelligent smartphone-based multimode imaging otoscope for the mobile diagnosis of otitis media. [2022]

5. United States pubmed.ncbi.nlm.nih.gov

Automated diagnosis of otitis media: vocabulary and grammar. [2021]

6. England pubmed.ncbi.nlm.nih.gov

Evaluating the generalizability of deep learning image classification algorithms to detect middle ear disease using otoscopy. [2023]

7. United States pubmed.ncbi.nlm.nih.gov

Development of an Automatic Diagnostic Algorithm for Pediatric Otitis Media. [2019]

8. Switzerland pubmed.ncbi.nlm.nih.gov

Handheld Briefcase Optical Coherence Tomography with Real-Time Machine Learning Classifier for Middle Ear Infections. [2021]