Skin image reference tool to help doctors diagnose skin conditions
A Skin Image Reference Tool to Aid Healthcare Providers' Diagnosis of Commonly Encountered Dermatologic Diseases
Wake Forest University Health Sciences · NCT07033169
This project will test whether Belle.ai can use three de-identified photos to help dermatologists at an Advocate Health clinic pick the right diagnosis for common skin conditions.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 400 (estimated) |
| Ages | 10 Years and up |
| Sex | All |
| Sponsor | Wake Forest University Health Sciences (other) |
| Locations | 1 site (Winston-Salem, North Carolina) |
| Trial ID | NCT07033169 on ClinicalTrials.gov |
What this trial studies
Consented patients will have three clinical photos uploaded into the Belle.ai system, which uses deep learning trained on over 500,000 images to generate a differential from more than 2,000 skin conditions. All photos are de-identified and labeled only with study codes, and no other patient data are collected. A Dermatologic Review Committee of experts will review and adjudicate cases within the Belle web portal to compare the AI's primary working diagnosis to expert opinion. Success is defined as greater than 80% concordance between Belle.ai's top diagnosis and the dermatology experts, with secondary review of the remaining differential.
Who should consider this trial
Good fit: Patients who present to an Advocate Health dermatology clinic with visible skin conditions, can give informed consent, and whose clinicians can capture and upload smartphone images are the intended participants.
Not a fit: Patients who cannot comply with image capture or consent requirements, and pediatric patients with genital lesions (excluded for privacy), are unlikely to benefit from participation.
Why it matters
Potential benefit: If successful, the tool could speed and standardize dermatology diagnoses, improving timely treatment and access to care.
How similar studies have performed: Other AI-based dermatology image tools have shown promising results for some common conditions, but external validation and consistent performance across diverse skin tones remain variable.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Patient must present to an Advocate Health dermatology clinic * Patient must have the ability and willingness to provide informed consent and comply with study procedures and visits * Participant dermatologists must have access to the required technology (e.g., smartphone with internet access) and be capable of using it for the required image capture Exclusion Criteria: * Patients who are unable to comply with study procedures due to physical or mental health limitations (as assessed by study coordinator) * Pediatric, adolescent, and teen patients who present with dermatological conditions on their genitalia will not be included in the study (in support of patient privacy concerns).
Where this trial is running
Winston-Salem, North Carolina
- Wake Forest University Health Sciences Department of Dermatology — Winston-Salem, North Carolina, United States (RECRUITING)
Study contacts
- Principal investigator: Lindsay C Strowd, MD — Wake Forest University Health Sciences
- Study coordinator: Irma M Richardson, MHA
- Email: irichard@wakehealth.edu
- Phone: 336-716-2903
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.
Conditions: Dermatologic Disease, artificial intelligence, skin diseases, dermatology