The goal of this research study is to test a new, investigational tool that uses artificial intelligence (AI) to help primary care providers assess skin conditions. This tool is an AI-powered dermatology image reference app that works with a smartphone. For clarity, the AI makes no diagnoses; it provides reference images. Primary care providers then use their own medical judgement and training to make the diagnosis.
The sponsor aims to compare the diagnoses made by primary care providers (such as doctors, nurse practitioners, and physician assistants) with the support of the AI tool compared to a panel of dermatologists, who are setting the gold standard. By doing so, the sponsor can determine the value of the AI tool for primary care providers and understand how it might be used alongside traditional clinical care.
This AI capability complies with FDA regulatory guidelines and is not considered a medical device, similar to a Google image search, which returns similar looking images for reference purposes. For intervention, they healthcare providers use their own training and clinical judgement to make the diagnosis, and not the AI.
Patient must present to walk-in clinic with a primary dermatological complaint.
Patient must have the ability and willingness to provide informed consent and comply with study procedures and visits.
Participants must have access to the required technology (e.g., smartphone with internet access) and be capable of using it for the required image capture.
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).
Single group
Dermatology/Skin - Other
Diagnostic testBelle AI for skin image assessment.
Accuracy of Belle AI Image References
Comparison of Belle AI's image reference system primary probability diagnosis to the reference diagnosis established by the dermatological review committee; additional evaluation of the accuracy of the second and third highest probability diagnoses determined by the Bell Image Match Score
Impact on Economic Burden
Measure economic impact by enabling remote assessment for patients
Agreement between diagnoses
Assessment of agreement between Belle AI's dermatological image reference system primary probability diagnosis and diagnoses made by primary care providers
Provider-Rated Usefulness
Primary care providers rating of the usefulness of the Belle AI in supporting dermatological diagnoses, including subgroup analyses by dermatological training and experience; separate into cases of agreement and disagreement between AI and provider diagnoses.
Cost-Impact Analysis
Cost-impact assessment of Belle AI's diagnostic effectiveness using theoretical cost savings in cases of accurate AI diagnosis.
Protocol Adherence
Separate analyses for per-protocol and intent-to-treat populations to understand adherence effects.
Click on the lead sponsor to view all of their trials.
BelleTorus Corporation
Lead sponsor
Urban Health Plan Inc.
Collaborator
