Artificial Intelligence Patient App for RDEB SCCs

NCT05843994 | Active Not Recruiting

• 1 other identifier: 2023-5810
• Study Type: observational
• Target: 20
• Locations: 1 country
• Sites: 1

Brief Summary

In this study, an artificial intelligence model to detect squamous cell carcinomas (SCC) on photos of recessive dystrophic epidermolysis bullosa (RDEB) skin is developed. The ultimate goal is to integrate this model into an app for patients and physicians, to help detect SCCs in RDEB early. SCCs which rapidly metastasize are the main cause of death in adults with RDEB. The earlier an SCC is recognized, the easier it can be removed and the better the outcome. AI leverages computer science to perform tasks that typically require human intelligence and has recently been used to identify skin cancers based on images. We are currently developing an AI approach for early detection of SCC and distinction of malignancy from chronic wounds and other RDEB skin findings. The aim is to create a web application for patients with RDEB to upload images of their skin and get an output as to SCC present/ no SCC. This will be especially valuable for patients with difficult access to medical expertise and those who are hesitant to allow full skin examination at each visit, often because of fear of biopsies. Thus, this project will directly benefit patients by allowing early recognition of SCCs and will empower patients and their families by providing a home use tool. So far, the study team has mainly used professional images (photographs taken in hospital settings by physicians, nurses, and clinical photographers) of both SCCs in RDEB and images of RDEB skin without SCC to develop and train the AI model. The images that are expected in a real-life setting will mostly be pictures taken by patients or family members with their phones or digital cameras. These images have different properties regarding resolution, focus, lighting, and backgrounds. Incorporating such images will be crucial in the upcoming phases of model development-testing and validation-for the web application be a success for patients.

Conditions

Epidermolysis Bullosa Dystrophica

Keywords

epidermolysis bullosa; skin abnormalities; congenital abnormalities; skin disease, genetic; genetic diseases, inborn; skin diseases; skin disease, vesiculobullous; carcinoma, squamous cell; skin neoplasms; artificial intelligence

Outcome Measures

Primary Outcomes (1)

• Percent agreement of the presence or absence of squamous cell carcinoma (SCC) on the skin in photographs as detected by the App versus confirmed physician diagnosis

  one day survey

Interventions

online survey OTHER

Participants will complete an online survey and submit photographs.

Eligibility Criteria

• Age: 12 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Patients with RDEB worldwide are invited to participate in this virtual research to contribute photographs of their SCCs. To participate in this study, please follow this link: https://redcap.nubic.northwestern.edu/redcap/surveys/?s=JH9LHR4CC4R4H3HN

You may qualify if:

• patient with recessive dystrophic epidermolysis bullosa
• patient with history of cutaneous squamous cell carcinoma
• patient consent for upload and use of clinical data and photographs

You may not qualify if:

• Patients who do not agree to upload and use of photographs and clinical data

Sponsors & Collaborators

• Northwestern University: lead
• Epidermolysis Bullosa Research Partnership: collaborator

Study Sites (1)

Department of Dermatology, Northwestern University Feinberg School of Medicine and Lurie Children's Hospital

Chicago, Illinois, 60611, United States

Location

MeSH Terms

Conditions

Epidermolysis Bullosa Dystrophica; Epidermolysis Bullosa; Skin Abnormalities; Congenital Abnormalities; Skin Diseases, Genetic; Genetic Diseases, Inborn; Skin Diseases; Skin Diseases, Vesiculobullous; Carcinoma, Squamous Cell; Skin Neoplasms

Condition Hierarchy (Ancestors)

Congenital, Hereditary, and Neonatal Diseases and Abnormalities; Collagen Diseases; Connective Tissue Diseases; Skin and Connective Tissue Diseases; Carcinoma; Neoplasms, Glandular and Epithelial; Neoplasms by Histologic Type; Neoplasms; Neoplasms, Squamous Cell; Neoplasms by Site

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Study Record Dates

• First Submitted: April 24, 2023
• First Posted: May 6, 2023
• Study Start: January 30, 2023
• Primary Completion (Estimated): November 30, 2028
• Study Completion (Estimated): November 30, 2028
• Last Updated: February 3, 2026

Record last verified: 2026-01

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)