Artificial Intelligence Augmented Training in Skin Cancer Diagnostics for General Practitioners

NCT04576416 | Completed

• 1 other identifier: AISC-GP
• Study Type: interventional
• Target: 115
• Locations: 1 country
• Sites: 1

Brief Summary

Background: The worldwide incidence of skin cancer has been rising for 50 years, in particular the incidence of malignant melanoma has increased approx. 2-7% annually and is the most common cancer amongst Danes aged 15-34. Currently there is a significant amount of misdiagnosis of skin cancer and mole cancer. Our aim is to improve general practitioners' diagnostic skills and accuracy of skin and mole cancer. Research questions: In a population of Danish General Practitioners (GPs) what is the dose/response effect of hours spent with an educational platform that offers AI augmented training and clinical feedback on their diagnostic accuracy and accurate clinical management (treatment, dismissal, referral)? Does access to an educational platform that offers AI augmented training and clinical feedback increase the number of malignant skin lesions referred by Danish GPs without simultaneously increasing the number of incorrect benign referrals? Can the participating GPs clinical accuracy be predicted from the MCQ-score by comparing their quiz answers and diagnostic accuracy on their registered lesions with their score on the MCQ? Method: 90 Danish GPs will at baseline, 1 month and end of trial answer a Multiple Choice Questionnaire (MCQ). There is no change to current clinical practice, but all participating doctors will be asked to register a clinical picture and a dermoscopic image as well as basic information about the lesion and patient (age, gender, location and diagnosis) of all skin lesions examined due to a suspicion for non-melanoma or melanoma skin cancer, raised by the GP or patient. GPs in the intervention group are besides the registration application (R-app) given access to an AI augmented training and clinical feedback through an educational smartphone app (E-app). Within the E-app the doctor can access quizzes on a library of 10,000+ skin lesions, written articles about the 40 most common skin lesions, and a clinical feedback module that gives the GP feedback on their registered skin lesions. Feedback on skin lesions with the registered clinical management of referred/excised/biopsied will be provided continuously by independent experts in skin cancer diagnostics (\>10 years of experience) through a web-based review system developed by our group. Feedback on the remaining registered cases are withheld until the end of the study period. This is done to simulate a realistic clinical setting during the study.

Conditions

Melanoma; Skin Cancer

Keywords

Artificial Intelligence; Education; Diagnostic Accuracy; Skin Cancer

Outcome Measures

Primary Outcomes (3)

• Time spent on educational materials

  The participants time spend with the digital educational platform is measured by the platform.

  Participants are assessed over a period of 5 months.

• Change in diagnostic accuracy

  The change in diagnostic accuracy is measured as percentage of correctly diagnosed skin lesions.

  Participants are assessed over a period of 5 months.

• Benign/Malignant Ratio

  All registered lesions will be evaluated by a expert dermatologist. Using the expert opinion as golden standard a ratio of the benign and malignant skin lesions forwarded by the General Practitioner is calculated.

  Participants are assessed over a period of 5 months.

Secondary Outcomes (1)

• Multiple-Choice-Questionnaire predictability of diagnostic accuracy

  Participants are assessed over a period of 5 months.

Study Arms (2)

Intervention

EXPERIMENTAL

During the three months the intervention group will receive access to the AI augmented digital educational platform and its two modules (Training Module and Clinical Feedback Module). They will receive continuous clinical feedback on their registered lesions.

Other: AI augmented training and clinical feedback

Control

NO INTERVENTION

The control group continues its standard clinical practice without access to the E-app, but does register skin lesions throughout the full 3 month period.

Interventions

AI augmented training and clinical feedback OTHER

The educational platform has two modules: The training module includes AI enhanced case training on a library of 10,000+ benign and malignant skin lesion cases each coupled to written learning modules. Participants will be able to track their progression through automatically generated performance statistics and discuss difficult cases with peers within the application. Clinical feedback is defined as diagnostic feedback on all cases registered in the registration module. Feedback during the trial will be based on either histopathology or the consensus agreement of domain experts (if no biopsy is taken). Feedback on referred or dismissed skin lesions will be provided by independent experts in skin cancer diagnostics ( \>10 years of experience) through a web-based review system developed by our group.

Intervention

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)

You may qualify if:

• Participating doctors are required to have a danish doctors authorization and work at least 4 days a week in a general practitioners office.
• The participating doctors may register skin lesions on patients of all ages with skin lesions suspected of skin cancer. A skin lesion is for the purpose of this study defined as a mole or tumor that either patient or GP raises suspicion of skin cancer about.

You may not qualify if:

• Doctors that have participated in a small qualitative pilot study are excluded.

Sponsors & Collaborators

• Herlev Hospital: lead

Study Sites (1)

AISC Research Fascility

Valby, Danmark, 2500, Denmark

Location

MeSH Terms

Conditions

Melanoma; Skin Neoplasms

Condition Hierarchy (Ancestors)

Neuroendocrine Tumors; Neuroectodermal Tumors; Neoplasms, Germ Cell and Embryonal; Neoplasms by Histologic Type; Neoplasms; Neoplasms, Nerve Tissue; Nevi and Melanomas; Neoplasms by Site; Skin Diseases; Skin and Connective Tissue Diseases

Study Officials

• Gustav G Nervil, MD

  Research Unit of Plastic Surgery, Herlev Hospital

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: Participating doctors are either given access to an AI augmented digital educational platform or not. During the study period, both doctors of the intervention and control arm are registering skin lesions they encounter in their daily practice. The expert dermatologists that evaluate the registered skin lesions are unaware of the registering doctors allocation.
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Model Details: A randomized superiority clinical trial. Participating doctors are stratified and randomized to either intervention or control in a 3:1 allocation ratio.

Study Record Dates

• First Submitted: September 24, 2020
• First Posted: October 6, 2020
• Study Start: November 1, 2021
• Primary Completion: January 15, 2022
• Study Completion: January 31, 2022
• Last Updated: July 25, 2023

Record last verified: 2023-07

Locations

DK (1)