Neoplasms

Skin and Connective Tissue Diseases

All Conditions

Rare Diseases

Melanoma

Skin Neoplasms

Neuroendocrine Tumors

Neuroectodermal Tumors

Neuroectodermal Tumors, Primitive

Neoplasms, Germ Cell and Embryonal

Neoplasms by Histologic Type

Neoplasms, Nerve Tissue

Nevus, Pigmented

Nevus

Nevi and Melanomas

Skin Diseases

Neuroendocrine Tumor

Neuroepithelioma

This group will receive access to the AI augmented digital online educational system and its two modules (Training Module and Clinical Feedback Module). They will receive continuous clinical feedback on their registered lesions.

This group is withheld their access to the AI augmented digital online educational system for 2 months.

After the 2 months delay, the subjects in the group are given the same access as the participants in Group A.

DermLoop Learn is our AI augmented digital online educational system with case training on a library of 10,000+ benign and malignant skin lesion as well as written learning modules for the most common skin lesion diagnosis.

DermLoop Learn

Gustav G Nervil, MD

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, and most excised skin lesions are benign.

Previous studies have shown that there is no significant increase in doctors diagnostic accuracy during the first 6 years of clinical work.

The resources spend on healthy people could be put to better use, if the Benign-Malignant Ratio could be lowered. This could potentially be done by better educating the doctors during their everyday clinical practice.

Aim:

The aim of this study is to investigate the dose/response effect of an AI augmented training and clinical feedback on the diagnostic accuracy of skin cancer and clinical decisions among doctors from specialized skin cancer centers.

Research question: How much specialized doctors need to train before their diagnostic accuracy and clinical decisions change?

Design:

This study is a superiority trial designed as an international multicenter randomized controlled trial of doctors in highly specialized centers that diagnose and/or treat skin- and mole cancer.

Randomization Eligible participants will be randomized into either the intervention or control group, ratio 1:1.

Intervention:

The participants of group A are given access to a digital educational online system developed by the research group, are asked to register all skin lesions seen with a registration app (clinical and dermoscopic photos and clinical data), also developed by the research group, and will be given clinical feedback on every registered skin lesion.

Participants in group B are also asked from day one to register all skin lesions and will receive feedback on these as the participants of group A, but are withheld their access to the digital educational online system for 2 months.

Feedback on removed/biopsied skin lesions is given directly from the pathologist, who in turn are given easy access to photographs and clinical data of the patient and skin lesion in question.

Statistics:

The average increase in diagnostic accuracy for the population of participating doctors as an effect of the hours spent with the digital educational online system is calculated using Generalized Estimating Equations (GEE).

As benign lesions can be excised/treated for other reasons than suspicion of malignancy we will analyze correctly diagnosed benign lesions treated for different reasons (cosmetic or functional complaints etc.) separately.

We expect a majority of registered lesions to be benign, despite most of the patients already having been seen by GPs before referral.

Ethical considerations:

Patient participation contains no immediate strain or discomfort for the patient, and no change to current clinical practice, as dermoscopic evaluation is part of the clinical examination of skin lesions. The images captured are stored safely and anonymously with no risk for the patient.

With the current low diagnostic accuracy of young doctors the educational nature of the intervention justifies the study for the sake of all future patients with skin lesions that are less likely to be misdiagnosed.

Educational interventions on doctors do not require approval by The National Committee on Health Research Ethics in Denmark. However ethical considerations have been made and the project is in concordance with the Helsinki Declaration II.

A randomized superiority clinical trial. Participating doctors are randomized to either group A or B in a 1:1 ratio.

Participating doctors are either given access to an AI augmented digital educational online system or not. During the study period, doctors of both groups are registering skin lesions they encounter in their daily practice using the same hardware and software.

The expert dermatologists that evaluate the registered skin lesions are unaware of the registering doctors allocation.

AI Augmented Training for Skin Specialists

Artificial Intelligence Augmented Training in Skin Cancer Diagnostics for Skin Cancer Specialists

Dose/response between hours spent with the education system and change in diagnostic accuracy for the participating doctors

Difference in Benign to Malignant ratio (BMR) in treated/referred/sent home lesions suspected of skin cancer.

Correlation between diagnostic accuracy and score measured on the MCQ at baseline and at 0 and 2 months.

Change in the amount of referrals between the control and intervention group of the departments of dermatology to the departments of plastic surgery in the time before and after the intervention.

Herlev Hospital

Principal Investigator

DermLoop Learn is our AI augmented digital educational platform with case training on a library of 18,000+ benign and malignant skin lesion as well as written learning modules for the most common skin lesion diagnosis.

Louisa Bønløkke Hansen

Background:

Melanoma mortality remains almost stable with a 0.2-1.5% increase annually despite rapid growth in reported melanoma incidence of 2.5-8.6% per year. Part of this discrepancy could be explained by overdiagnosis of melanoma, which may be as high as 54%. Histopathology is considered the gold standard diagnosis for melanocytic lesions despite only a moderately good intra- and inter-rater reliability. A possible explanation of why the inter-rater reliability is suboptimal could be that pathologists are inexperienced, extra cautious, or lack sufficient information needed for a reliable diagnosis.It has been hypothesized that the horizontal overview of a lesion through dermoscopy combined with clinical information on a given tumor, enables the generation of a tentative diagnosis that the pathologists can use to actively search for signs of pathology. Former research shows that clinicians' competence in dermoscopy can be improved by a short learning intervention, but that these skills aren't sustainable

Aim:

The aim of this study is to examine how acquired basic skills in dermoscopy of pigmented lesions and access to clinical images of a lesion, affect pathologists' confidence, accuracy and inter-rater reliability when interpreting melanocytic lesions.

Method:

Preparative phase:

Case database

Lesion data will be collected from patients during the period between 02.11.2020 and 22.01.2021 at the Department of Plastic Surgery, Herlev Hospital. Requirements for eligibility are:

The patient is referred through the clinical cancer pathways for melanoma The lesion is excised upon evaluation by the plastic surgeon.

An internal investigation has shown that approximately ⅓ of all melanocytic lesions referred in the clinical cancer pathway are melanomas (in situ and invasive).

Patients will receive oral and written information about the project and be asked to sign a consent form before participation. Participation will not affect the treatment, diagnostics, or follow-up of included patients. Upon consent the following information will be collected for each lesion:

Clinical image Dermoscopic image Patients´ CPR-number (personal ID-number) Gender and age of the patient Location of skin tumor (3D avatar) Medical history (congenital nevi, pregnant patient, how long has it been present, appearance change, symptoms, former melanoma, family history of melanoma, sun exposure within the last six months) As soon as the lesions have been prepared for pathological examination, a representative slide (including pathognomic features) for each skin lesion will be chosen by an experienced dermatopathologist. This slide will subsequently be digitized and coupled to the remaining information (dermoscopic and clinical image, tumor location, gender, age, lesion information, etc.). Thereafter the CPR number is deleted, rendering the case anonymous. Each case will be stored in a database under a random anonymous ID number.

Web-based IT-platform

In order to maximize patient participation and the number of pathologists that can be included in the study, the investigators will develop an IT platform for the trial. The platform will enable the following features:

Sign-in Automated randomization Login Case presentation Diagnosis of cases Tracking

The IT platform:

The diagnostic options will be based on the standardized MPATH-Dx formula (participants will be introduced to this before participation) used in former studies on inter-rater reliability. Subsequent to diagnosing the lesion, participating pathologists will rate their confidence in the chosen diagnosis on a 5-step Likert scale. Participants will be grouped by department or affiliation center in order to enable post-hoc cluster analyses and continuous status reports during the study. The tracking feature will enable search pattern analysis including time per diagnosis and percentage of time spent looking at the histology slide and dermoscopy photo. Saliency heat maps will be developed that enable visualization of "classical" search patterns (both global and feature specific) in both study groups.

Executive phase:

General pathologists and dermatopathologists from Denmark, Australia and other countries will be enrolled between 1.09.2021 and 1.10.2021. All participants will be sent an email informing them about the trial and the handling of their data before signing a digital consent. Upon inclusion each enrolled pathologist will be asked to fill out a digital sign-in form with the following variables:

Name E-mail address (including verification) Age Gender Subspecialization (general pathologist or dermatopathologist) Number of years interpreting skin lesions Caseload from melanocytic lesions per month Percentage of caseload from melanocytic lesions Number of second opinion assessments per month Number of second opinion referrals per month Former training in dermoscopy (yes/no) Perceived relevance of dermoscopic images during histopathological evaluation on a 5-step Likert scale

Following the sign-in, all participants will be asked to answer a dermoscopy test consisting of 20 formerly validated test items. Then they will be automatically stratified by level of dermatopathological experience and randomized (allocation ratio 1:1) to either the intervention or control group. Participants in the intervention group will receive immediate access to a previously developed digital (tablet or smartphone) educational platform in dermoscopy of melanocytic lesions and then answer the dermoscopy test again, before diagnosing the lesions in this study. Participants in the control group will not be given access to the learning intervention but will diagnose the lesions from this study immediately after sign up and dermoscopy test. Each participant will be asked to assess a minimum of 50 cases within 14 days, preferably all 200 cases.

Statistics:

The accuracy will be measured as the number of correct answers divided by the total number of answers. Consensus agreement among pathologists with a caseload of more than 60 melanocytic lesions per month and at least 10 years of experience will be used as the gold standard. Inter-rater reliability will be measured using generalizability theory that allows calculations in nested and unbalanced designs. Mean time spent per diagnosis and diagnostic confidence during 1st evaluation will be compared between the study groups using independent t-tests. A post hoc ANOVA will compare time spent per diagnosis and confidence of pathologists grouped by time spent training in dermoscopy.

Randomized clinical trial. Pathologists are randomized to either the control group or det intervention, allocation ratio 1:1.

Participating Pathologists are either given access to a learning intervention called DermLoop Learn for a short period, or not given access to any learning intervention. During the trial, both groups are interpreting histopathological skin lesions with acces to clinical information, an overview picture, and a dermoscopic picture of the lesion.

Dermoscopy Augmented Histology Trial

Correlation Between Dermoscopy Training of Pathologists and Improvement of Histopathological Interpretation of Skin Lesions

Comparison of the pathologists interpretation/diagnosis of each case.

Comparing time spent per case (overall) and time spent on each image (clinical, dermoscopic, histopathological) with the interpretation of the case e.g. the diagnosis.

Medical student

Carcinoma

Access to educational mobile application for 8 days, diagnosing 500 digital patient-cases.

Control group receiving no intervention, continuing daily practice.

Educational Mobile Application with a library of digital patient-cases and written learning modules the user can access on 36 common skin lesions, both benign and malignant.

Dermloop Learn

This study aimed to examine if self-paced learning with a novel digital patient-case-based educational platform can increase primary care physicians' diagnostic accuracy of malignant and benign skin lesions on both the level of benign/malignant and the diagnosis level. Secondarily the study aimed to investigate the time spent in reaching this change in proficiency.

Participants were given a questionnaire and an initial Skin Cancer Multiple Choice-Questionnaire (MCQ) to test their diagnostic skills regardining skin and mole cancer and the most common differential diagnoses.

Participants in the Intervention group was then given access to an educational mobile application (App) for 8 days and asked to diagnose 500 patient cases. The participants did so at their own leisure and time.

After 8 days they were asked to abstain from using the App for another 8 days (wash out period) and were then given a Final Skin Cancer Multiple Choice-Questionnaire (MCQ).

Participants of the control group received no intervention nor education during the 16 days of waiting before they took the final Skin Cancer Multiple Choice-Questionnaire.

Intervention and Controlgroup parallel design using sequential continues block randomization.

App Teaches Doctors to Diagnose Skin Cancer

Improving Diagnostic Accuracy in Skin Cancer Diagnostics Using Educational Mobile App: a Randomized Controlled Study

Participant quiz-answer data can be shared upon reasonable request.

Participants are given a test before and after the intervention using a skin cancer MCQ test with 12 digital-patient cases. A higher score means better diagnostic proficiency. The primary outcome is the change of this score.

Sensitivity, Specificity and Positive Predictive Value of the participants in the intervention group, calculated on their cases seen in the educational mobile application.

The Dermloop Learn app tracks how much time each user spends quizzing and reading.

Study title	NCT ID	Conditions	Interventions	Eligibility	Organization
AI Augmented Training for Skin Specialists	NCT04758988	Melanoma Skin Cancer	DermLoop Learn	-	Herlev Hospital
Dermoscopy Augmented Histology Trial	NCT05004792	Melanoma Pigmented Lesio...	DermLoop Learn	-	Herlev Hospital
Dermoscopy Augmented Histology Trial	NCT05004792	Melanoma Pigmented Lesio...	DermLoop Learn	-	Herlev Hospital
App Teaches Doctors to Diagnose Skin Cancer	NCT05661370	Melanoma (Skin) Carcinoma	Dermloop Learn	18 Years - 120 Years	Herlev Hospital
App Teaches Doctors to Diagnose Skin Cancer	NCT05661370	Melanoma (Skin) Carcinoma	Dermloop Learn	18 Years - 120 Years	Herlev Hospital
App Teaches Doctors to Diagnose Skin Cancer	NCT05661370	Melanoma (Skin) Carcinoma	Dermloop Learn	18 Years - 120 Years	Herlev Hospital

Spots Global Cancer Trial Database for dermloop learn