Trial Review

The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been endorsed by the ANZCTR. Before participating in a study, talk to your health care provider and refer to this information for consumers
Trial registered on ANZCTR


Registration number
ACTRN12615000268549
Ethics application status
Approved
Date submitted
2/03/2015
Date registered
23/03/2015
Date last updated
26/06/2018
Type of registration
Prospectively registered

Titles & IDs
Public title
Efficacy of Smartphone applications in diagnosing and detecting melanoma
Scientific title
For a patient with naevi, do smart phone applications when compared to diagnosis by gold standard histo-pathological report/dermatologist provide an effective way for individuals to self-detect melanoma.
Secondary ID [1] 286252 0
Nil
Universal Trial Number (UTN)
U1111-1167-5675
Trial acronym
Linked study record

Health condition
Health condition(s) or problem(s) studied:
melanoma 294305 0
Condition category
Condition code
Cancer 294628 294628 0 0
Malignant melanoma
Cancer 294629 294629 0 0
Non melanoma skin cancer
Skin 294630 294630 0 0
Dermatological conditions

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure
Study of the efficacy of use of Dr Mole, Skinvision and Spotmole Plus smartphone applications in the self diagnosis of melanoma from images of naevi. Photos of naevi will be taken by smartphones. A dermatology consultation will determine if lesions are suspicious or benign. For patients with suspicious lesions, photos will be taken prior to the traditional dermatological intervention involving excision of the lesion. The smartphone photo's will be submitted to each of the smartphone applications for evaluation. The smartphone application evaluations will then be compared to the histo-pathological report and dermatologist diagnosis for suspect lesions, and to the dermatologist diagnosis for benign lesions (as no histo-pathological diagnosis will be available for benign lesions).
Intervention code [1] 291267 0
Diagnosis / Prognosis
Comparator / control treatment
Histo-pathological report/Dermatologist diagnosis of naevi images
Control group
Active

Outcomes
Primary outcome [1] 294392 0
Statistically significant results from analysis of outcomes of original image evaluations by the smartphone applications compared to gold standard histo-pathological reports/dermatologist diagnosis. Overall sensitivity, specificity, positive predictive value and negative predictive value for each application will be determined. McNemar chi-square test will be used to compare the respective sensitivities of the various smartphone applications. This is a composite primary outcome to determine the overall accuracy of the smartphone applications in detecting suspicious lesions.
Timepoint [1] 294392 0
Primary timepoint is when the smartphone application evaluation of the smartphone naevi photo is compared to the gold standard histo-pathological report/dermatologist diagnosis of the same naevi
Secondary outcome [1] 313185 0
Statistically significant results from analysis of outcomes of smartphone photo's taken from high quality printouts of original images (original smartphone photos of the actual naevi on the patient), with evaluations by the smartphone applications compared to gold standard histo-pathological report/dermatologist diagnosis. Overall sensitivity, specificity positive predictive value and negative predictive value for each application will be determined. McNemar chi-square test will be used to compare the respective sensitivities of the various smartphone applications. This is a composite secondary outcome to determine the overall accuracy of the smartphone applications for detecting suspicious lesions when using smartphone photos of high quality printouts of the original naevi photos (rather than the original naevi photos taken and used in Primary Outcome 1).
Timepoint [1] 313185 0
High quality print outs of the original naevi photo's will be made. Smartphone photo's of these print outs will be taken and submitted to the smartphone applications for evaluation. These secondary photo evaluations by the smartphone applications with be compared to the gold standard histo-pathological report/dermatologist diagnosis of the same naevi.

Eligibility
Key inclusion criteria
Patients with suspected melanoma and/or clinically benign lesions
Minimum age
18 Years
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
No suspected melanoma or clinically benign lesions

Study design
Purpose of the study
Diagnosis
Allocation to intervention
Non-randomised trial
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
Masking / blinding
Who is / are masked / blinded?



Intervention assignment
Other design features
Phase
Not Applicable
Type of endpoint/s
Statistical methods / analysis
Each of the applications will be presented with each skin lesion. Each result will be determined as positive, negative or unevaluable. The percentage of images presented to each application that are evaluable will be described. For each photo, we will assign the app a score of “correct” if it identified a melanoma as such, and “incorrect” if a melanoma received a different or benign diagnosis, using the histo-pathological reports as the gold standard. For benign lesions, the clinical diagnosis by a board certified dermatologist will be used as the gold standard. Histology and clinical diagnosis are both best clinical practice in each respective case and hence there is no confounding effect. We will assign a score of “correct” to benign lesions which were identified as such by the apps, and “incorrect” if it was given a higher grade of suspicion. Statistical analysis of these results will be performed using commercially available software. Overall sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) for each application will be determined for both real time imaging and photos taken later from printouts.
Within the study period we expect to be able to recruit 10 patients with a suspected melanoma and 20 patients with clinically benign lesions. Allowing for 10% of these lesions being unavailable for photographing due to exclusion criteria (lesions with uncertain histological diagnoses, Spitz nevi, pigmented spindle cell nevus of Reed and other uncommon or potentially ambiguous lesions), this will leave 9 melanomas and 18 benign lesions for evaluation. This estimated number of suitable lesions for evaluation will allow an estimation of sensitivity with a confidence interval of 95%. We will use McNemar chisquare test to compare the respective sensitivities of the various apps. All statistical significance will be accepted at p<0.05.

Recruitment
Recruitment status
Completed
Date of first participant enrolment
Anticipated
26/03/2015
Actual
2/04/2015
Date of last participant enrolment
Anticipated
Actual
12/07/2016
Date of last data collection
Anticipated
Actual
12/07/2016
Sample size
Target
30
Accrual to date
Final
38
Recruitment in Australia
Recruitment state(s)
QLD
Recruitment hospital [1] 3512 0
Princess Alexandra Hospital - Woolloongabba
Recruitment postcode(s) [1] 9277 0
4102 - Woolloongabba

Funding & Sponsors
Funding source category [1] 290814 0
University
Name [1] 290814 0
Dermatology Research Centre, School of Medicine, University of Queensland
Country [1] 290814 0
Australia
Primary sponsor type
University
Name
Dermatology Research Centre, School of Medicine, University of Queensland
Address
Translational Research Institute (TRI)
37 Kent St,
Woolloongabba, QLD, 4102
Country
Australia
Secondary sponsor category [1] 289500 0
None
Name [1] 289500 0
Address [1] 289500 0
Country [1] 289500 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 292438 0
Metro South Human Research Ethics Committee
Ethics committee address [1] 292438 0
Centres for Health Research
Lvl 7, Translational Research Institute,
37 Kent St,
Woolloongabba, QLD, 4102
Ethics committee country [1] 292438 0
Australia
Date submitted for ethics approval [1] 292438 0
Approval date [1] 292438 0
02/10/2014
Ethics approval number [1] 292438 0
HREC/14/QPAH/473
Ethics committee name [2] 292439 0
University of Queensland Institutional Human Research Ethics Committee
Ethics committee address [2] 292439 0
University of Queensland
UQ Research and Innovation
Cumbrae-Stewart Building,
St Lucia, QLD, 4072
Ethics committee country [2] 292439 0
Australia
Date submitted for ethics approval [2] 292439 0
Approval date [2] 292439 0
13/10/2014
Ethics approval number [2] 292439 0
2014001372

Summary
Brief summary
This study aims to determine whether the smartphone applications for skin screening are effective at providing an accurate diagnosis of melanoma.
Who is it for?
You may be eligible to join this study if you are aged 18 years or above and have a suspected melanoma and/or clinically benign skin lesion.
Study details.
The accuracy of smartphone applications will be tested by taking photos of the skin lesions and comparing the smartphone applications evaluation against the histological gold standard diagnosis by a dermatologist.
If the study shows that these applications are accurate, this will allow greater acceptance of them for medical use. If inaccurate, it will raise concerns about the need for regulation of these applications due to the health risk posed.
Trial website
Trial related presentations / publications
Alex Ngoo, Anna Finnane, Jean-Marie Tan, Monika Janda, H. Peter Soyer. 'The Efficacy of smartphone applications in detecting melanoma. Asia-pacific combined dermatology research conference 2016 – poster presentation

Alex Ngoo. 'The efficacy of smartphone applications in detecting melanoma'. 2nd Global advances and controversies in skin cancer 2015 – oral presentation

Alex Ngoo. 'The efficacy of smartphone applications in detecting melanoma'.UQ undergraduate research conference 2015 – oral presentation
Public notes

Contacts
Principal investigator
Name 55270 0
Prof H. Peter Soyer
Address 55270 0
Dermatology Research Centre
Level 5, Translational Research Institute
37 Kent St,
Woolloongabba, QLD, 4102
Country 55270 0
Australia
Phone 55270 0
+61 07 3443 8017
Fax 55270 0
Email 55270 0
[email protected]
Contact person for public queries
Name 55271 0
Mrs Elizabeth Payne
Address 55271 0
Dermatology Research Centre
Level 5, Translational Research Institute
37 Kent St,
Woolloongabba, QLD, 4102
Country 55271 0
Australia
Phone 55271 0
+61 07 3443 7397
Fax 55271 0
Email 55271 0
[email protected]
Contact person for scientific queries
Name 55272 0
Mrs Elizabeth Payne
Address 55272 0
Dermatology Research Centre
Level 5, Translational Research Institute
37 Kent St,
Woolloongabba, QLD, 4102
Country 55272 0
Australia
Phone 55272 0
+61 07 3443 7397
Fax 55272 0
Email 55272 0
[email protected]

No information has been provided regarding IPD availability


What supporting documents are/will be available?

No Supporting Document Provided



Results publications and other study-related documents

Documents added manually
No documents have been uploaded by study researchers.

Documents added automatically
SourceTitleYear of PublicationDOI
Dimensions AIEfficacy of smartphone applications in high-risk pigmented lesions2017https://doi.org/10.1111/ajd.12599
N.B. These documents automatically identified may not have been verified by the study sponsor.