[Skip to Content]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address 18.207.136.184. Please contact the publisher to request reinstatement.
[Skip to Content Landing]
Figure.
Mean Percent Correct on Preassessments and Postassessments for Application and Rule-Based Groups
Mean Percent Correct on Preassessments and Postassessments for Application and Rule-Based Groups

This figure shows a statistically significant improvement in postassessment outcomes for users of Skinder (absolute difference, 9%; P = .003).

Table.  
Composite Results of Poststudy Questionnairea
Composite Results of Poststudy Questionnairea
1.
Aldridge  RB, Zanotto  M, Ballerini  L, Fisher  RB, Rees  JL.  Novice identification of melanoma: not quite as straightforward as the ABCDs.  Acta Derm Venereol. 2011;91(2):125-130. doi:10.2340/00015555-1070PubMedGoogle ScholarCrossref
2.
Girardi  S, Gaudy  C, Gouvernet  J, Teston  J, Richard  MA, Grob  JJ.  Superiority of a cognitive education with photographs over ABCD criteria in the education of the general population to the early detection of melanoma: a randomized study.  Int J Cancer. 2006;118(9):2276-2280.PubMedGoogle ScholarCrossref
3.
Aldridge  RB, Maxwell  SS, Rees  JL.  Dermatology undergraduate skin cancer training: a disconnect between recommendations, clinical exposure and competence.  BMC Med Educ. 2012;12:27. doi:10.1186/1472-6920-12-27PubMedGoogle ScholarCrossref
4.
McWhirter  JE, Hoffman-Goetz  L.  Visual images for patient skin self-examination and melanoma detection: a systematic review of published studies.  J Am Acad Dermatol. 2013;69(1):47-55. Published online March 6, 2013. doi:10.1016/j.jaad.2013.01.031PubMedGoogle ScholarCrossref
5.
Aldridge  RB, Glodzik  D, Ballerini  L, Fisher  RB, Rees  JL.  Utility of non-rule-based visual matching as a strategy to allow novices to achieve skin lesion diagnosis.  Acta Derm Venereol. 2011;91(3):279-283. doi:10.2340/00015555-1049PubMedGoogle ScholarCrossref
Views 616
Citations 0
Research Letter
June 2018

Assessment of Smartphone Application for Teaching Intuitive Visual Diagnosis of Melanoma

Author Affiliations
  • 1Section of Dermatology, West Virginia University, Morgantown
  • 2University of Utah School of Medicine, Salt Lake City
  • 3Section of Dermatology, Virginia Tech Carilion School of Medicine, Roanoke
JAMA Dermatol. 2018;154(6):730-731. doi:10.1001/jamadermatol.2018.1525

The ABCD rule has long been the primary framework for teaching clinicians and patients to differentiate melanomas from benign lesions. However, it remains unclear that such rule-based methods are a substitute for pattern-recognition skills in the diagnosis of skin lesions.1,2 Dermatologists develop an innate sense of how melanomas appear after examining thousands of malignant and benign lesions. In contrast, most medical students are relatively disadvantaged by the paucity of their dermatology exposure. Thus, limited experience is the primary barrier to the development of pattern-recognition and intuition as a reliable tool for melanoma diagnosis in nonexperts.3 To remedy this problem, we developed a novel web-based application to mimic the training of a dermatologist by teaching medical students intuitive melanoma diagnosis in a highly condensed period of time.

Our application, Skinder, teaches intuitive visual diagnosis of melanoma by quickly presenting the learner with thousands of benign and malignant skin lesions. The user makes a rapid binary decision, by swiping right for benign or left for malignant, and receives instant feedback on accuracy. With this application, the learner can amass a mental repository of diagnostic experience in a short amount of time. To determine if intuitive visual diagnosis training is superior to a traditional rule-based algorithm, we compared our web-based application with the publicly available Internet Curriculum For Melanoma Early Detection (INFORMED) Skin Education Series.

Methods

This randomized diagnostic study was conducted on 36 medical students at a single institution. The study was approved by the West Virginia University institutional review board. All participants were financially compensated and provided written informed consent. Medical students, without a formal clinical dermatology rotation, were randomized into either the rule-based or application group. Each participant took a 32 image pretest where they were asked to determine if each lesion was a melanoma or a benign skin lesion. Participants were then given an hour of observed training time devoted to their assigned learning modality. Immediately following training, participants took a postassessment consisting of the same 32 images in randomized order to evaluate improvement. The pretest and posttest means of the 2 groups were compared using a simple t test. Participants also completed an exit questionnaire.

Results

The pretest mean for the application group was 75% correct, compared with 74.7% correct for the INFORMED group. The posttest mean for the application group was 86.3% correct, compared with 77.5% correct for the INFORMED group. The posttest mean difference between the 2 groups represents a statistically significant improvement for the web-based application group (absolute difference, 9%; P = .003) (Figure). During the 60-minute training session, application users estimated that Skinder held their attention for 34.3 minutes, which is less than the 45.6 minutes estimated by INFORMED trainees. Overall, Skinder users believed they were more likely than INFORMED users to access their learning modality again if given the opportunity (Table).

Discussion

This study reinforces the importance of visual pattern recognition in clinical diagnosis4,5 and supports the premise that intuitive diagnosis is superior to rule-based algorithms. Despite its small sample size, this study supports that Skinder is a more effective learning tool for accurate diagnosis of melanoma than traditional rule-based methods. Future studies will expand the sample size as well as investigate the use of the application beyond medical students to include primary care physicians, nurses, and patients with the goal of early recognition of skin malignant abnormalities.

Back to top
Article Information

Corresponding Author: Michael S. Kolodney, MD, PhD, Section of Dermatology, Department of Medicine, West Virginia University, Fourth Floor HSCN, Rm 4075-A, PO Box 9158, Morgantown, WV 26506 (michael.kolodney@hsc.wvu.edu).

Accepted for Publication: April 13, 2018.

Published Online: May 16, 2018. doi:10.1001/jamadermatol.2018.1525

Author Contributions: Dr Kolodney and Mr Lacy had full access to all of the data in the study and take responsibility for the integrity of the data and the accuracy of the data analysis.

Study concept and design: All authors.

Acquisition, analysis, or interpretation of data: Lacy, Kolodney.

Drafting of the manuscript: Lacy, Kolodney.

Critical revision of the manuscript for important intellectual content: All authors.

Statistical analysis: Lacy, Kolodney.

Obtained funding: Kolodney.

Administrative, technical, or material support: Coman, Kolodney.

Study supervision: Kolodney.

Conflict of Interest Disclosures: None reported.

Funding/Support: This study was supported by a Sulzberger Institute grant awarded to Dr Coman and a West Virginia University Dean’s Office Stimulus grant awarded to Dr Kolodney.

Role of the Funder/Sponsor: The Sulzberger Institute and West Virginia University had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication.

Additional Contributions: We are indebted to web developer Jeremy Lilly, BA, for his work in coding and maintaining our application, Skinder. He was compensated for his work.

References
1.
Aldridge  RB, Zanotto  M, Ballerini  L, Fisher  RB, Rees  JL.  Novice identification of melanoma: not quite as straightforward as the ABCDs.  Acta Derm Venereol. 2011;91(2):125-130. doi:10.2340/00015555-1070PubMedGoogle ScholarCrossref
2.
Girardi  S, Gaudy  C, Gouvernet  J, Teston  J, Richard  MA, Grob  JJ.  Superiority of a cognitive education with photographs over ABCD criteria in the education of the general population to the early detection of melanoma: a randomized study.  Int J Cancer. 2006;118(9):2276-2280.PubMedGoogle ScholarCrossref
3.
Aldridge  RB, Maxwell  SS, Rees  JL.  Dermatology undergraduate skin cancer training: a disconnect between recommendations, clinical exposure and competence.  BMC Med Educ. 2012;12:27. doi:10.1186/1472-6920-12-27PubMedGoogle ScholarCrossref
4.
McWhirter  JE, Hoffman-Goetz  L.  Visual images for patient skin self-examination and melanoma detection: a systematic review of published studies.  J Am Acad Dermatol. 2013;69(1):47-55. Published online March 6, 2013. doi:10.1016/j.jaad.2013.01.031PubMedGoogle ScholarCrossref
5.
Aldridge  RB, Glodzik  D, Ballerini  L, Fisher  RB, Rees  JL.  Utility of non-rule-based visual matching as a strategy to allow novices to achieve skin lesion diagnosis.  Acta Derm Venereol. 2011;91(3):279-283. doi:10.2340/00015555-1049PubMedGoogle ScholarCrossref
×