Early Recognition of Malignant Skin Lesions Through Smartphone Application
Posted: Wednesday, September 12, 2018
Honing intuitive pattern-recognition skills may prove to be a more meaningful learning method for accurately diagnosing malignant skin abnormalities over traditional, rule-based approaches. Michael S. Kolodney, MD, PhD, of West Virginia University, Morgantown, and colleagues from Utah and Virginia tested the use of a novel Web-based application, Skinder, shared their findings in research letter in JAMA Dermatology.
“Our application, Skinder, teaches intuitive visual diagnosis of melanoma by quickly presenting the learner with thousands of benign and malignant skin lesions,” explained the researchers. It provides immediate feedback on accuracy as users swipe right for nonmelanoma or left for melanoma. “With this application, the learner can amass a mental repository of diagnostic experience in a short amount of time.”
A total of 36 medical students were randomly assigned to either the rule-based Internet Curriculum for Melanoma Early Detection (INFORMED) Skin Education Series group or the Skinder group. Each participant underwent a 32-image pretest, an hour-long training dependent on their assigned group, and a 32-image posttest. Whereas the mean scores from the preassessment and the postassessment of the rule-based INFORMED group slightly increased from 74.7% to 77.5%, those of the Skinder group improved from 75% to 86.3%.
For future studies, the researchers plan to incorporate larger sample sizes and expand the use of the application to include other health-care professionals and patients.