Smartphone App Effectively Teaches Visual Diagnosis of Melanoma
Intuitive diagnosis may be more effective than rule-based algorithms.
A smartphone application called Skinder is a more effective learning tool for accurately diagnosing melanoma than traditional, rule-based methods, according to results published in JAMA Dermatology.
These results support the premise that intuitive diagnosis is more effective than the use of rule-based algorithms.
Skinder is an application that presents the user with thousands of benign and malignant skin lesions. The user swipes right for benign or left for malignant and the application provides instant feedback on accuracy.
The study included medical students from a single institution (n=36) who were randomly assigned to either a rule-based or application group. Each participant took a 32-image pretest, determining whether each lesion was a melanoma or was benign.
After the pretest, participants were given an hour of observed training time. Immediately after training, participants took a posttest that consisted of the same 32 images from the pretest in a randomized order.
The mean pretest scores were 75% for the application group and 74.7% for the rule-based group. After training, the mean posttest score for the application group was 86.3%, compared with 77.5% for the rule-based group.
“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,” the researchers wrote.
Lacy FA, Coman GC, Holliday AC, Kolodney MS. Assessment of smartphone application for teaching intuitive visual diagnosis of melanoma [published online May 16, 2018]. JAMA Dermatol. doi:10.1001/jamadermatol.2018.1525