Mobile medical applications for melanoma risk assessment: False assurance or valuable tool?

Xavier Chadwick, Lois J. Loescher, Monika Janda, H. Peter Soyer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Scopus citations

Abstract

With the smartphone revolution, consumer-focused mobile medical applications (apps) have flooded the market without restriction. We searched the market for commercially available apps on all mobile platforms that could provide automated risk analysis of the most serious skin cancer, melanoma. We tested 5 relevant apps against 15 images of previously excised skin lesions and compared the apps' risk grades to the known histopathologic diagnosis of the lesions. Two of the apps did not identify any of the melanomas. The remaining 3 apps obtained 80% sensitivity for melanoma risk identification; specificities for the 5 apps ranged from 20%-100%. Each app provided its own grading and recommendation scale and included a disclaimer recommending regular dermatologist evaluation regardless of the analysis outcome. The results indicate that autonomous lesion analysis is not yet ready for use as a triage tool. More concerning is the lack of restrictions and regulations for these applications.

Original languageEnglish (US)
Title of host publicationProceedings of the 47th Annual Hawaii International Conference on System Sciences, HICSS 2014
PublisherIEEE Computer Society
Pages2675-2684
Number of pages10
ISBN (Print)9781479925049
DOIs
StatePublished - 2014
Event47th Hawaii International Conference on System Sciences, HICSS 2014 - Waikoloa, HI, United States
Duration: Jan 6 2014Jan 9 2014

Publication series

NameProceedings of the Annual Hawaii International Conference on System Sciences
ISSN (Print)1530-1605

Other

Other47th Hawaii International Conference on System Sciences, HICSS 2014
Country/TerritoryUnited States
CityWaikoloa, HI
Period1/6/141/9/14

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Mobile medical applications for melanoma risk assessment: False assurance or valuable tool?'. Together they form a unique fingerprint.

Cite this