Title :
Mobile Medical Applications for Melanoma Risk Assessment: False Assurance or Valuable Tool?
Author :
Chadwick, Xavier ; Loescher, Lois J. ; Janda, Marcel ; Soyer, H. Peter
Author_Institution :
Dermatology Res. Centre Sch. of Med., Univ. of Queensland, Brisbane, QLD, Australia
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.
Keywords :
cancer; medical computing; mobile computing; patient diagnosis; risk analysis; skin; smart phones; telemedicine; automated risk analysis; false assurance; melanoma; melanoma risk assessment; mobile medical applications; recommendation scale; regular dermatologist evaluation; skin cancer; skin lesions diagnosis; smartphone; Lesions; Malignant tumors; Medical diagnostic imaging; Mobile communication; Skin; Skin cancer; Mobile apps; melanoma; skin lesion analysis;
Conference_Titel :
System Sciences (HICSS), 2014 47th Hawaii International Conference on
Conference_Location :
Waikoloa, HI
DOI :
10.1109/HICSS.2014.337