Diagnostic Inaccuracy of Smartphone Applications for Melanoma Detection | Dermatology | JAMA Dermatology | JAMA Network
[Skip to Navigation]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address Please contact the publisher to request reinstatement.
Brady MS, Oliveria SA, Christos PJ,  et al.  Patterns of detection in patients with cutaneous melanoma.  Cancer. 2000;89(2):342-34710918164PubMedGoogle ScholarCrossref
Epstein DS, Lange JR, Gruber SB, Mofid M, Koch SE. Is physician detection associated with thinner melanomas?  JAMA. 1999;281(7):640-64310029126PubMedGoogle ScholarCrossref
Kantor J, Kantor DE. Routine dermatologist-performed full-body skin examination and early melanoma detection.  Arch Dermatol. 2009;145(8):873-87619687416PubMedGoogle ScholarCrossref
McGuire ST, Secrest AM, Andrulonis R, Ferris LK. Surveillance of patients for early detection of melanoma: patterns in dermatologist vs patient discovery.  Arch Dermatol. 2011;147(6):673-67821690529PubMedGoogle ScholarCrossref
Morris DP. Health-care apps for smartphones pit FDA against tech industry. Washington Post. June 22, 2012.http://www.washingtonpost.com/business/economy/health-care-apps-for-smartphones-pit-fda-against-tech-industry/2012/06/22/gJQAHCcBvV_story_2.html. Accessed August 25, 2012
Senior K. Smart phones: new clinical tools in oncology?  Lancet Oncol. 2011;12(5):429-43021536224PubMedGoogle ScholarCrossref
De Leo G, Brivio E, Sautter SW. Supporting autobiographical memory in patients with Alzheimer's disease using smart phones.  Appl Neuropsychol. 2011;18(1):69-7621390903PubMedGoogle ScholarCrossref
Low D, Clark N, Soar J,  et al.  A randomised control trial to determine if use of the iResus© application on a smart phone improves the performance of an advanced life support provider in a simulated medical emergency.  Anaesthesia. 2011;66(4):255-262Google ScholarCrossref
Ciemins E, Coon P, Sorli C. An analysis of data management tools for diabetes self-management: can smart phone technology keep up?  J Diabetes Sci Technol. 2010;4(4):958-96020663462PubMedGoogle Scholar
US Food and Drug Administration.  FDA outlines oversight of mobile medical applications. FDA news release. July 19, 2011. http://www.fda.gov/NewsEvents/Newsroom/PressAnnouncements/ucm263340.htm. Accessed August 25, 2012
US Food and Drug Administration.  FDA Safety and Innovation Act. Updated July 31, 2012. http://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/Overview/ucm310927.htm. Accessed August 25, 2012
Federal Trade Commission.   “Acne cure” mobile app marketers will drop baseless claims under FTC settlements. Released September 8, 2011. http://www.ftc.gov/opa/2011/09/acnecure.shtm. Accessed August 25, 2012
April 2013

Diagnostic Inaccuracy of Smartphone Applications for Melanoma Detection

Author Affiliations

Author Affiliations: Department of Dermatology, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania (Drs Akilov, Patton, English, Ho, and Ferris). Mr Wolf and Ms Moreau are medical students at the University of Pittsburgh, Pittsburgh, Pennsylvania.

JAMA Dermatol. 2013;149(4):422-426. doi:10.1001/jamadermatol.2013.2382

Objective To measure the performance of smartphone applications that evaluate photographs of skin lesions and provide the user with feedback about the likelihood of malignancy.

Design Case-control diagnostic accuracy study.

Setting Academic dermatology department.

Participants and Materials Digital clinical images of pigmented cutaneous lesions (60 melanoma and 128 benign control lesions) with a histologic diagnosis rendered by a board-certified dermatopathologist, obtained before biopsy from patients undergoing lesion removal as a part of routine care.

Main Outcome Measures Sensitivity, specificity, and positive and negative predictive values of 4 smartphone applications designed to aid nonclinician users in determining whether their skin lesion is benign or malignant.

Results Sensitivity of the 4 tested applications ranged from 6.8% to 98.1%; specificity, 30.4% to 93.7%; positive predictive value, 33.3% to 42.1%; and negative predictive value, 65.4% to 97.0%. The highest sensitivity for melanoma diagnosis was observed for an application that sends the image directly to a board-certified dermatologist for analysis; the lowest, for applications that use automated algorithms to analyze images.

Conclusions The performance of smartphone applications in assessing melanoma risk is highly variable, and 3 of 4 smartphone applications incorrectly classified 30% or more of melanomas as unconcerning. Reliance on these applications, which are not subject to regulatory oversight, in lieu of medical consultation can delay the diagnosis of melanoma and harm users.