Shannon Wongvibulsin, Matthew J Yan, Vartan Pahalyants, William Murphy, Roxana Daneshjou, Veronica Rotemberg
{"title":"Current State of Dermatology Mobile Applications With Artificial Intelligence Features.","authors":"Shannon Wongvibulsin, Matthew J Yan, Vartan Pahalyants, William Murphy, Roxana Daneshjou, Veronica Rotemberg","doi":"10.1001/jamadermatol.2024.0468","DOIUrl":null,"url":null,"abstract":"<p><strong>Importance: </strong>With advancements in mobile technology and artificial intelligence (AI) methods, there has been a substantial surge in the availability of direct-to-consumer mobile applications (apps) claiming to aid in the assessment and management of diverse skin conditions. Despite widespread patient downloads, these apps exhibit limited evidence supporting their efficacy.</p><p><strong>Objective: </strong>To identify and characterize current English-language AI dermatology mobile apps available for download, focusing on aspects such as purpose, supporting evidence, regulatory status, clinician input, data privacy measures, and use of image data.</p><p><strong>Evidence review: </strong>In this cross-sectional study, both Apple and Android mobile app stores were systematically searched for dermatology-related apps that use AI algorithms. Each app's purpose, target audience, evidence-based claims, algorithm details, data availability, clinician input during development, and data usage privacy policies were evaluated.</p><p><strong>Findings: </strong>A total of 909 apps were initially identified. Following the removal of 518 duplicates, 391 apps remained. Subsequent review excluded 350 apps due to nonmedical nature, non-English languages, absence of AI features, or unavailability, ultimately leaving 41 apps for detailed analysis. The findings revealed several concerning aspects of the current landscape of AI apps in dermatology. Notably, none of the apps were approved by the US Food and Drug Administration, and only 2 of the apps included disclaimers for the lack of regulatory approval. Overall, the study found that these apps lack supporting evidence, input from clinicians and/or dermatologists, and transparency in algorithm development, data usage, and user privacy.</p><p><strong>Conclusions and relevance: </strong>This cross-sectional study determined that although AI dermatology mobile apps hold promise for improving access to care and patient outcomes, in their current state, they may pose harm due to potential risks, lack of consistent validation, and misleading user communication. Addressing challenges in efficacy, safety, and transparency through effective regulation, validation, and standardized evaluation criteria is essential to harness the benefits of these apps while minimizing risks.</p>","PeriodicalId":14734,"journal":{"name":"JAMA dermatology","volume":null,"pages":null},"PeriodicalIF":11.5000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10921342/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JAMA dermatology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1001/jamadermatol.2024.0468","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"DERMATOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Importance: With advancements in mobile technology and artificial intelligence (AI) methods, there has been a substantial surge in the availability of direct-to-consumer mobile applications (apps) claiming to aid in the assessment and management of diverse skin conditions. Despite widespread patient downloads, these apps exhibit limited evidence supporting their efficacy.
Objective: To identify and characterize current English-language AI dermatology mobile apps available for download, focusing on aspects such as purpose, supporting evidence, regulatory status, clinician input, data privacy measures, and use of image data.
Evidence review: In this cross-sectional study, both Apple and Android mobile app stores were systematically searched for dermatology-related apps that use AI algorithms. Each app's purpose, target audience, evidence-based claims, algorithm details, data availability, clinician input during development, and data usage privacy policies were evaluated.
Findings: A total of 909 apps were initially identified. Following the removal of 518 duplicates, 391 apps remained. Subsequent review excluded 350 apps due to nonmedical nature, non-English languages, absence of AI features, or unavailability, ultimately leaving 41 apps for detailed analysis. The findings revealed several concerning aspects of the current landscape of AI apps in dermatology. Notably, none of the apps were approved by the US Food and Drug Administration, and only 2 of the apps included disclaimers for the lack of regulatory approval. Overall, the study found that these apps lack supporting evidence, input from clinicians and/or dermatologists, and transparency in algorithm development, data usage, and user privacy.
Conclusions and relevance: This cross-sectional study determined that although AI dermatology mobile apps hold promise for improving access to care and patient outcomes, in their current state, they may pose harm due to potential risks, lack of consistent validation, and misleading user communication. Addressing challenges in efficacy, safety, and transparency through effective regulation, validation, and standardized evaluation criteria is essential to harness the benefits of these apps while minimizing risks.
期刊介绍:
JAMA Dermatology is an international peer-reviewed journal that has been in continuous publication since 1882. It began publication by the American Medical Association in 1920 as Archives of Dermatology and Syphilology. The journal publishes material that helps in the development and testing of the effectiveness of diagnosis and treatment in medical and surgical dermatology, pediatric and geriatric dermatology, and oncologic and aesthetic dermatologic surgery.
JAMA Dermatology is a member of the JAMA Network, a consortium of peer-reviewed, general medical and specialty publications. It is published online weekly, every Wednesday, and in 12 print/online issues a year. The mission of the journal is to elevate the art and science of health and diseases of skin, hair, nails, and mucous membranes, and their treatment, with the aim of enabling dermatologists to deliver evidence-based, high-value medical and surgical dermatologic care.
The journal publishes a broad range of innovative studies and trials that shift research and clinical practice paradigms, expand the understanding of the burden of dermatologic diseases and key outcomes, improve the practice of dermatology, and ensure equitable care to all patients. It also features research and opinion examining ethical, moral, socioeconomic, educational, and political issues relevant to dermatologists, aiming to enable ongoing improvement to the workforce, scope of practice, and the training of future dermatologists.
JAMA Dermatology aims to be a leader in developing initiatives to improve diversity, equity, and inclusion within the specialty and within dermatology medical publishing.