AI-based smartphone apps for risk assessment of skin cancer need more evaluation and better regulation

Rubeta N Matin; Jacqueline Dinnes

doi:10.1038/s41416-021-01302-3

AI-based smartphone apps for risk assessment of skin cancer need more evaluation and better regulation

Br J Cancer. 2021 May;124(11):1749-1750. doi: 10.1038/s41416-021-01302-3. Epub 2021 Mar 19.

Authors

Rubeta N Matin¹, Jacqueline Dinnes^{2

3}

Affiliations

¹ Department of Dermatology, Oxford University Hospitals NHS Foundation Trust, Oxford, UK.
² Test Evaluation Research Group, Institute of Applied Health Research, University of Birmingham, Edgbaston, Birmingham, UK. j.dinnes@bham.ac.uk.
³ NIHR Birmingham Biomedical Research Centre, University Hospitals Birmingham NHS Foundation Trust and University of Birmingham, Birmingham, UK. j.dinnes@bham.ac.uk.

Abstract

Smartphone applications ("apps") with artificial intelligence (AI) algorithms are increasingly used in healthcare. Widespread adoption of these apps must be supported by a robust evidence-base and app manufacturers' claims appropriately regulated. Current CE marking assessment processes inadequately protect the public against the risks created by using smartphone diagnostic apps.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adult
Algorithms
Artificial Intelligence* / legislation & jurisprudence
Artificial Intelligence* / standards
Diagnostic Test Approval* / legislation & jurisprudence
Diagnostic Test Approval* / standards
Early Detection of Cancer / instrumentation
Early Detection of Cancer / methods
Early Detection of Cancer / standards
Europe
European Union
Evidence-Based Medicine
Humans
Mobile Applications* / legislation & jurisprudence
Mobile Applications* / standards
Precancerous Conditions / diagnosis
Risk Assessment
Sensitivity and Specificity
Skin Neoplasms / diagnosis*
Skin Neoplasms / etiology
Skin Neoplasms / pathology
Smartphone / legislation & jurisprudence
Smartphone / standards
United States
United States Food and Drug Administration