Skin cancers occur commonly worldwide. The prognosis and disease burden are highly dependent on the cancer type and disease stage at diagnosis. We systematically reviewed studies on artificial intelligence and machine learning (AI/ML) algorithms that aim to facilitate the early diagnosis of skin cancers, focusing on their application in primary and community care settings. We searched MEDLINE, Embase, Scopus, and Web of Science (from Jan 1, 2000, to Aug 9, 2021) for all studies providing evidence on applying AI/ML algorithms to the early diagnosis of skin cancer, including all study designs and languages. The primary outcome was diagnostic accuracy of the algorithms for skin cancers. The secondary outcomes included an overview of AI/ML methods, evaluation approaches, cost-effectiveness, and acceptability to patients and clinicians. We identified 14?224 studies. Only two studies used data from clinical settings with a low prevalence of skin cancers. We reported data from all 272 studies that could be relevant in primary care. The primary outcomes showed reasonable mean diagnostic accuracy for melanoma (89·5% [range 59·7?100%]), squamous cell carcinoma (85·3% [71·0?97·8%]), and basal cell carcinoma (87·6% [70·0?99·7%]). The secondary outcomes showed a heterogeneity of AI/ML methods and study designs, with high amounts of incomplete reporting (eg, patient demographics and methods of data collection). Few studies used data on populations with a low prevalence of skin cancers to train and test their algorithms; therefore, the widespread adoption into community and primary care practice cannot currently be recommended until efficacy in these populations is shown. We did not identify any health economic, patient, or clinician acceptability data for any of the included studies. We propose a methodological checklist for use in the development of new AI/ML algorithms to detect skin cancer, to facilitate their design, evaluation, and implementation.
This systematic review was funded by the National Institute for Health Research Policy Research Programme, conducted through the Policy Research Unit in Cancer Awareness, Screening, and Early Diagnosis (PR-PRU-1217–21601). The views expressed in this publication are those of the authors and not necessarily those of the National Health Service, the NIHR or the Department of Health and Social Care. The first author (OTJ) was also supported by the CanTest Collaborative funded by Cancer Research UK (C8640/A23385), of which FMW is Director, JE is an Associate Director, and NC is Research Fellow. During protocol development, this Review benefited from the advice of an international expert panel from the CanTest collaborative, including Willie Hamilton (University of Exeter, Exeter, UK), Greg Rubin (University of Newcastle, Newcastle, UK), Hardeep Singh (Baylor College of Medicine, Houston, TX, USA), and Niek de Wit (University Medical Center Utrecht, Utrecht, Netherlands). The research was also supported by a Cancer Research UK Cambridge Centre Clinical Research Fellowship for OTJ, and a National Health and Medical Research Council Investigator Fellowship (APP1195302) for JE. The funding sources had no role in the study design, data collection, data analysis, data interpretation, writing of the report, or in the decision to submit for publication. The authors would like to thank Isla Kuhn (Reader Services Librarian, University of Cambridge Medical Library, Cambridge, UK) for her help in developing the search strategy. We also thank Smiji Saji, who assisted with the early stages of the Review, Haruyuki Yanaoka, who assisted with the translation and assessment of papers that were written in Korean, and Steve Morris who assisted with the analysis of the data.