CoChat
Sign Up
Cited by 119Cutaneous Melanoma Detection and ManagementDermatology and Skin DiseasesArtificial Intelligence in Healthcare and Education

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Systematic review of deep learning image analyses for the diagnosis and monitoring of skin disease

Open access
Choy, Shern Ping, Kim, Byung Jin, Paolino, Alexandra, Tan, Wei Ren, Lim, Sarah Man Lin, Seo, Jessica, Tan, Sze Ping, Francis, Luc, Tsakok, Teresa, Simpson, Michael, Barker, Jonathan N. W. N., Lynch, Magnus D., Corbett, Mark S., Smith, Catherine H., Mahil, Satveer K.·2023·npj Digital Medicine
DOI 10.1038/s41746-023-00914-8PMC PMC10533565
Open this paper in CoChat — free accountOpen PDF

Abstract

Skin diseases affect one-third of the global population, posing a major healthcare burden. Deep learning may optimise healthcare workflows through processing skin images via neural networks to make predictions. A focus of deep learning research is skin lesion triage to detect cancer, but this may not translate to the wider scope of >2000 other skin diseases. We searched for studies applying deep learning to skin images, excluding benign/malignant lesions (1/1/2000-23/6/2022, PROSPERO CRD42022309935). The primary outcome was accuracy of deep learning algorithms in disease diagnosis or severity assessment. We modified QUADAS-2 for quality assessment. Of 13,857 references identified, 64 were included. The most studied diseases were acne, psoriasis, eczema, rosacea, vitiligo, urticaria. Deep learning algorithms had high specificity and variable sensitivity in diagnosing these conditions. Accuracy of algorithms in diagnosing acne (median 94%, IQR 86-98; n = 11), rosacea (94%, 90-97; n = 4), eczema (93%, 90-99; n = 9) and psoriasis (89%, 78-92; n = 8) was high. Accuracy for grading severity was highest for psoriasis (range 93-100%, n = 2), eczema (88%, n = 1), and acne (67-86%, n = 4). However, 59 (92%) studies had high risk-of-bias judgements and 62 (97%) had high-level applicability concerns. Only 12 (19%) reported participant ethnicity/skin type. Twenty-four (37.5%) evaluated the algorithm in an independent dataset, clinical setting or prospectively. These data indicate potential of deep learning image analysis in diagnosing and monitoring common skin diseases. Current research has important methodological/reporting limitations. Real-world, prospectively-acquired image datasets with external validation/testing will advance deep learning beyond the current experimental phase towards clinically-useful tools to mitigate rising health and cost impacts of skin disease.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-023-00914-8

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 PRISMA flowchart of study records. PRISMA flowchart showing the study selection process.
Fig. 1 PRISMA flowchart of study records. PRISMA flowchart showing the study selection process.CC BY · PubMed Central
Fig. 2 Summary of quality assessment results of all studies (using modified QUADAS-2). Quality assessment of all included studies.
Fig. 2 Summary of quality assessment results of all studies (using modified QUADAS-2). Quality assessment of all included studies.CC BY · PubMed Central
Fig. 3 Type of deep learning algorithms included in the systematic review, by year of publication. The number of different types of deep learning (DL) algorithms are presented by year of publication of the studies. As five studies used multiple DL algorithms, the total number of algorithms sum to 69 across the 64 included studies.
Fig. 3 Type of deep learning algorithms included in the systematic review, by year of publication. The number of different types of deep learning (DL) algorithms are presented by year of publication of the studies. As five studies used multiple DL algorithms, the total number of algorithms sum to 69 across the 64 included studies.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 29 references

Research works printed but not linked: 1

  1. Page M. J. H. J. & Sterne J. A. C. Chapter 13: Assessing risk of bias due to missing results in a synthesis. in Cochrane Handbook for Systematic Reviews of Interventions version 63 (updated February 2022) Ch. 13 (Cochrane, 2022).

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Choy, S. P., Kim, B. J., Paolino, A., Tan, W. R., Lim, S. M. L., Seo, J., Tan, S. P., Francis, L., Tsakok, T., Simpson, M., Barker, J. N. W. N., Lynch, M. D., Corbett, M. S., Smith, C. H., & Mahil, S. K.
Affiliations
  • King's College London (GB)
  • St George’s University Hospitals NHS Foundation Trust (GB)
  • Maidstone and Tunbridge Wells NHS Trust (GB)
  • Imperial College London (GB)
  • Barking, Havering And Redbridge University Hospitals NHS Trust (GB)
  • University of York (GB)
Corresponding author
Mahil, Satveer K.
ORCID
Venue
npj Digital Medicine
Publisher
Springer Science and Business Media LLC
Published
2023-09-27
Volume
6
Issue
1
Pages
180-180
ISSN
2398-6352 (ISSN-L)
DOI
10.1038/s41746-023-00914-8
PMC
PMC10533565
OpenAlex
W4387104519
Cited by
105
References
29
Citations by year
2026: 35 · 2025: 43 · 2024: 25 · 2023: 2
FWCI
3.40
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (acceptedVersion, public-domain)
  • Research Portal (King's College London) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • DH | National Institute for Health Research (NIHR302258)
  • Psoriasis Association (PhD Studentship)
  • RCUK | Medical Research Council ([MR/R001839/1])
Topics
  • Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
  • Health Sciences › Medicine › Dermatology › Dermatology and Skin Diseases
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
deep learning, dermatological diagnosis, skin lesion image analysis, acne, psoriasis, atopic dermatitis, rosacea, vitiligo, urticaria, disease severity classification, diagnostic accuracy, risk of bias, external validation, skin type, dermatology

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review