CoChat

Using artificial intelligence on dermatology conditions in Uganda: A case for diversity in training data sets for machine learning

Open access
Kamulegeya, Louis Henry, Okello, Mark, Bwanika, John Mark, Musinguzi, Davis, Lubega, William, Rusoke, Davis, Nassiwa, Faith, Börve, Alexander · 2019 · African Health Sciences

The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.

Abstract

Introduction: Artificial intelligence (AI) in healthcare has gained momentum with advances in affordable technology that has potential to help in diagnostics, predictive healthcare and personalized medicine. In pursuit of applying universal non-biased AI in healthcare, it is essential that data from different settings (gender, age and ethnicity) is represented. We present findings from beta-testing an AI-powered dermatological algorithm called Skin Image Search, by online dermatology company First Derm on Fitzpatrick 6 skin type (dark skin) dermatological conditions. Methods: 123 dermatological images selected from a total of 173 images retrospectively extracted from the electronic database of a Ugandan telehealth company, The Medical Concierge Group (TMCG) after getting their consent. Details of age, gender and dermatological clinical diagnosis were analyzed using R on R studio software to assess the diagnostic accuracy of the AI app along disease diagnosis and body part. Predictability levels of the AI app was graded on a scale of 0 to 5, where 0-no prediction made and 1-5 demonstrating reducing correct prediction. Results: 76 (62%) of the dermatological images were from females and 47 (38%) from males. The 5 most reported body parts were; genitals (20%), trunk (20%), lower limb (14.6%), face (12%) and upper limb (12%) with the AI app predicting a diagnosis in 62% of image body parts uploaded. Overall diagnostic accuracy of the AI app was low at 17% (21 out of 123 predictable images) with varying predictability levels correctness i.e. 1-8.9%, 2-2.4%, 3-2.4%, 4-1.6%, 5-1.6% with performance along individual diagnosis highest with dermatitis (80%). Conclusion: There is a need for diversity in the image datasets used when training dermatology algorithms for AI applications in clinical decision support as a means to increase accuracy and thus offer correct treatment across skin types and geographies.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1101/826057

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Illustration of the testing process of the AI app
Figure 1 Illustration of the testing process of the AI appCC BY · PubMed Central
Figure 2 Overall disease diagnostic accuracy of the AI app
Figure 2 Overall disease diagnostic accuracy of the AI appCC BY · PubMed Central
Figure 3 Diagnostic accuracy of the AI app by a body part of the dermatological image
Figure 3 Diagnostic accuracy of the AI app by a body part of the dermatological imageCC BY · PubMed Central
Figure 4 Gender comparison of the diagnostic accuracy of the AI app across dermatological clinical diagnoses
Figure 4 Gender comparison of the diagnostic accuracy of the AI app across dermatological clinical diagnosesCC BY · PubMed Central
Figure 5 Gender comparison of the diagnostic accuracy of the AI app along with body parts of the dermatological images
Figure 5 Gender comparison of the diagnostic accuracy of the AI app along with body parts of the dermatological imagesCC BY · PubMed Central

Verification

Claims the paper makes

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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 31 references

Cited by

Metadata

Authors
Kamulegeya, L. H., Okello, M., Bwanika, J. M., Musinguzi, D., Lubega, W., Rusoke, D., Nassiwa, F., & Börve, A.
Affiliations
Sahlgrenska University Hospital (SE)
Corresponding author
Kamulegeya, Louis Henry
Venue
African Health Sciences
Publisher
openRxiv
Published
2019-10-31
Volume
23
Issue
2
Pages
753-63
ISSN
1680-6905 (ISSN-L)
OpenAlex
W4387584778
Cited by
111
References
30
Citations by year
2026: 15 · 2025: 32 · 2024: 26 · 2023: 18 · 2022: 10 · 2021: 7 · 2020: 3
FWCI
3.63
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • African Health Sciences (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
dermatology, artificial intelligence, Fitzpatrick skin type, dark skin, training data diversity, algorithmic bias, diagnostic accuracy, telemedicine, Uganda, skin inflammation
MeSH terms
Machine Learning, Artificial Intelligence, Dermatology, Female, Humans, Male, Retrospective Studies, Uganda

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.