Using artificial intelligence on dermatology conditions in Uganda: a case for diversity in training data sets for machine learning
| dc.contributor.author | Louis Kamulegeya | |
| dc.contributor.author | John Bwanika | |
| dc.contributor.author | Mark Okello | |
| dc.contributor.author | Davis Rusoke | |
| dc.contributor.author | Faith Nassiwa | |
| dc.contributor.author | William Lubega | |
| dc.contributor.author | Davis Musinguzi | |
| dc.contributor.author | Alexander Börve | |
| dc.date.accessioned | 2026-11-18T07:10:25Z | |
| dc.date.issued | 2023 | |
| dc.description | Official PMC article XML states CC BY 4.0 and permits use, sharing, adaptation, distribution and reproduction with attribution. Rights classification: FULL_TEXT_OK. Licence verified from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10782289/ (checked 2026-11-18). Source: The Medical Concierge Group, Research and Projects; The Medical Concierge Group, Information and Technology; Sahlgrenska University Hospital, Departments of Orthopaedics African relevance: Sector: Healthcare. Ugandan telehealth data used to test dermatology AI on Fitzpatrick type 6 skin, documenting African dataset gaps in clinical AI. Official PMC article XML states CC BY 4.0 and permits use, sharing, adaptation, distribution and reproduction with attribution. | |
| dc.description.abstract | BackgroundIn pursuit of applying universal non-biased Artificial Intelligence (AI) in healthcare, it is essential that data from different geographies are represented.ObjectiveTo assess the diagnostic performance of an AI-powered dermatological algorithm called Skin Image Search on Fitzpatrick 6 skin type (dark skin) dermatological conditions.Methods123 dermatological images selected from a total of 173 images were 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 analysed using R on R studio software to assess the diagnostic accuracy of the AI app along with disease diagnosis and body part. Predictability levels of the AI app were graded on a scale of 0 to 5, where 0- no prediction was made and 1-5 demonstrated a reduction incorrect diagnosis prediction rate of the AI.Results76 (62%) of the dermatological images were from females and 47 (38%) from males. Overall diagnostic accuracy of the AI app on black dermatological conditions was low at 17% (21 out of 123 predictable images) compared to 69.9% performance on Caucasian skin type as reported from the training results. There were 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%).ConclusionThere is need for diversity of image datasets used to train dermatology algorithms for AI applications to increase accuracy across skin types and geographies. | |
| dc.identifier.doi | 10.4314/ahs.v23i2.86 | |
| dc.identifier.uri | https://doi.org/10.4314/ahs.v23i2.86 | |
| dc.identifier.uri | https://library.dare.co.zw/handle/123456789/5089 | |
| dc.language.iso | en | |
| dc.publisher | Makerere University Medical School | |
| dc.rights | CC BY 4.0. Licence evidence: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10782289/. Official PMC article XML states CC BY 4.0 and permits use, sharing, adaptation, distribution and reproduction with attribution. | |
| dc.rights.holder | Named authors | |
| dc.rights.license | CC BY 4.0 | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.source | The Medical Concierge Group, Research and Projects; The Medical Concierge Group, Information and Technology; Sahlgrenska University Hospital, Departments of Orthopaedics | |
| dc.source.uri | https://doi.org/10.4314/ahs.v23i2.86 | |
| dc.subject | Healthcare | |
| dc.subject | Artificial intelligence | |
| dc.subject | Dermatology | |
| dc.subject | Fitzpatrick 6 skin type | |
| dc.subject | Telehealth | |
| dc.subject | Algorithms | |
| dc.subject | African Health Sciences | |
| dc.title | Using artificial intelligence on dermatology conditions in Uganda: a case for diversity in training data sets for machine learning | |
| dc.type | journal article |