Using artificial intelligence on dermatology conditions in Uganda: A case for diversity in training data sets for machine learning
Open accessThe 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.
Integrity signals
Registry
Cites
Statistics
Figures





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.
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?
The cited source says what the claim attributes to it.
In the citing paper
“AIs trained primarily on lighter skin tones may not generalize as well when tested on darker skin157 .”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [157]
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
Hay, R. J., Johns, N. E., Williams, H. C., Bolliger, I. W., Dellavalle, R. P., Margolis, D. J., Marks, R., Naldi, L., Weinstock, M. A., Wulf, S. K., et al. (2014) · Journal of Investigative Dermatology · doi:10.1038/jid.2013.446 · Cited by 1,706
Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data
Gianfrancesco, M. A., Tamang, S., Yazdany, J., & Schmajuk, G. (2018) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2018.3763 · Cited by 1,395
Findings from the Global Burden of Disease Study 2021
Murray, C. J. L. (2024) · The Lancet · doi:10.1016/s0140-6736(24)00769-4 · Cited by 1,057
A comprehensive review on automation in agriculture using artificial intelligence
Jha, K., Doshi, A., Patel, P., & Shah, M. (2019) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2019.05.004 · Cited by 1,005
Feasey, N., Wansbrough-Jones, M., Mabey, D. C. W., & Solomon, A. W. (2010) · British Medical Bulletin · doi:10.1093/bmb/ldp046 · Cited by 817
Letting Artificial Intelligence in Education Out of the Box: Educational Cobots and Smart Classrooms
Timms, M. J. (2016) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-016-0095-y · Cited by 428
Global Burden of Skin Disease: Inequities and Innovations
Seth, D., Cheldize, K., Brown, D., & Freeman, E. E. (2017) · Current Dermatology Reports · doi:10.1007/s13671-017-0192-7 · Cited by 366
The Ugly Truth About Ourselves and Our Robot Creations: The Problem of Bias and Social Inequity
Howard, A., & Borenstein, J. (2018) · Science and Engineering Ethics · doi:10.1007/s11948-017-9975-2 · Cited by 337
Marchetti, M. A., Codella, N. C. F., Dusza, S. W., Gutman, D. A., Helba, B., Kalloo, A., Mishra, N., Carrera, C., Celebi, M. E., DeFazio, J. L., et al. (2018) · Journal of the American Academy of Dermatology · doi:10.1016/j.jaad.2017.08.016 · Cited by 330
Artificial Intelligence in Pathology
Chang, H. Y., Jung, C. K., Woo, J. I., Lee, S., Cho, J., Kim, S. W., & Kwak, T.-Y. (2019) · Journal of Pathology and Translational Medicine · doi:10.4132/jptm.2018.12.16 · Cited by 246
Cited by
Deep learning-enabled medical computer vision
Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., Mottaghi, A., Liu, Y., Topol, E., Dean, J., & Socher, R. (2021) · npj Digital Medicine · doi:10.1038/s41746-020-00376-2 · Cited by 1,406
Addressing bias in big data and AI for health care: A call for open science
Norori, N., Hu, Q., Aellen, F. M., Faraci, F. D., & Tzovara, A. (2021) · Patterns · doi:10.1016/j.patter.2021.100347 · Cited by 903
Timmons, A. C., Duong, J. B., Simo Fiallo, N., Lee, T., Vo, H. P. Q., Ahle, M. W., Comer, J. S., Brewer, L. C., Frazier, S. L., & Chaspari, T. (2023) · Perspectives on Psychological Science · doi:10.1177/17456916221134490 · Cited by 263
“In another example, Kamulegeya et al. (2019) found that an algorithm used to diagnose skin conditions, built on a primarily non-Hispanic White sample, performed far below acceptable levels when applied to people with other skin tones.”
BackgroundOlczak, J., Pavlopoulos, J., Prijs, J., Ijpma, F. F. A., Doornberg, J. N., Lundström, C., Hedlund, J., & Gordon, M. (2021) · Acta Orthopaedica · doi:10.1080/17453674.2021.1918389 · Cited by 127
“For example, a skin cancer detector trained on a dataset dominated by fair skin can have problems detecting melanoma in dark-skinned patients (Adamson and Smith 2018, Kamulegeya et al. 2019).”
BackgroundJayakumar, S., Sounderajah, V., Normahani, P., Harling, L., Markar, S. R., Ashrafian, H., & Darzi, A. (2022) · npj Digital Medicine · doi:10.1038/s41746-021-00544-y · Cited by 110
The Sociodemographic Biases in Machine Learning Algorithms: A Biomedical Informatics Perspective
Franklin, G., Stephens, R., Piracha, M., Tiosano, S., Lehouillier, F., Koppel, R., & Elkin, P. (2024) · Life · doi:10.3390/life14060652 · Cited by 76
“Generally, the data used for training deep convolutional neural networks (DCNNs) are biased towards datasets of individuals of predominantly Western European and Asian descent [54,55].”
BackgroundMethodInfluentialEscalé-Besa, A., Yélamos, O., Vidal-Alaball, J., Fuster-Casanovas, A., Miró Catalina, Q., Börve, A., Ander-Egg Aguilar, R., Fustà-Novell, X., Cubiró, X., Rafat, M. E., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-31340-1 · Cited by 70
Self-citationIacucci, M., Santacroce, G., Zammarchi, I., Maeda, Y., Del Amor, R., Meseguer, P., Kolawole, B. B., Chaudhari, U., Di Sabatino, A., Danese, S., et al. (2024) · The Lancet Gastroenterology & Hepatology · doi:10.1016/s2468-1253(24)00053-0 · Cited by 73
Artificial intelligence in dermatology: advancements and challenges in skin of color
Fliorent, R., Fardman, B., Podwójniak, A., Javaid, K., Tan, I. J., Ghani, H., Truong, T. M., Rao, B. K., & Heath, C. R. (2024) · International Journal of Dermatology · doi:10.1111/ijd.17076 · Cited by 89
Boyd, K., & Andalibi, N. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579528 · Cited by 88
“For example, it is well-established that training data sets do not include sufficient data on Black Americans’ faces, speech, or text [22, 40, 45, 65, 81].”
BackgroundThe Algorithmic Divide: A Systematic Review on AI-Driven Racial Disparities in Healthcare
Haider, S. A., Borna, S., Gomez-Cabello, C. A., Pressman, S. M., Haider, C. R., & Forte, A. J. (2024) · Journal of Racial and Ethnic Health Disparities · doi:10.1007/s40615-024-02237-0 · Cited by 92
“…used in the various AI algorithms represented a diverse range of racial backgrounds, including Black, Hispanic, Caucasian, and Asian individuals, with evidence indicating that Black people experienced the highest levels of discrimination due to the use of AI [34, 39, 40, 43, 46, 48–50, 56, 59, 64].”
Making decisions: Bias in artificial intelligence and data‑driven diagnostic tools
Aquino, Y. S. J. (2023) · Australian Journal of General Practice · doi:10.31128/ajgp-12-22-6630 · Cited by 58
Kaur, D., Hughes, J. W., Rogers, A. J., Kang, G., Narayan, S. M., Ashley, E. A., & Perez, M. V. (2024) · Circulation: Heart Failure · doi:10.1161/circheartfailure.123.010879 · Cited by 58
“19 On the contrary, there have been cases of machine learning algorithms producing less biased results in comparison to other scoring meth-ods.”
ResultMachine Learning Research Trends in Africa: A 30 Years Overview with Bibliometric Analysis Review
Ezugwu, A. E.-S., Oyelade, O. N., Ikotun, A. M., Agushaka, J. O., & Ho, Y. (2023) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-09930-z · Cited by 67
“The algorithm was trained using a local dataset from The Medical Concierge Group (TMCG) to diagnostically analyze and extract the gender, age and dermatological diagnosis [26].”
MethodIacucci, M., Santacroce, G., Maeda, Y., & Ghosh, S. (2025) · Gastroenterology · doi:10.1053/j.gastro.2025.03.005 · Cited by 56
AI-Enhanced Healthcare: Not a new Paradigm for Informed Consent
Pruski, M. (2024) · Journal of Bioethical Inquiry · doi:10.1007/s11673-023-10320-0 · Cited by 52
Lucius, M., De All, J., De All, J. A., Belvisi, M., Radizza, L., Lanfranconi, M., Lorenzatti, V., & Galmarini, C. M. (2020) · Diagnostics · doi:10.3390/diagnostics10110969 · Cited by 40
“Indeed, it was recently reported that a DNN trained on an image dataset composed mainly of Caucasian population skin images (Fitzpatrick 1 and 2 skin types) could not be extrapolated to African-black skin color patients [52].”
BackgroundFungal Skin Disease Classification Using the Convolutional Neural Network
Nigat, T. D., Sitote, T. M., & Gedefaw, B. M. (2023) · Journal of Healthcare Engineering · doi:10.1155/2023/6370416 · Cited by 46
“developed a skin disease identifcation model of Uganda [16].”
BackgroundChlorogiannis, D.-D., Apostolos, A., Chlorogiannis, A., Palaiodimos, L., Giannakoulas, G., Pargaonkar, S., Xesfingi, S., & Kokkinidis, D. G. (2023) · Healthcare · doi:10.3390/healthcare11212906 · Cited by 37
“The training data was comprised of images from roughly 90% white people and 5–10% from other ethnicities and as a result the diagnostic accuracy in this population was half [28].”
BackgroundAggarwal, P., & Papay, F. (2021) · Journal of Dermatological Treatment · doi:10.1080/09546634.2021.1944970 · Cited by 45
“However, when the same algorithm was provided images of dermatological conditions in people with darker skin color, it was able to recognize the correct diagnosis in its top 5 differential diagnoses in only 17% of the images (11).”
BackgroundHow to mitigate the risks of deployment of artificial intelligence in medicine?
İlikhan, S. U., Özer, M., Tanberkan, H., & Bozkurt, V. (2024) · TURKISH JOURNAL OF MEDICAL SCIENCES · doi:10.55730/1300-0144.5814 · Cited by 54
“It has been shown that when images of dermatological lesions from predominantly white patients are used in the training set, the accuracy of AI systems in identifying lesions in darker-skinned patients significantly decreases [40].”
BackgroundSkin Type Diversity in Skin Lesion Datasets: A Review
Alipour, N., Burke, T., & Courtney, J. (2024) · Current Dermatology Reports · doi:10.1007/s13671-024-00440-0 · Cited by 62
“Findings show that these devices are inaccurate, and even may not work at all for dark-skinned people [1, 15].”
BackgroundSoubutts, E., Shrestha, P., Davidson, B. I., Qu, C., Mindel, C., Sefi, A., Marshall, P., & McNaney, R. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642641 · Cited by 34
Artificial Intelligence (AI) and Emergency Medicine: Balancing Opportunities and Challenges
Amiot, F., Potier, B., Viard, T., Tellier, É., & Peschanski, N. (2025) · JMIR Medical Informatics · doi:10.2196/70903 · Cited by 48
“When applied to Fitzpatrick skin type 6 (dark skin) dermatological conditions, the AI system achieved only 17% diagnostic accuracy compared to 69.9% for Caucasian skin types [42].”
InfluentialEthical data acquisition for LLMs and AI algorithms in healthcare
Williams, M. M., Karim, W., Gelman, J., & Raza, M. M. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01399-9 · Cited by 26
“Similarly, convolutional neural networks for skin lesion classi fi cation show signi fi cantlyreduceddiagnosticaccuracyforBlackpatients,astheyareoften trained on datasets where only 5% to 10% of the images come from Black individuals 9 .”
Uwishema, O., Ghezzawi, M., Charbel, N., Alawieh, S., Roy, S., Wojtara, M. S., Hakayuwa, C. M., Ja’afar, I. K., Nkurunziza, G., & Prasad, M. (2025) · International Journal of Emergency Medicine · doi:10.1186/s12245-025-00975-4 · Cited by 27
“Kamulegeya et al. (2023) [31] notably found a drastic drop in diagnostic accuracy for Black skin conditions (17”
InfluentialAl-Ani, A., Rayyan, A., Maswadeh, A., Sultan, H., Alhammouri, A., Asfour, H., Alrawajih, T., Al Sharie, S., Al Karmi, F., Al-Azzam, A. M., et al. (2024) · BMC Medical Ethics · doi:10.1186/s12910-024-01008-0 · Cited by 21
The Impact of Artificial Intelligence on Cancer Diagnosis and Treatment: A Review
Najafi, N. N., Hajihassani, H., & Irani, M. A. (2025) · Cancer Informatics · doi:10.1177/11769351251371273 · Cited by 26
“160 The integration of large and diverse datasets is crucial to addressing complex challenges in healthcare.”
Sheng, Y., Yang, J., Wu, Y., Mao, K., Shi, Y., Hu, J., Jiang, W., & Yang, L. (2022) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3489517.3530427 · Cited by 25
Improving medical machine learning models with generative balancing for equity and excellence
Theodorou, B., Danek, B. P., Tummala, V., Kumar, S. D. M., Malin, B., & Sun, J. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01438-z · Cited by 25
Aggarwal, P. (2021) · JMIR Dermatology · doi:10.2196/31697 · Cited by 22
Escalé-Besa, A., Fuster‐Casanovas, A., Börve, A., Yélamos, O., Fustà‐Novell, X., Rafat, M. E., Marin-Gomez, F. X., & Vidal‐Alaball, J. (2022) · JMIR Research Protocols · doi:10.2196/37531 · Cited by 18
Self-citationArtificial intelligence for nonmelanoma skin cancer
Trager, M. H., Gordon, E. R., Breneman, A., Weng, C., & Samie, F. H. (2024) · Clinics in Dermatology · doi:10.1016/j.clindermatol.2024.06.016 · Cited by 13
Ghanta, S. N., Alaref, S. J., Lala, A., Nadkarni, G. N., Ganatra, S., Dani, S. S., & Mehta, J. L. (2024) · Diagnostics · doi:10.3390/diagnostics14212393 · Cited by 16
Improving Artificial Intelligence−Based Diagnosis on Pediatric Skin Lesions
Mehta, P. P., Sun, M., Betz‐Stablein, B., Halpern, A. C., Soyer, H. P., Weber, J., Köse, K., & Rotemberg, V. M. (2023) · Journal of Investigative Dermatology · doi:10.1016/j.jid.2022.08.058 · Cited by 15
SANO: Score-based Diffusion Model for Anomaly Localization in Dermatology
González-Jiménez, Á., Lionetti, S., Pouly, M., & Navarini, A. A. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00300 · Cited by 11
“Furthermore, most of the current training data consist of white skin samples, leading to a significant bias in the performance of DL algorithms, particularly when applied to different skin tones [1,15,18].”
BackgroundGupta, R. K., Parvadiya, L., & Dudhat, K. R. (2025) · Critical Reviews in Therapeutic Drug Carrier Systems · doi:10.1615/critrevtherdrugcarriersyst.2025053255 · Cited by 13
Dunnmon, J. (2021) · Radiologic Clinics of North America · doi:10.1016/j.rcl.2021.07.006 · Cited by 10
Ethics framework for predictive clinical AI model updating
Pruski, M. (2023) · Ethics and Information Technology · doi:10.1007/s10676-023-09721-x · Cited by 14
Iacucci, M., Maeda, Y., & Ghosh, S. (2024) · Gastroenterology · doi:10.1053/j.gastro.2024.03.004 · Cited by 9
Hardware design and the fairness of a neural network
Guo, Y., Yan, Z., Yu, X., Kong, Q., Xie, J., Luo, K., Zeng, D., Wu, Y., Jia, Z., & Shi, Y. (2024) · Nature Electronics · doi:10.1038/s41928-024-01213-0 · Cited by 13
Jiwa, A., Ngatia, A., Benali, K., Boehmer, N., Delle, S., Emedom-Nnamdi, P., Fofie, C. O., O’Brien, C. M., Olatunji, T., Obayagbona, K. I., et al. (2026) · Journal of Medical Internet Research · doi:10.2196/63495 · Cited by 11
Corbin, A., & Marques, O. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-14211-1 · Cited by 16
“[16] needed to create their own dataset of darker skin types to build”
BackgroundSales, C., & Coates, S. J. (2025) · Current Dermatology Reports · doi:10.1007/s13671-025-00469-9 · Cited by 9
“A 2023 study found that one AI model displayed low diagnostic performance on Fitzpatrick 6 skin types, particularly for fungal diseases [63].”
Ethical Principles and Considerations concerning the Use of Artificial Intelligence in Healthcare*
Gieop, M. O. O. N., Yang, J. H., Son, Y., Choi, E. K., & Lee, I. (2023) · Korean Journal of Medical Ethics · doi:10.35301/ksme.2023.26.2.103 · Cited by 9
“11) 흑색종을 진단하는 한 인공지능 개발 과정에서 이미지 데이터셋 중 흑인 환자의 데이터는 5%에 불과하였고, 그 결과 흑인 환자에 대한 인 공지능의 정확성은 백인환자 대비 절반에 불과하였다[26].”
Representation of Demographics in Otolaryngology by Artificial Intelligence Text‐to‐Image Platforms
Shaari, A. L., Saad, A. M., Patel, A. M., & Filimonov, A. (2025) · Laryngoscope Investigative Otolaryngology · doi:10.1002/lio2.70152 · Cited by 8
“Biases in AI can directly harm patient care and exacerbate existing disparities, especially in minority populations underrepresented in training data [27, 30].”
Mwageni, N., van Wijk, R., Daba, F., Mamo, E., Debelo, K., Jansen, B., Schoenmakers, A., van Hees, C. L. M., Kasang, C., Mieras, L. F., et al. (2024) · Tropical Medicine and Infectious Disease · doi:10.3390/tropicalmed9010018 · Cited by 11
“However, similar to this study, better performance levels of the AI app were found when focusing specifically on dermatitis; correct diagnosis was predicted as most likely diagnosis in 80% of the images [40].”
ResultPruski, M. (2024) · Journal of Medical Ethics · doi:10.1136/jme-2023-109675 · Cited by 6
“…relates to such issues as health inequalities affecting under-representated sectors of the population in research datasets and clinical trials, 8–11 and ‘algorithmic bias’—where algorithms have the potential to perpetuate and amplify human biases, and to create new ones, which when caused by…”
BackgroundChoudhury, A., Saremi, M. L., & Urena, E. (2022) · Advances in medical technologies and clinical practice book series · doi:10.4018/978-1-6684-5092-5.ch005 · Cited by 7
Zhang, L., Yu, R., Chen, K., Zhang, Y., Li, Q., & Chen, Y. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108294 · Cited by 5
Eapen, B. R., Archer, N., & Sartipi, K. (2020) · JMIR Dermatology · doi:10.2196/18149 · Cited by 5
“Such models tend to be less sensitive in making predictions on different skin types [25].”
BackgroundHarvey, V. M., Lester, J., Jaleel, T., Takeshita, J., McMichael, A. J., Miller-Monthrope, Y., Jablonski, N. G., Lewis, J., Alexis, A. F., Brown, S. G., et al. (2025) · Archives of Dermatological Research · doi:10.1007/s00403-025-04219-6 · Cited by 8
“When tested on darker skin types, automated algorithms have less than half of the diagnostic accuracy than when tested on white skin [25].”
Applications of Artificial Intelligence in Dermatology
Arza, A., Lebhar, J., & Lipoff, J. B. (2025) · Dermatologic Clinics · doi:10.1016/j.det.2025.05.003 · Cited by 7
Is the public sector Africa’s hidden force for AI-driven healthcare transformation?
Nyamawe, A. S. (2025) · Telematics and Informatics Reports · doi:10.1016/j.teler.2025.100258 · Cited by 7
Building Trustworthy AI in Healthcare
Amadi, C., & Ojo, A. (2025) · IEEE Access · doi:10.1109/access.2025.3648410 · Cited by 16
“…AI models have been shown to have exhibited reduced accuracy in diagnosing conditions such as melanoma among darker-skinned individuals, a disparity directly attributable to their training on datasets predominantly composed of images from fair-skinned individuals [70], [71], [72].”
Christensen, J. M. M., Tømmerås, M. N., Kromann, B., Haulrig, M. B., Manolache, M., Løvendorf, M. B., & Dyring‐Andersen, B. (2026) · JID Innovations · doi:10.1016/j.xjidi.2026.100497 · Cited by 5
Wang, X., Yu, Y., Teigland, R., & Hollberg, A. (2025) · Energy and AI · doi:10.1016/j.egyai.2025.100557 · Cited by 7
Rubegni, E., Ayoub, O., Rizzo, S., Barbero, M., Bernegger, G., Faraci, F. D., Mangili, F., Soldini, E., Trimboli, P., & Facchini, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-60606-9_16 · Cited by 9
Khatun, N., Spinelli, G., & Colecchia, F. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1394386 · Cited by 8
The Data Artifacts Glossary: a community-based repository for bias on health datasets
Gameiro, R. R., Woite, N. L., Sauer, C. M., Hao, S., Fernandes, C. O., Premo, A. E., Teixeira, A. R., Resli, I., Wong, A.-K. I., & Celi, L. A. (2025) · Journal of Biomedical Science · doi:10.1186/s12929-024-01106-6 · Cited by 7
“Already, evidence of bias in AI spans across a variety of applications, from sex-based disparities in algorithms predicting cardiovascular risks [13], to ethnic disparities in the detection of skin-related diseases such as melanoma [14].”
Gichuhi, H. W., Magumba, M. A., Kumar, M., & Mayega, R. W. (2022) · medRxiv · doi:10.1101/2022.12.01.22283003 · Cited by 4
Skin Type Diversity: a Case Study in Skin Lesion DatasetsPreprint
Alipour, N., Burke, T., & Courtney, J. (2023) · Research Square · doi:10.21203/rs.3.rs-3160120/v1 · Cited by 4
Nyamawe, A. S., & Shao, D. D. (2026) · Digital Health · doi:10.1177/20552076261418897 · Cited by 5
“32,15 Data scarcity and incompleteness have been reported in several studies, 30,33,34 demonstrating how it can lead to reliance on algorithms predominantly developed outside Africa.”
Iacucci, M., Santacroce, G., Maeda, Y., Majumder, S., Hassan, C., Shung, D. L., Stidham, R. W., Bisschops, R., Naranjo, V., Grisan, E., et al. (2026) · Nature Reviews Gastroenterology & Hepatology · doi:10.1038/s41575-026-01190-z · Cited by 5
“Equity and universal accessibility are paramount; AI systems should function without discrimination, ensuring fair outputs regardless of race, gender, socioeconomic status or geographic location 84 .”
Data-Algorithm-Architecture Co-Optimization for Fair Neural Networks on Skin Lesion Dataset
Sheng, Y., Yang, J., Li, J., Alaina, J., Xu, X., Shi, Y., Hu, J., Jiang, W., & Yang, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72117-5_15 · Cited by 9
Woite, N. L., Gameiro, R. R., Leite, M. G. H. S. J., Hammond, A., Cobanaj, M., & Celi, L. A. (2025) · Critical Care Science · doi:10.62675/2965-2774.20250380 · Cited by 7
The Impact of Artificial Intelligence on Health Equity in Dermatology
Rinderknecht, F.-A. B., Nwandu, L., Daneshjou, R., & Lester, J. (2024) · Current Dermatology Reports · doi:10.1007/s13671-024-00436-w · Cited by 5
“…DDI dataset, [33] another found that the diagnostic accuracy of one AI model on Fitzpatrick type VI skin was 17% compared to 69.9% on white skin, [34] and another study found that the diagnostic accuracy of basal cell carcinoma in a deep learning algorithm differed significantly between white…”
InfluentialHolmlund, T. B., Diaz-Asper, C. M., & Elvevåg, B. (2020) · Cortex · doi:10.1016/j.cortex.2020.08.024 · Cited by 4
Opportunities and Challenges of Applying Artificial Intelligence in Healthcare
Fahmy, A. M. (2024) · Premier Journal of Artificial Intelligence · doi:10.70389/pjai.100003 · Cited by 5
Transforming Public Health Practice with Artificial Intelligence: A Framework-Driven Approach
Oleribe, O. O., Uzoaru, F., Tarfa, A., Olaniran, O. H., & Taylor-Robinson, S. D. (2026) · Healthcare · doi:10.3390/healthcare14030385 · Cited by 4
“For example, dermatology-focused AI tools have shown limitations when applied to darker skin tones, underscoring the importance of inclusive design and training data [66,67].”
Machado, C., & Hessel, S. (2026) · BMC Artificial Intelligence · doi:10.1186/s44398-026-00027-8 · Cited by 4
Checklist for Medical Imaging using Artificial Intelligence by Evaluation of Machine Learning Models
Bhatnagar, S. (2023) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca57980.2023.10220939 · Cited by 1
“Moreover, model performance reverted to random when socioeconomic and logistical variables, as well as information on the healthcare process (such as various scanners) were considered [5].”
BackgroundAddressing Racial Bias in Cardiovascular Disease Risk Prediction with Fair Data Augmentation
Cui, H., & Han, Y. (2023) · International Conference on Computational Intelligence, Networks and Security (ICCINS) · doi:10.1109/iccins58907.2023.10450015 · Cited by 5
Kakish, D. R. K., AlSamhori, J. F., Qaqish, L. N., Aburumman, L., Sarsur, R., Salkhadi, A. A., Nassif, Z. B., Akmal, M. A., & Nashwan, A. J. (2025) · Dermatological Reviews · doi:10.1002/der2.70022 · Cited by 5
Gupta, V., Broughton, J., Rukundo, A., & Pinky, L. Y. (2025) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2025.101627 · Cited by 5
From traditional to deep learning methods for skin lesion segmentation: A literature review
Hammimou, A., Ezzahori, H., Boudaoud, A., & Aqil, M. (2025) · Scientific African · doi:10.1016/j.sciaf.2025.e02783 · Cited by 4
Survey of Detection and Identification of Black Skin Diseases Based on Machine Learning
Zinsou, K. M. S., Diop, I., Diop, C. T., Bah, A., Ndiaye, M., & Sow, D. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-34896-9_16 · Cited by 2
Applications of Artificial Intelligence in Plastic and Reconstructive Surgery
Reese, V. C., Moawad, R., Mandalapu, S. A., Krapp, M., Sanders, C., & Albano, N. J. (2025) · Artificial intelligence · doi:10.5772/intechopen.1011825 · Cited by 1
Artificial intelligence for semen analysis and sperm selection
Kikuchi, J., Lorimer, J., Shahali, S., & Nosrati, R. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-26745-1.00010-4 · Cited by 2
A Comprehensive Approach to Responsible AI Development and Deployment
Makhni, S., Rico, J., Cerrato, P. L., Hill, B., Overgaard, S. M., Wu, J., Fairbanks, J., Tripp, R., Redziniak, J., Blundo, R., et al. (2025) · Mayo Clinic Proceedings Digital Health · doi:10.1016/j.mcpdig.2025.100294 · Cited by 3
Dowie, T. (2025) · Cureus · doi:10.7759/cureus.94909 · Cited by 11
“Although overall accuracy was 17%, the model showed an 80% accuracy in specific conditions, such as dermatitis, compared to 0% in fungal infections, showing that the capability varies depending on the pathology [24].”
InfluentialDzwonkowska, A., Dzwonkowski, J., Kozłowska, A., Przybysz, K., Rachoń, J., Stadnik, L., Szerenos, N., Trocka, D., Woroniecka, N., & Zienkiewicz, N. (2026) · International Journal of Innovative Technologies in Social Science · doi:10.31435/ijitss.3(51).2026.6375 · Cited by 1
Owoyemi, A., Osiyemi, A., Owoyemi, J., & Boyd, A. (2022) · Springer eBooks · doi:10.1007/978-3-030-64573-1_330 · Cited by 1
Fast and Fair Medical AI on the Edge Through Neural Architecture Search for Hybrid Vision Models
Yang, C., Sheng, Y., Dong, P., Kong, Z., Li, Y., Yu, P., Yang, L., Lin, X., & Wang, Y. (2023) · doi:10.1109/iccad57390.2023.10323652 · Cited by 4
“Reports [4] also indicate that these systems achieved an accuracy rate of 70% for the entire dataset but only 34.7% for women and a mere 17% for individuals with dark skin.”
BackgroundInfluentialArtificial Intelligence in Shoulder Arthroscopy
Rupp, M., Geissbuhler, A. R., Dornan, G. J., Pogorzelski, J., & Millett, P. J. (2024) · Springer eBooks · doi:10.1007/978-3-031-70310-2_11 · Cited by 1
A Framework for Evaluating the Efficacy of Foundation Embedding Models in HealthcarePreprint
Xu, S. H., Gui, H., Rotemberg, V. M., Wang, T., Chen, Y. T., & Daneshjou, R. (2024) · medRxiv · doi:10.1101/2024.04.17.24305983 · Cited by 6
“One case study showed that only 17% of FST VI images were correctly diagnosed through models that were predominately trained on light skin types (Kamulegeya et al., 2023).”
BackgroundArtificial Intelligence-based Diagnosis of Kaposi Sarcoma using Photographs in Dark-skinned PatientsPreprint
Coates, S. J., Yang, F., Hill, C., Xue, Z., Rajaraman, S., Semeere, A., Ayanga, R., Laker‐Oketta, M., Byakwaga, H., Lukande, R. L., et al. (2025) · medRxiv · doi:10.1101/2025.04.21.25326060 · Cited by 1
Escalé-Besa, A., Fuster‐Casanovas, A., Bröve, A., Yélamos, O., Novell, X. F., Rafat, M. E., Marin-Gomez, F. X., & Vidal-Alaball, J. (2022) · doi:10.2196/preprints.37531
Self-citationOwoyemi, A., Osiyemi, A., Owoyemi, J., & Boyd, A. (2021) · Springer eBooks · doi:10.1007/978-3-030-58080-3_330-1 · Cited by 1
A Novel Technique to Investigation of Infectious Diseases
Dasgupta, U., & Garg, N. (2022) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit2283123
Artificial Intelligence: Development and Applications in Neurosurgery
Shah, R., Reese, V. C., Oselkin, M., & Stawicki, S. P. (2023) · Artificial intelligence · doi:10.5772/intechopen.113034 · Cited by 1
Editor’s choice: Covid-19 and HIV are still very much with us
Tumwine, J. K. (2023) · African Health Sciences · doi:10.4314/ahs.v23i2.1
Silva, A. L. R. V., Matozinho, D. V. P., Oliveira, H. D., Inohona, L. F., & de Carvalho, K. C. N. (2024) · Cuadernos de Educación y Desarrollo · doi:10.55905/cuadv16n2-ed.esp.252
Machine learning approaches for screening of materials in flexible electronic devices
Deng, S. (2024) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/177761 · Cited by 1
Human Factors and Behavioral Sensing in AI Applications
Constantinides, M., Spathis, D., & Yfantidou, S. (2025) · Human-computer interaction series · doi:10.1007/978-3-031-61375-3_10 · Cited by 1
Reusing Patient Data to Train Artificial Intelligence for Medical Devices in the European Union
Ladeia, Y. R., & Sousa, N. (2025) · Acta Médica Portuguesa · doi:10.20344/amp.22509
Gerschewski, F. E. (2025) · hautnah · doi:10.1007/s12326-025-00721-w · Cited by 1
Deshpande, A. H., Borkar, S. S., & Baheti, J. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-96-3648-8_3 · Cited by 1
Threats to the Validity of the Predictive System Performance for Ophthalmology
Woźniak, M., & Grzybowski, A. E. (2025) · Springer eBooks · doi:10.1007/978-3-031-83756-2_6
Neural Networks and Computer Vision
Yoon, A. P., & Chung, K. C. (2025) · Hand Clinics · doi:10.1016/j.hcl.2025.08.006 · Cited by 1
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)
- PMC
- PMC10782289
- 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
- diamond
- doi.org
- 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.