“…Their characterization of the underrepresentation of skin of color in top search results online reinforces the relative lesser ability of dermatologists to diagnose conditions in darker-skinned patients. 2 The authors' description of potential bias in Google's search algorithm is consistent with biases described in prior studies and criticisms of Google's search algorithms. 2,3 Notably, out of 5 websites appearing in the top 10 image results, the 4 most frequent were medical media outlets or resources, including DermNetNZ, MedicalNewsToday, Healthline, and MerckManuals, indicating that a bias toward lighter-skinned patients in Google's image search results may in fact be a consequence or perpetuation of similar biases on these sites.…”
supporting
confidence: 70%
“…2 The authors' description of potential bias in Google's search algorithm is consistent with biases described in prior studies and criticisms of Google's search algorithms. 2,3 Notably, out of 5 websites appearing in the top 10 image results, the 4 most frequent were medical media outlets or resources, including DermNetNZ, MedicalNewsToday, Healthline, and MerckManuals, indicating that a bias toward lighter-skinned patients in Google's image search results may in fact be a consequence or perpetuation of similar biases on these sites. Thus, the authors' findings may, in fact, reflect the larger issue, in general, of the underrepresentation of skin of color in dermatology, educational materials, and reference materials, 4 even including skin findings reported in association with COVID-19.…”
“…Their characterization of the underrepresentation of skin of color in top search results online reinforces the relative lesser ability of dermatologists to diagnose conditions in darker-skinned patients. 2 The authors' description of potential bias in Google's search algorithm is consistent with biases described in prior studies and criticisms of Google's search algorithms. 2,3 Notably, out of 5 websites appearing in the top 10 image results, the 4 most frequent were medical media outlets or resources, including DermNetNZ, MedicalNewsToday, Healthline, and MerckManuals, indicating that a bias toward lighter-skinned patients in Google's image search results may in fact be a consequence or perpetuation of similar biases on these sites.…”
supporting
confidence: 70%
“…2 The authors' description of potential bias in Google's search algorithm is consistent with biases described in prior studies and criticisms of Google's search algorithms. 2,3 Notably, out of 5 websites appearing in the top 10 image results, the 4 most frequent were medical media outlets or resources, including DermNetNZ, MedicalNewsToday, Healthline, and MerckManuals, indicating that a bias toward lighter-skinned patients in Google's image search results may in fact be a consequence or perpetuation of similar biases on these sites. Thus, the authors' findings may, in fact, reflect the larger issue, in general, of the underrepresentation of skin of color in dermatology, educational materials, and reference materials, 4 even including skin findings reported in association with COVID-19.…”
“…Of the remaining 2871 images, 61.5% were classified as light/white, 30% as medium/brown and 8.5% as dark/ black (Table 1). Compared to general dermatology textbooks [3][4][5] we found that SOC images (brown + black = 38.52%) were better represented in pediatric dermatology textbooks. Still, there exists a real knowledge gap as regards to confidently diagnosing skin diseases in SOC.…”
Section: Re Sults and Discussionmentioning
confidence: 71%
“…2 Evaluations of clinical photographs in standard dermatology textbooks have shown an insufficient exposure to SOC images. [3][4][5] These studies found that there were few photographs of dark skin for common skin diseases, making it difficult for students to identify skin conditions in brown and black skin, consequently hampering patient management. 3,5…”
Section: Introductionmentioning
confidence: 99%
“…[3][4][5] These studies found that there were few photographs of dark skin for common skin diseases, making it difficult for students to identify skin conditions in brown and black skin, consequently hampering patient management. 3,5…”
Due to globalization, dermatologists routinely see patients of different ethnicities and skin tones. Surveys from the US have shown that dermatologists felt that their training was lacking in diagnosing dermatoses in skin-of-color patients. Underrepresentation of skin of color in dermatology textbooks has been reported. We evaluated clinical images in selected pediatric dermatology textbooks with regard to skin color.
BackgroundStudies have revealed a lack of representation of skin of colour patients in academic sources of dermatologic diseases, including databases. This visual racism has consequently generated less comfort and confidence among the specialists in the care and attention of this ethnic group, including the opportunity of being correctly diagnosed.ObjectivesTo investigate and uncover potential racial biases in the HAM10000 data set through an exploratory analysis of the dark skin tones representation, the identification of inaccuracies in its documentation, the recognition of relevant skin conditions absent for darker skin and the lack of ethnic diversity variables crucial for validating diagnosis across different skin tones.MethodsAn exploratory examination was conducted to investigate the occurrence of dark skin within the HAM10000 database (housed in a Harvard Dataverse repository), consisting of 10,015 dermoscopic images of skin lesions. A visual depiction encompassing the whole skin tones was generated by sampling four crucial data points from each image and applying the Gray World Algorithm for colour normalization. To confirm the accuracy of the graphical representation, dermatologists validated the pixel sampling process by analysing a randomly selected 10% of the images for each type of skin lesion. This visual representation was produced for the entire data set as well as for each skin lesion type. The study was further enhanced by comparing the skin lesion representation within the HAM10000 data set against documented prevalences of relevant conditions affecting dark skin.ResultsLess than 5% of the images came from dark‐skinned patients. Nevertheless, in about 4.9% of cases, our pixel sampling method might inadvertently capture shadows or dark spots resulting from the imaging device or the lesion itself rather than the individual's actual skin tone. In addition, there are inaccuracies in the data set's claims of diversity and comprehensive coverage, notably the underrepresentation of conditions prevalent in darker skin and the absence of ethnic diversity variables.ConclusionsVisual racism is an issue that needs to be addressed in medical sources of information and education. Image databases and artificial intelligence models need to be nourished with information, including all skin types, to guarantee equal access to opportunities. Furthermore, any instances where conditions affecting people of colour are underrepresented must be meticulously documented and reported to highlight and address these disparities effectively. This is particularly important in dermoscopy imaging, where solely relying on image‐based racial bias analysis is limited. The alteration of the patient's actual skin tone by the dermatoscope's lighting complicates the accurate assessment of racial bias.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.