Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning.

Images depicting dark skin tones are significantly underrepresented in the educational materials used to teach primary care physicians and dermatologists to recognize skin diseases. This could contribute to disparities in skin disease diagnosis across different racial groups. Previously, domain experts have manually assessed textbooks to estimate the diversity in skin images. Manual assessment does not scale to many educational materials and introduces human errors. To automate this process, we present the Skin Tone Analysis for Representation in EDucational materials (STAR-ED) framework, which assesses skin tone representation in medical education materials using machine learning. Given a document (e.g., a textbook in .pdf), STAR-ED applies content parsing to extract text, images, and table entities in a structured format. Next, it identifies images containing skin, segments the skin-containing portions of those images, and estimates the skin tone using machine learning. STAR-ED was developed using the Fitzpatrick17k dataset. We then externally tested STAR-ED on four commonly used medical textbooks. Results show strong performance in detecting skin images (0.96 ± 0.02 AUROC and 0.90 ± 0.06 F1 score) and classifying skin tones (0.87 ± 0.01 AUROC and 0.91 ± 0.00 F1 score). STAR-ED quantifies the imbalanced representation of skin tones in four medical textbooks: brown and black skin tones (Fitzpatrick V-VI) images constitute only 10.5% of all skin images. We envision this technology as a tool for medical educators, publishers, and practitioners to assess skin tone diversity in their educational materials.

Impact of, Factors for the Success of, and Concerns Regarding Transplant Patients' Skin Cancer Campaigns: Observational Study.

BACKGROUND: Due to rising health care costs, patients have sought alternative ways of addressing medical expenses. In particular, transplant patients have complex and expensive medical needs-including skin cancer surveillance-that may not be fully covered by insurance. One such method of financing medical costs is by crowdsourcing through web-based platforms, most notably GoFundMe. OBJECTIVE: Previous work identified factors associated with GoFundMe campaigns' fundraising success for dermatologic diseases. We sought to characterize these factors in transplant recipients' campaigns for funds raised for covering skin cancer-related costs. These factors include demographics, campaign traits, and subjective themes. METHODS: From January to April 2022, we analyzed GoFundMe campaigns using the following search terms chosen on the basis of author consensus: "transplant skin cancer," "transplant basal cell," "transplant squamous," "transplant melanoma," and "dermatologist transplant." Demographic data were coded from campaign text or subjectively coded based on author consensus. Campaigns were read completely by 2 independent coders and associated with up to 3 different themes. Linear regression was performed to examine the qualities associated with success, which was defined as funds raised when controlling for campaign goals. Logistic regression was used to examine qualities associated with extremely successful campaigns, defined as those raising funds over 1.5 times the IQR. RESULTS: Across 82 campaigns, we identified several factors that were associated with fundraiser success. Patients who experienced complications during infectious disease treatment, those who received a pancreas transplant, or those who died from their disease raised significantly more money. Patients older than 61 years raised significantly less money. Extremely successful campaigns (>US $20,177) were associated with campaigners who emphasized a disability from their disease, those who were reluctant to ask for help, or those who died due to their disease. CONCLUSIONS: Demographic and thematic factors are associated with transplant patients' skin cancer-related fundraising success, favoring those who are younger, in more extreme situations, and appear reluctant to ask for help; these findings are consistent with those of previous studies. Additionally, transplant patients have complex and expensive dermatologic needs that may not be fully covered by insurance, as reflected in their GoFundMe campaigns. The most commonly mentioned reasons for fundraising included living expenses or loss of income, inadequate or no insurance, and end-of-life costs. Our findings may inform transplant patients how to maximize the success of their campaigns and highlight gaps in health care coverage for skin cancer-related costs. Limitations include the possibility for misclassification due to the data abstraction process and limiting data collection to fundraisers available on GoFundMe while excluding those on other websites. Further research should investigate the ethical implications of crowdfunding, financial needs of this patient population, and potential ways to improve access to routine skin cancer surveillance among patients receiving transplants.

Direct-to-Consumer Teledermatology Growth: A Review and Outlook for the Future.

The direct-to-consumer (DTC) telemedicine industry, including teledermatology, has seen rapid expansion in recent years, partly because of the COVID-19 pandemic. The shortage of dermatologists and the visual nature of dermatologic conditions attracted DTC companies to dermatology. As more patients continue to seek medical consultations and prescription medications from these for-profit companies, we must approach their growth with healthy skepticism. Shortcomings of DTC teledermatology include concerns about conflicts of interest (COIs), overdiagnosis, and overprescribing. Although DTC teledermatology is certainly here to stay, an appropriate understanding of this industry will allow dermatologists to advise patients and advocate for best practices.

Synchronous and asynchronous teledermatology: A narrative review of strengths and limitations.

The policy changes prompted by the COVID-19 pandemic caused synchronous models (primarily video visits) to supplant asynchronous models (store-and-forward or shared digital photographs) as the default and predominant modality of teledermatology care. Here, we call attention to the unique strengths and limitations of these models in terms of clinical utility, accessibility, and cost-effectiveness. Strengths of synchronous visits include direct physician-patient interaction and current reimbursement parity; limitations include variable video image quality, technological difficulties, and accessibility barriers. Strengths of asynchronous visits include greater convenience, especially for clinicians, and potential for image quality superior to video; limitations include less direct physician-patient communication, barriers to follow-up, and limited reimbursement. Both synchronous and asynchronous models have been shown to be cost-effective. Teledermatology is positioned to play a prominent role in patient care post-pandemic. Moving forward, dermatologists are challenged to optimize teledermatology use in order to improve outcomes, efficiency, and workflows to meet diverse patient needs. Future directions will depend on sustainable reimbursement of both teledermatology formats by government and private payers.