JMIR dermatology最新文献

Unlabelled: Our team explored the utility of unpaid versions of 3 artificial intelligence chatbots in offering patient-facing responses to questions about 5 common dermatological diagnoses, and highlighted the strengths and limitations of different artificial intelligence chatbots, while demonstrating how chatbots presented the most potential in tandem with dermatologists' diagnosis.

Background: Online digital materials are integral to patient education and health care outcomes in dermatology. Acanthosis nigricans (AN) is a common condition, often associated with underlying diseases such as insulin resistance. Patients frequently search the internet for information related to this cutaneous finding. To our knowledge, the quality of online educational materials for AN has not been systematically examined.

Objective: The primary objective of this study was to profile the readability and quality of the content of publicly available digital educational materials on AN and identify questions frequently asked by patients.

Methods: This study analyzed publicly available internet sources to identify the most frequent questions searched by patients regarding AN using the Google Rankbrain algorithm. Furthermore, available articles on AN were evaluated for quality and reading level using metrics such as the Brief DISCERN score, and readability was determined using three specific scales including the Flesch-Kincaid score, Gunning Fog index, and the Coleman-Liau index, based on literature.

Results: Patients most frequently accessed facts on AN from government sources, which comprised 30% (n=15) of the analyzed sources. The available articles did not meet quality standards and were at a reading level not appropriate for the general public. The majority of articles (n=29/50, 58%) had substandard Brief DISCERN scores, failing to meet the criteria for good quality.

Conclusions: Clinicians should be aware of the paucity of valuable online educational material on AN and educate their patients accordingly.

Background: Thus far, considerable research has been focused on classifying a lesion as benign or malignant. However, there is a requirement for quick depth estimation of a lesion for the accurate clinical staging of the lesion. The lesion could be malignant and quickly grow beneath the skin. While biopsy slides provide clear information on lesion depth, it is an emerging domain to find quick and noninvasive methods to estimate depth, particularly based on 2D images.

Objective: This study proposes a novel methodology for the depth estimation and visualization of skin lesions. Current diagnostic methods are approximate in determining how much a lesion may have proliferated within the skin. Using color gradients and depth maps, this method will give us a definite estimate and visualization procedure for lesions and other skin issues. We aim to generate 3D holograms of the lesion depth such that dermatologists can better diagnose melanoma.

Methods: We started by performing classification using a convolutional neural network (CNN), followed by using explainable artificial intelligence to localize the image features responsible for the CNN output. We used the gradient class activation map approach to perform localization of the lesion from the rest of the image. We applied computer graphics for depth estimation and developing the 3D structure of the lesion. We used the depth from defocus method for depth estimation from single images and Gabor filters for volumetric representation of the depth map. Our novel method, called red spot analysis, measures the degree of infection based on how a conical hologram is constructed. We collaborated with a dermatologist to analyze the 3D hologram output and received feedback on how this method can be introduced to clinical implementation.

Results: The neural model plus the explainable artificial intelligence algorithm achieved an accuracy of 86% in classifying the lesions correctly as benign or malignant. For the entire pipeline, we mapped the benign and malignant cases to their conical representations. We received exceedingly positive feedback while pitching this idea at the King Edward Memorial Institute in India. Dermatologists considered this a potentially useful tool in the depth estimation of lesions. We received a number of ideas for evaluating the technique before it can be introduced to the clinical scene.

Conclusions: When we map the CNN outputs (benign or malignant) to the corresponding hologram, we observe that a malignant lesion has a higher concentration of red spots (infection) in the upper and deeper portions of the skin, and that the malignant cases have deeper conical sections when compared with the benign cases. This proves that the qualitative results map with the initial classification performed by the neural model. The positive feedback provided by the dermatologist suggests that th

Unlabelled: This observational cost analysis was conducted to assess the efficacy of the Mark Cuban Cost Plus Drug Company (CostPlus) relative to GoodRx and found that CostPlus has significant potential to improve the financial burden of prescription medications within dermatology.

Background: Student-run clinics (SRCs) for dermatology hold potential to significantly advance skin-related health equity, and a comprehensive analysis of these clinics may inform strategies for optimizing program effectiveness.

Objective: We aimed to perform a scoping review of the literature about dermatology SRCs across the United States.

Methods: We conducted systematic literature searches of Ovid MEDLINE, Ovid Embase, and Scopus on March 1, 2023, and June 19, 2024. No date, language, or paper-type restrictions were included in the search strategy. A total of 229 references were uploaded to Covidence for screening by 2 independent reviewers (SK and LL), and 23 full-text documents were assessed for eligibility. After an additional 8 documents were identified through a gray literature search, a total of 31 studies were included in the final analysis. Inclusion criteria were as follows: (1) studies set in an SRC, which was operationally led by medical students and could render condition-relevant treatments to patients, with dermatology care; (2) published in English; (3) within the United States; (4) included characterization of any of the following: logistics, care, patients, or design; and (5) included all study or document types, including gray literature that was not peer reviewed (eg, conference abstracts, preprints, and letters to the editor). Exclusion criteria were (1) papers not published in English and (2) those with duplicated data or that were limited in scope or not generalizable. Data were extracted qualitatively using Microsoft Excel to categorize the studies by several domains, including clinic location, demographics, services offered, and barriers to care.

Results: There are at least 19 dermatology SRCs across the United States. The most common conditions encountered included atopic dermatitis; acne; fungal infections; benign nevi; psoriasis; and neoplasms, such as basal cell carcinoma, squamous cell carcinoma, and melanoma. Key facilitators for the clinics included faculty oversight, attending physician participation for biopsy histopathology, and dedicated program coordinators. Major barriers included lack of follow-up, medication nonadherence, and patient no-shows.

Conclusions: Dermatology SRCs serve a diverse patient population, many of whom are underrepresented in traditional dermatology settings. This scoping review provides insights to help build stronger program foundations that better address community dermatologic health needs.

Unlabelled: The Global Burden of Disease (GBD) study aims to characterize the worldwide prevalence and morbidity of major diseases, while PatientsLikeMe (PLM) is an online community providing patient-generated insights into lived experiences; for dermatologic conditions, quantitative comparisons of GBD and PLM data revealed expected demographic differences but also notable correlations, highlighting their potential as complementary data sources elucidating unmet patient needs and priorities.

Unlabelled: Pigmentary disorders have been implicated in causing psychosocial turmoil in patients as they can cause some degree of cosmetic disfigurement. Lichen planus pigmentosus (LPP) presents as ashy, dermatosis-like eruptions on sun-exposed areas, particularly on the head, neck, and earlobes. On the other hand, vitiligo is a chronic disorder that appears as depigmented patches on the skin. A 61-year-old man with Fitzpatrick skin phototype IV presented to us initially with LPP but eventually also developed vitiligo. The patient was treated with low-dose oral isotretinoin for LPP and topical tacrolimus 0.1% ointment for both LPP and vitiligo with a good clinical outcome. One case of segmental vitiligo and zosteriform LPP, affecting a 22-year-old Indian woman, has been previously reported in the English-language literature. An autoimmune etiology that causes melanocytorrhagy may be a plausible hypothesis for the coexistence of these 2 conditions.

Unlabelled: This study investigates the application of ChatGPT, an artificial intelligence tool, in providing information on skin toxicities associated with cancer treatments, highlighting that while ChatGPT can serve as a valuable resource for clinicians, its use for patient education requires careful consideration due to the complex nature of the information provided.

Unlabelled: We found that third-party apps such as Figure 1 were used predominantly by nondermatologist medical personnel for collaboration in medical decision-making related to dermatologic conditions conducted with other health care providers. This finding calls attention to the need for more readily available resources for nondermatologist health care providers encountering patients with skin-related conditions, with the added benefits of trained dermatologists being allies on such medical app platforms, and the platform allowing for recognition of instances when additional consultation or referral to trained dermatologists for more complex cases is appropriate.

Background: Continuous glucose monitoring (CGM) and continuous subcutaneous insulin infusions (CSIIs) are the current standard treatment devices for type 1 diabetes (T1D) management. With a high prevalence of T1D beginning in pediatrics and carrying into adulthood, insufficient glycemic control leads to poor patient outcomes. Dermatologic complications such as contact dermatitis, lipodystrophies, and inflammatory lesions are among those associated with CGM and CSII, which reduce glycemic control and patient compliance.

Objective: This systematic review aims to explore the current literature surrounding dermatologic complications of CGM and CSII as well as the impact on patient outcomes.

Methods: A systematic review of the literature was carried out using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines using 5 online databases. Included articles were those containing primary data relevant to human participants and adverse reactions to CGM and CSII devices in pediatric populations, of which greater than 50% of the sample size were aged 0-21 years. Qualitative analysis was chosen due to the heterogeneity of outcomes.

Results: Following the application of exclusion criteria, 25 studies were analyzed and discussed. An additional 5 studies were identified after the initial search and inclusion. The most common complication covered is contact dermatitis, with 13 identified studies. Further, 7 studies concerned lipodystrophies, 5 covered nonspecific cutaneous changes, 3 covered unique cutaneous findings such as granulomatous reactions and panniculitis, and 2 discussed user acceptability.

Conclusions: The dermatologic complications of CGM and CSII pose a potential risk to long-term glycemic control in T1D, especially in young patients where skin lesions can lead to discontinuation. Increased manufacturer transparency is critical and further studies are needed to expand upon the current preventative measures such as device site rotation and steroid creams, which lack consistent effectiveness.