Cladribine Use in Xanthoma Disseminatum: A Rare Case Presentation and Brief Updated Literature Review.

Xanthoma disseminatum (XD) is a rare, non-Langerhans cell histiocytosis. While treatment is notoriously difficult, 2-chlorodeoxyadenosine (cladribine) has recently emerged as a potential effective therapeutic option. Here, we describe the case of a 65-year-old male with XD who experienced significant cutaneous improvement after cladribine treatment. We also provide an updated literature review on cladribine use in patients with XD in light of reported adverse effects (AEs). While the efficacy of cladribine in XD is clear, no consensus exists for treatment duration and AE management. Hence, we strongly encourage interdisciplinary discourse involving dermatology and oncology in these cases.

Image Quality Assessment Using Convolutional Neural Network in Clinical Skin Images.

The image quality received for clinical evaluation is often suboptimal. The goal is to develop an image quality analysis tool to assess patient- and primary care physician-derived images using deep learning model. Dataset included patient- and primary care physician-derived images from August 21, 2018 to June 30, 2022 with 4 unique quality labels. VGG16 model was fine tuned with input data, and optimal threshold was determined by Youden's index. Ordinal labels were transformed to binary labels using a majority vote because model distinguishes between 2 categories (good vs bad). At a threshold of 0.587, area under the curve for the test set was 0.885 (95% confidence interval = 0.838-0.933); sensitivity, specificity, positive predictive value, and negative predictive value were 0.829, 0.784, 0.906, and 0.645, respectively. Independent validation of 300 additional images (from patients and primary care physicians) demonstrated area under the curve of 0.864 (95% confidence interval = 0.818-0.909) and area under the curve of 0.902 (95% confidence interval = 0.85-0.95), respectively. The sensitivity, specificity, positive predictive value, and negative predictive value for the 300 images were 0.827, 0.800, 0.959, and 0.450, respectively. We demonstrate a practical approach improving the image quality for clinical workflow. Although users may have to capture additional images, this is offset by the improved workload and efficiency for clinical teams.

Evaluation of the Tolerability of Hedgehog Pathway Inhibitors in the Treatment of Advanced Basal Cell Carcinoma: A Narrative Review of Treatment Strategies.

Hedgehog pathway inhibitors (HHIs) have broadened the treatment options available for patients with advanced basal cell carcinoma (BCC) for whom traditional therapeutic approaches are not feasible or effective. Sonidegib and vismodegib are oral HHIs that were approved for treatment of patients with advanced BCC after demonstrating promising efficacy in the pivotal Phase II BOLT (NCT01327053) and ERIVANCE (NCT00833417) trials, respectively. However, the incidence and types of treatment-emergent adverse events (AEs) observed with these agents may limit continuous use of HHIs and ultimately impact clinical outcomes. In this review, we summarize the safety and tolerability profiles of sonidegib and vismodegib and discuss potential management strategies for HHI class-effect AEs, including muscle spasms, creatine phosphokinase increase, alopecia, and dysgeusia. These AEs primarily occur early in treatment and can lead to treatment discontinuation. Differences in the pharmacokinetic profiles of sonidegib and vismodegib may contribute to the variability noted in times to onset and resolution of these and other AEs. Evidence suggests that protocol modifications, such as treatment interruptions and dose reductions, are effective ways to manage AEs while maintaining disease control. Nonpharmacologic and pharmacologic interventions may also be considered as part of an AE management strategy. Overall, healthcare providers and patients with advanced BCC should be aware of the HHI class-effect AEs and plan effective management strategies to avoid treatment discontinuation and optimize therapeutic response.

Implementation evaluation of a teledermatology virtual clinic at an academic medical center.

BACKGROUND: Teledermatology (TD) is an evidence-based practice that may increase access to dermatologic care. We sought to use the Exploration, Preparation, Implementation, and Sustainment (EPIS) and the Reach, Efficacy, Adoption, Implementation, and Maintenance (RE-AIM) frameworks to evaluate implementation of TD at Duke. METHODS: The EPIS and RE-AIM frameworks were deployed to design and implement a TD program that leveraged the strengths of the Duke University Health System and addressed previously reported barriers to implementation of store-and-forward and synchronous TD models. In the resultant hybrid TD model, trained primary care providers (PCPs) sent e-comm referrals with clinical and dermatoscopic images to dermatology. These e-consults were reviewed asynchronously and patients were scheduled for a synchronous video visit with dermatology within days. Dermatologists managed the patient plan. This hybrid TD model was piloted at four primary care clinics. Pertinent outcomes from a TD-adapted RE-AIM framework were tracked using electronic health record data. Patient satisfaction was assessed using a post-video visit survey (n = 18). Implementation barriers and facilitators were also collected through provider surveys (n = 24 PCPs, n = 10 dermatologists, n = 10 dermatology residents). RESULTS: At four PCP clinics throughout 9/1/2021-4/30/2022, there were 218 TD referrals. Video visits occurred on average 7.5 ± 0.5 days after referral and 18/18 patients completing the post-visit survey were satisfied. Adoption varied between clinics, with one placing 22% of all dermatology referrals as TD and another placing 2%. The primary PCP barriers to TD were time burdens, lack of fit in clinic flow, and discomfort with image taking. Top-endorsed potential facilitating interventions included allowing for rash referrals without dermoscopy and assurance for clinical evaluation within 3 days. CONCLUSIONS: The use of implementation science frameworks allowed for identification of system and contextual strengths which informed the hybrid TD pilot. Barriers and facilitating interventions will provide guidance for expansion and ongoing maintenance of TD.

Implementation Evaluation of a Teledermatology Virtual Clinic at an Academic Medical Center.

Background: Teledermatology (TD) is an evidence-based practice that may increase access to dermatologic care. We sought to evaluate implementation of TD at four Duke primary care practices. Methods: We implemented a hybrid TD program where trained primary care providers (PCPs) sent referrals with clinical and dermatoscopic images to dermatology. Patients were seen by dermatologists over video visit within days, and dermatologists managed the patient plan. We evaluated implementation using the Reach, Efficacy, Adoption, Implementation, and Maintenance (RE-AIM) framework using electronic health record data. Implementation barriers and facilitators were collected through surveys (n = 24 PCPs, n = 10 dermatologists, n = 10 dermatology residents). Results: At four PCP clinics throughout 9/1/2021-4/30/2022 there were 218 TD referrals. Video visits occurred on average 7.5 days after referral and 18/18 patients completing the post-visit survey were satisfied. Adoption varied between clinics, with one placing 22% of all dermatology referrals as TD and another placing 2%. The primary PCP barriers to TD were time burdens, lack of fit in clinic flow, and discomfort with image taking. Top-endorsed potential facilitating interventions included allowing for rash referrals without dermoscopy and assurance for clinical evaluation within 3 days. Conclusions: Addressing TD process fit into PCP clinic flow and reducing time burdens may increase PCP uptake of TD.

Early Detection and Prognostic Assessment of Cutaneous Melanoma: Consensus on Optimal Practice and the Role of Gene Expression Profile Testing.

Importance: Therapy for advanced melanoma has transformed during the past decade, but early detection and prognostic assessment of cutaneous melanoma (CM) remain paramount goals. Best practices for screening and use of pigmented lesion evaluation tools and gene expression profile (GEP) testing in CM remain to be defined. Objective: To provide consensus recommendations on optimal screening practices and prebiopsy diagnostic, postbiopsy diagnostic, and prognostic assessment of CM. Evidence Review: Case scenarios were interrogated using a modified Delphi consensus method. Melanoma panelists (n = 60) were invited to vote on hypothetical scenarios via an emailed survey (n = 42), which was followed by a consensus conference (n = 51) that reviewed the literature and the rationale for survey answers. Panelists participated in a follow-up survey for final recommendations on the scenarios (n = 45). Findings: The panelists reached consensus (≥70% agreement) in supporting a risk-stratified approach to melanoma screening in clinical settings and public screening events, screening personnel recommendations (self/partner, primary care provider, general dermatologist, and pigmented lesion expert), screening intervals, and acceptable appointment wait times. Participants also reached consensus that visual and dermoscopic examination are sufficient for evaluation and follow-up of melanocytic skin lesions deemed innocuous. The panelists reached consensus on interpreting reflectance confocal microscopy and some but not all results from epidermal tape stripping, but they did not reach consensus on use of certain pigmented lesion evaluation tools, such as electrical impedance spectroscopy. Regarding GEP scores, the panelists reached consensus that a low-risk prognostic GEP score should not outweigh concerning histologic features when selecting patients to undergo sentinel lymph node biopsy but did not reach consensus on imaging recommendations in the setting of a high-risk prognostic GEP score and low-risk histology and/or negative nodal status. Conclusions and Relevance: For this consensus statement, panelists reached consensus on aspects of a risk-stratified approach to melanoma screening and follow-up as well as use of visual examination and dermoscopy. These findings support a practical approach to diagnosing and evaluating CM. Panelists did not reach consensus on a clearly defined role for GEP testing in clinical decision-making, citing the need for additional studies to establish the clinical use of existing GEP assays.

Teledermatology May Benefit Marginalized Populations: National and Institutional Trends during the COVID-19 Pandemic.

INTRODUCTION: Limited data exist regarding demographic-specific teledermatology (TD) utilization during the coronavirus disease 2019 (COVID-19) pandemic. This study aimed to determine TD utilization trends during the pandemic. METHODS: A retrospective cohort study for national and institutional populations was conducted. Patient encounters in the American Academy of Dermatology's DataDerm registry (DataDerm) were analyzed from 1 April 2020 through 30 June 2021. All dermatological patients seen by Duke University Health Systems (DUHS) were analyzed from 1 March 2020 through 30 April 2021. In-person clinic visits versus TD encounters (national and institutional) and no-show rates (institutional only) were collected for visit type (i.e., TD versus in-person), sex, race, age/generation, and in- versus out-of-state location (national only). TD utilization is defined as the cohort of interest using TD (e.g., females, whites) within a demographic group (i.e., sex, race) as a percentage of total TD users. This was compared with in-person utilization during the identical timeframe. RESULTS: For US national data, 13,964,816 encounters were analyzed. Sex, race, age, and location each had a significant association with TD utilization (adjusted p < 0.001). For institutional data, 54,400 encounters were analyzed. Sex, race, and age had a significant association with TD utilization (adjusted p < 0.001). Both datasets revealed majority female populations for telehealth visits (DataDerm 66.0%; DUHS 61.7%). Non-white populations accounted for a higher percentage of TD utilizers (DataDerm 15.0%; DUHS 37.3%) when compared with in-person utilizers (DataDerm 11.7%; DUHS 22.3%). Younger patients utilized TD (DataDerm 63.6%; DUHS 62.6%) more than in-person services (DataDerm 26.3%; DUHS 43.8%). Institutional no-show rates between telehealth and in-person visits were lower for Black patients (11.8% versus 19.2%), other non-white races (10.6% versus 13.6%), and younger ages/generations (9.8% versus 12.8%), respectively. TD utilization decreased over time nationally as a percentage of total visits (2.9% versus 0.3%) in 2020 versus 2021, respectively. CONCLUSIONS AND RELEVANCE: During the COVID-19 pandemic, certain populations (females, younger patients, non-white races) showed higher TD utilization. Understanding TD utilization trends is critical in defining the role of virtual care for improving universal care access, optimizing resources, and informing future healthcare models for all patient populations.

Deep Learning in Dermatology: A Systematic Review of Current Approaches, Outcomes, and Limitations.

Artificial intelligence (AI) has recently made great advances in image classification and malignancy prediction in the field of dermatology. However, understanding the applicability of AI in clinical dermatology practice remains challenging owing to the variability of models, image data, database characteristics, and variable outcome metrics. This systematic review aims to provide a comprehensive overview of dermatology literature using convolutional neural networks. Furthermore, the review summarizes the current landscape of image datasets, transfer learning approaches, challenges, and limitations within current AI literature and current regulatory pathways for approval of models as clinical decision support tools.

Use of convolutional neural networks in skin lesion analysis using real world image and non-image data.

Background: Understanding performance of convolutional neural networks (CNNs) for binary (benign vs. malignant) lesion classification based on real world images is important for developing a meaningful clinical decision support (CDS) tool. Methods: We developed a CNN based on real world smartphone images with histopathological ground truth and tested the utility of structured electronic health record (EHR) data on model performance. Model accuracy was compared against three board-certified dermatologists for clinical validity. Results: At a classification threshold of 0.5, the sensitivity was 79 vs. 77 vs. 72%, and specificity was 64 vs. 65 vs. 57% for image-alone vs. combined image and clinical data vs. clinical data-alone models, respectively. The PPV was 68 vs. 69 vs. 62%, AUC was 0.79 vs. 0.79 vs. 0.69, and AP was 0.78 vs. 0.79 vs. 0.64 for image-alone vs. combined data vs. clinical data-alone models. Older age, male sex, and number of prior dermatology visits were important positive predictors for malignancy in the clinical data-alone model. Conclusion: Additional clinical data did not significantly improve CNN image model performance. Model accuracy for predicting malignant lesions was comparable to dermatologists (model: 71.31% vs. 3 dermatologists: 77.87, 69.88, and 71.93%), validating clinical utility. Prospective validation of the model in primary care setting will enhance understanding of the model's clinical utility.

Lesion identification and malignancy prediction from clinical dermatological images.

We consider machine-learning-based lesion identification and malignancy prediction from clinical dermatological images, which can be indistinctly acquired via smartphone or dermoscopy capture. Additionally, we do not assume that images contain single lesions, thus the framework supports both focal or wide-field images. Specifically, we propose a two-stage approach in which we first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy that can be used for high-level screening processes. Further, we consider augmenting the proposed approach with clinical covariates (from electronic health records) and publicly available data (the ISIC dataset). Comprehensive experiments validated on an independent test dataset demonstrate that (1) the proposed approach outperforms alternative model architectures; (2) the model based on images outperforms a pure clinical model by a large margin, and the combination of images and clinical data does not significantly improves over the image-only model; and (3) the proposed framework offers comparable performance in terms of malignancy classification relative to three board certified dermatologists with different levels of experience.

Successful Outpatient Management of Diffuse Photosensitive Bullous Dermatitis Following Pembrolizumab Therapy.

Immune checkpoint inhibitors including programmed death protein 1 inhibitors show great therapeutic benefit for numerous advanced malignancies but can cause a spectrum of immune-related adverse events, with cutaneous toxicity being a common presentation. This report includes two cases of lung adenocarcinoma treated with pembrolizumab that developed rare presentations of diffuse bullous lichenoid dermatitis involving >50% total body surface area. These cases were successfully treated in the outpatient setting with oral dexamethasone and minimal interruption of pembrolizumab therapy, a more conservative approach than current guidelines suggest. J Drugs Dermatol. 2022;21(6):668-670. doi:10.36849/JDD.6715.

Clinical and direct immunofluorescence characteristics of cutaneous toxicity associated with enfortumab vedotin.

Enfortumab vedotin (EV), a novel antibody-drug conjugate approved for metastatic urothelial carcinoma, causes a variety of cutaneous adverse reactions. We present two cases of bullous eruptions following treatment with EV, both demonstrating IgG deposition on direct immunofluorescence (DIF) correlating to the location of nectin-4 in the epidermis. This suggests that the IgG component of EV binding to nectin-4 in keratinocytes is likely a primary contributor to the high rates of cutaneous toxicity.

Hedgehog inhibitors with and without adjunctive therapy in treatment of locally advanced basal cell carcinoma.

BACKGROUND: Hedgehog inhibitor therapy (HHIT) is considered first-line treatment for locally advanced, unresectable basal cell carcinoma (laBCC). HHIT often results in a partial response, which requires adjunctive therapy (AT) post HHIT. We present real-world data for laBCCs undergoing HHIT ± AT. METHODS: Retrospective review at Duke University from 11/01/2007 through 5/20/2020 revealed 13 patients treated with systemic HHIT (sonidegib or vismodegib) for laBCC. RESULTS: Fourteen laBCCs were identified in 13 patients. LaBCCs were treated with sonidegib (n = 10, 71%) or vismodegib (n = 4, 29%) for a median (IQR) of 9.4 (9.3) or 9.8 (8.5) months, respectively. The median (IQR) follow-up time from HHIT initiation was 15.5 (8.7) months. Tumors were most often located on the trunk (43%), followed by head and neck (29%), extremities (21%), and orbit/periorbital area (7%). Nine laBCCs (64%) were treated with HHIT alone, of which five (36%) achieved complete response (CR), four (29%) achieved partial response (PR), and five (36%) achieved CR with combined HHIT and AT post-HHIT. Duration of HHIT treatment (IQR) was 7.5 (3.5) months in the 10 CR patients, versus 15.1 (6.3) months in the four PR patients (P = 0.024). Nine patients (69%) experienced adverse events from HHIT, most commonly ageusia/dysgeusia, muscle spasms, and alopecia. CONCLUSION: As a single institutional experience, we report 10/14 laBCCs (71%) with CRs without recurrence and 4/14 laBCCs (29%) with PRs with HHIT ± AT over median follow-up of 15.5 months. Longer follow-up and larger cohorts evaluating responses with HHIT followed by AT are needed to substantiate our findings.

Outcomes of adjunctive therapies post hedgehog inhibitors in the management of locally advanced basal cell carcinoma: A systematic review and pooled analysis.

Management of patients with locally advanced basal cell carcinoma (laBCC) with traditional strategies has yielded suboptimal outcomes. Targeted treatments including hedgehog inhibitor therapy (HHIT) present limitations when utilized as monotherapy. Herein, we report evidence-based outcomes from available literature on multimodality treatments adjuvant to HHIT in laBCC management. Utilizing a systematic search strategy in PubMed, we identified studies published from inception to April 15, 2020, screened for definitive inclusion/exclusion criteria, and performed individual study quality assessment and pooled analysis to assess impact of adjunctive treatment-based responses post-HHIT on clinical response and recurrence outcomes. Twenty-nine studies (n = 103) were included. Primary findings include a complete response (CR) rate of 90.5%, the median follow-up of 12 months post-HHIT completion. The recurrence rate was 10.8% with 12-month median time to recurrence. Mohs micrographic surgery (MMS) had 100% CR post-HHIT, while no difference was observed between surgery and radiation therapy (RT). MMS and surgery had comparable 2-year recurrence free rates (RFR) at 87% and 86% respectively, while RT had the lower 2-year RFR at 67%. Male gender portended a more advanced stage at diagnosis and worse outcomes. In a subset analysis, periorbital laBCCs with orbital involvement had a CR rate of 81.8% versus 100% in those without orbital involvement, with similar rates of recurrence. Limited available quantitative data and possible publication bias were limitations. Pooled analysis of observational data supports use of adjunctive therapies post-HHIT to improve treatment response in patients with laBCC. Longer-term follow-up is needed to study recurrence rates after combination therapy.