Using deep learning for dermatologist-level detection of suspicious pigmented skin lesions from wide-field images.

A reported 96,480 people were diagnosed with melanoma in the United States in 2019, leading to 7230 reported deaths. Early-stage identification of suspicious pigmented lesions (SPLs) in primary care settings can lead to improved melanoma prognosis and a possible 20-fold reduction in treatment cost. Despite this clinical and economic value, efficient tools for SPL detection are mostly absent. To bridge this gap, we developed an SPL analysis system for wide-field images using deep convolutional neural networks (DCNNs) and applied it to a 38,283 dermatological dataset collected from 133 patients and publicly available images. These images were obtained from a variety of consumer-grade cameras (15,244 nondermoscopy) and classified by three board-certified dermatologists. Our system achieved more than 90.3% sensitivity (95% confidence interval, 90 to 90.6) and 89.9% specificity (89.6 to 90.2%) in distinguishing SPLs from nonsuspicious lesions, skin, and complex backgrounds, avoiding the need for cumbersome individual lesion imaging. We also present a new method to extract intrapatient lesion saliency (ugly duckling criteria) on the basis of DCNN features from detected lesions. This saliency ranking was validated against three board-certified dermatologists using a set of 135 individual wide-field images from 68 dermatological patients not included in the DCNN training set, exhibiting 82.96% (67.88 to 88.26%) agreement with at least one of the top three lesions in the dermatological consensus ranking. This method could allow for rapid and accurate assessments of pigmented lesion suspiciousness within a primary care visit and could enable improved patient triaging, utilization of resources, and earlier treatment of melanoma.

Implementation and Impact of a Store-and-Forward Teledermatology Platform in an Urban Academic Safety-Net Health Care System.

Background:Minority and low-income patients disproportionately experience dermatologic access challenges. Store-and-forward (SAF) teledermatology has emerged as a model of care delivery that may improve access. We sought to evaluate patterns of utilization and overall impact after SAF teledermatology implementation in a safety-net health care system. Methods:We performed a retrospective review of 3,285 teledermatology consultations from 2014 to 2017 in an urban academic safety-net health care system. Results:A total of 1,680 (51.2%) patients were referred for inflammatory/rash conditions and 967 (29.5%) for skin lesions. The teledermatologist recommended in-person evaluation in 1,199 encounters (36.5%). Median wait time for a subsequent appointment was 36 days (range 0-244 days). Of subsequent in-clinic visits, 237 patients (26.4%) underwent skin biopsy. No-show rate after referral was 11.8%. In comparison, median wait time for dermatology appointment through standard referral was 64 days, with a no-show rate of 18.6%. Biopsy rate of patients referred via teledermatology was 26.4%, in comparison to a rate of 10.9% of patients referred directly from primary care provider. Discussion:Implementation of SAF teledermatology in a safety-net health system resulted in avoidance of 63.5% potential dermatology visits. Consultation typically resulted in a change in suspected diagnosis or management plan. Rates of concordance between teledermatology consults and in-person evaluations were high. Median wait time was reduced by almost half, no-show rate was reduced ∼37%, and biopsy rate was more than double for teledermatology patients compared with standard referral. Conclusion:These findings suggest that SAF teledermatology may improve access to high-quality dermatologic care and increase clinic efficiencies for patients in safety-net health care systems.

Factors Contributing to Diagnostic Discordance Between Store-and-Forward Teledermatology Consultations and In-Person Visits: Case Series.

BACKGROUND: Use of asynchronous store-and-forward (SAF) teledermatology can improve access to timely and cost-effective dermatologic care and has increased during the COVID-19 pandemic. Previous research has found high diagnostic concordance rates between SAF teledermatology and face-to-face clinical diagnosis, but to our knowledge, none have used specific cases to illustrate factors contributing to diagnostic discordance. OBJECTIVE: To identify and illustrate characteristics that may have contributed to diagnostic discordance between store-and-forward teledermatology and in-person clinical diagnosis in a series of patients. METHODS: We identified 7 cases of diagnostic discordance between teledermatology and in-person visits where the favored diagnosis of the in-person dermatologist was not included in the differential diagnosis formulated by the teledermatologist. Cases were identified from a previously published retrospective chart review of 340 SAF teledermatology consultations, which was previously performed at an academic community health care system in the greater Boston area, Massachusetts, from January 1, 2014, through December 31, 2017. Of 99 patients who completed an in-person dermatology appointment after their teledermatology consultation, 7 had diagnostic disagreement between the teledermatologist and in-person dermatologist where the diagnosis in the in-person consultation was not included in the differential diagnosis in the original teledermatology consult. These 7 cases were examined by 2 author reviewers to identify factors that may have contributed to diagnostic discordance. RESULTS: Factors contributing to diagnostic discordance between SAF teledermatology consultations and in-person visits included poor image quality, inadequate history or diagnostic workup, inability to evaluate textural characteristics, diagnostic uncertainty due to atypical presentations, and evolution in appearance of skin conditions over time. CONCLUSIONS: We identified multiple factors that contributed to diagnostic discordance. Recognition and mitigation of these factors, when possible, may help to improve diagnostic accuracy and reduce the likelihood of misdiagnosis. Continuing education of referring providers and implementation of standardized guidelines for referrals may also be helpful in reducing the risk of misdiagnosis due to inherent limitations of teledermatology services.

Inter-clinician eConsults without programmatic incentives or requirements: a qualitative study of primary care provider perspectives.

BACKGROUND: Inter-clinician electronic consultation (eConsult) programmes are becoming more widespread in the USA as health care systems seek innovative ways of improving specialty access. Existing studies examine models with programmatic incentives or requirements for primary care providers (PCPs) to participate. OBJECTIVE: We aimed to examine PCP perspectives on eConsults in a system with no programmatic incentive or requirement for PCPs to use eConsults. METHODS: We conducted seven focus groups with 41 PCPs at a safety-net community teaching health care system in Eastern Massachusetts, USA. RESULTS: Focus groups revealed that eConsults improved PCP experience by enabling patient-centred care and enhanced PCP education. However, increased workload and variations in communication patterns added challenges for PCPs. Patients were perceived as receiving timelier and more convenient care. Timelier care combined with direct documentation in the patient record was perceived as improving patient safety. Although cost implications were less clear, PCPs perceived costs as being lowered through fewer unnecessary visits and laboratories. CONCLUSIONS: Our findings suggest that eConsult systems with no programmatic incentives or requirements for PCPs have the potential to improve care.

Clinical effectiveness and cost-effectiveness of teledermatology: Where are we now, and what are the barriers to adoption?

There has been rapid growth in teledermatology over the past decade, and teledermatology services are increasingly being used to support patient care across a variety of care settings. Teledermatology has the potential to increase access to high-quality dermatologic care while maintaining clinical efficacy and cost-effectiveness. Recent expansions in telemedicine reimbursement from the Centers for Medicare & Medicaid Services (CMS) ensure that teledermatology will play an increasingly prominent role in patient care. Therefore, it is important that dermatologists be well informed of both the promises of teledermatology and the potential practice challenges a continuously evolving mode of care delivery brings. In this article, we will review the evidence on the clinical and cost-effectiveness of teledermatology and we will discuss system-level and practice-level barriers to successful teledermatology implementation as well as potential implications for dermatologists.

Leprosy Diagnosed via Teledermatology in a U. S. Urban Academic Health Center Highlights Potential Benefits and a Pitfall of Existing Telemedicine Services.

Purpose: Teledermatology has emerged as an important tool to extend the reach of dermatologists. As utilization of teledermatology services increases, careful attention should be given to the design of the system for consulting dermatologists. Methodology: In this case study, we report how access to a patient's entire medical history in a teledermatology consultation was vital for an accurate diagnosis. Results: This case emphasizes the importance of full access to patients' medical records for improving diagnostic accuracy. We believe that full-access systems will lower the risk of misdiagnosis and will help to maximize the potential of teledermatology.

Neutrophilic dermatosis after azathioprine exposure.

IMPORTANCE: Azathioprine hypersensitivity syndrome can present clinically and histopathologically like Sweet syndrome. Shared clinical features include fever, constitutional symptoms, prompt response to systemic corticosteroid therapy, neutrophilia, and abrupt onset of erythematous cutaneous lesions. Histologically, both azathioprine hypersensitivity syndrome and Sweet syndrome are rich in neutrophils. OBSERVATIONS: An 81-year-old woman with Crohn disease presented with fever and an acute eruption of plaques on her extremities within 2 weeks of starting treatment with azathioprine. Laboratory evaluation was notable for leukocytosis and neutrophilia. Skin biopsy of an erythematous plaque on the thigh demonstrated a suppurative folliculitis. Azathioprine treatment was discontinued resulting in resolution of the clinical lesions within 5 days. Our case was compared with 18 cases with similar clinical features. CONCLUSIONS AND RELEVANCE: We report a case of azathioprine hypersensitivity syndrome and review the literature on azathioprine-induced eruptions with features of Sweet syndrome. Our patient's distribution of lesions on the extremities and the finding of suppurative folliculitis on histopathology were not classical for Sweet syndrome. Azathioprine hypersensitivity syndrome seems to be a neutrophil-driven dermatosis; therefore, many overlapping features with Sweet syndrome are not surprising. Due to the potential for anaphylaxis with azathioprine rechallenge, a better term for a Sweetlike presentation in the setting of azathioprine administration is azathioprine hypersensitivity syndrome.

Portfolios of biomedical HIV interventions in South Africa: a cost-effectiveness analysis.

BACKGROUND: Recent clinical trials of male circumcision, oral pre-exposure prophylaxis (PrEP), and a vaginal microbicide gel have shown partial effectiveness at reducing HIV transmission, stimulating interest in implementing portfolios of biomedical prevention programs. OBJECTIVE: To evaluate the effectiveness and cost-effectiveness of combination biomedical HIV prevention and treatment scale-up in South Africa, given uncertainty in program effectiveness. DESIGN: Dynamic HIV transmission and disease progression model with Monte Carlo simulation and cost-effectiveness analysis. PARTICIPANTS: Men and women aged 15 to 49 years in South Africa. INTERVENTIONS: HIV screening and counseling, antiretroviral therapy (ART), male circumcision, PrEP, microbicide, and select combinations. MAIN MEASURES: HIV incidence, prevalence, discounted costs, discounted quality-adjusted life years (QALYs), and incremental cost-effectiveness ratios. KEY RESULTS: Providing half of all uninfected persons with PrEP averts 28 % of future HIV infections for $9,000/QALY gained, but the affordability of such a program is questionable. Given limited resources, annual HIV screening and ART utilization by 75 % of eligible infected persons could avert one-third of new HIV infections, for approximately $1,000/QALY gained. Male circumcision is more cost-effective, but disproportionately benefits men. A comprehensive portfolio of expanded screening, ART, male circumcision, microbicides, and PrEP could avert 62 % of new HIV infections, reducing HIV prevalence from a projected 14 % to 10 % after 10 years. This strategy doubles treatment initiation and adds 31 million QALYs to the population. Despite uncertainty in program effectiveness, a comprehensive portfolio costs less than $10,000/QALY gained in 33 % of simulation iterations and less than $30,000/QALY gained in 90 % of iterations, assuming an annual microbicide cost of $100. CONCLUSIONS: A portfolio of modestly-effective biomedical HIV prevention programs, including male circumcision, vaginal microbicides, and oral PrEP, could substantially reduce HIV incidence and prevalence in South Africa and be likely cost-effective. Given limited resources, PrEP is the least cost-effective intervention of those considered.