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.

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.