Large language models (LLMs) are seen to have tremendous potential in advancing medical diagnosis recently, particularly in dermatological diagnosis, which is a very important task as skin and subcutaneous diseases rank high among the leading contributors to the global burden of nonfatal diseases. Here we present SkinGPT-4, which is an interactive dermatology diagnostic system based on multimodal large language models. We have aligned a pre-trained vision transformer with an LLM named Llama-2-13b-chat by collecting an extensive collection of skin disease images (comprising 52,929 publicly available and proprietary images) along with clinical concepts and doctors\' notes, and designing a two-step training strategy. We have quantitatively evaluated SkinGPT-4 on 150 real-life cases with board-certified dermatologists. With SkinGPT-4, users could upload their own skin photos for diagnosis, and the system could autonomously evaluate the images, identify the characteristics and categories of the skin conditions, perform in-depth analysis, and provide interactive treatment recommendations.

暂无摘要。

Skin and subcutaneous diseases are one of the most common problems affecting the health of children and adolescents. The purpose of this study was to investigate the burden of skin and subcutaneous diseases among children and adolescents and its association with socioeconomic status. Data was obtained from the Global Burden of Disease Study 2019. The number of cases, incidence rate, number of deaths, and death rate in 204 countries and territories from 1990 to 2019 were extracted and stratified by age, sex, and socioeconomic status. In 2019, the global incidence and death rates of skin and subcutaneous diseases in children and adolescents were 57966.98 (95% Uncertainty Interval [UI] 53776.15 to 62521.24) per 100,000 and 0.21 (95% UI 0.13 to 0.26) per 100,000, respectively. From 1990 to 2019, the global incidence rate increased by 5.80% (95% UI 4.82-6.72%) and the death rate decreased by 43.68% (95% UI 23.04-65.27%). The incidence and death rates were negatively correlated with socioeconomic status. Incidence rates were not different between females and males, but death rates were higher among females than males. The highest incidence and death rates were found in the 1-4-year age group and < 1-year age group, respectively. The global burden of skin and subcutaneous diseases in children and adolescents was characterized by regional imbalances. The global burden of skin and subcutaneous diseases in children and adolescents from poorer regions requires more attention. This study provides strong evidence for global policymaking for childhood and adolescent diseases.

暂无摘要。

BACKGROUND: Dermatology is an ideal specialty for artificial intelligence (AI)-driven image recognition to improve diagnostic accuracy and patient care. Lack of dermatologists in many parts of the world and the high frequency of cutaneous disorders and malignancies highlight the increasing need for AI-aided diagnosis. Although AI-based applications for the identification of dermatological conditions are widely available, research assessing their reliability and accuracy is lacking.
OBJECTIVE: The aim of this study was to analyze the efficacy of the Aysa AI app as a preliminary diagnostic tool for various dermatological conditions in a semiurban town in India.
METHODS: This observational cross-sectional study included patients over the age of 2 years who visited the dermatology clinic. Images of lesions from individuals with various skin disorders were uploaded to the app after obtaining informed consent. The app was used to make a patient profile, identify lesion morphology, plot the location on a human model, and answer questions regarding duration and symptoms. The app presented eight differential diagnoses, which were compared with the clinical diagnosis. The model\'s performance was evaluated using sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and F1-score. Comparison of categorical variables was performed with the χ2 test and statistical significance was considered at P<.05.
RESULTS: A total of 700 patients were part of the study. A wide variety of skin conditions were grouped into 12 categories. The AI model had a mean top-1 sensitivity of 71% (95% CI 61.5%-74.3%), top-3 sensitivity of 86.1% (95% CI 83.4%-88.6%), and all-8 sensitivity of 95.1% (95% CI 93.3%-96.6%). The top-1 sensitivities for diagnosis of skin infestations, disorders of keratinization, other inflammatory conditions, and bacterial infections were 85.7%, 85.7%, 82.7%, and 81.8%, respectively. In the case of photodermatoses and malignant tumors, the top-1 sensitivities were 33.3% and 10%, respectively. Each category had a strong correlation between the clinical diagnosis and the probable diagnoses (P<.001).
CONCLUSIONS: The Aysa app showed promising results in identifying most dermatoses.

暂无摘要。

Despite growing diversity in the United States population, studies show that medical education lacks representation of conditions in darker skin tones. Given that medical conditions present differently in different skin tones, limited exposure to images of darker tones in medical training may contribute to incorrect or delayed diagnoses, perpetuating health inequities. This study examines the preclinical curriculum at the Georgetown University School of Medicine (GUSOM) to report on its image representation with respect to skin tone and to assess the impact of a student-driven initiative in achieving visual learning equity (VLE). Of 1050 preclinical images, 58.2% depicted conditions in light/white skin tones, 31.3% in medium/brown, and 10.5% in dark/black. The microbiology and pathology courses had the highest percentages of dark/black and medium/brown images. Infectious disease images made up 36.3% of all images with 54.6% light/white, 31.5% medium/brown, and 13.9% dark/black. Overall, the first images representing conditions were 63.5% light/white, 30.0% medium/brown, and 6.6% dark/black. When dark/black images were presented first, 64.3% were of infectious diseases, compared to 35.1% for medium/brown and only 28.4% for white/light first images that were infectious diseases. A significant increase in images of conditions in darker skin tones was observed in the IRD course 2022 compared to the IRD course 2020 (P<.001). Our study highlights an underrepresentation of darker skin tones compared to lighter skin tones in the GUSOM preclinical curriculum. A student-led initiative significantly increased the representation of darker skin tones in dermatologic images, demonstrating the potential impact of such efforts in achieving VLE in medical education.J Drugs Dermatol. 2024;23(7):519-524.  doi:10.36849/JDD.7992.

暂无摘要。

Geriatric in-patient dermatoses are diverse. Few data in Morocco describe the epidemiological profile and factors associated with average length of stay (LOS). Our aim was to identify these dermatoses and determine the factors associated with LOS.

暂无摘要。