The global incidence of skin cancer is rising, emphasizing the need for early detection tools. Artificial intelligence (AI) models, including multimodal systems like ChatGPT-4o, can analyze visual data to assist clinicians in diagnosis. This study evaluated ChatGPT-4o's diagnostic accuracy in detecting melanoma and non-melanoma skin cancers from macroscopic and dermoscopic images. Ninety patients with histopathologically confirmed lesions were included. For each patient, macroscopic images were first uploaded to ChatGPT-4o, followed by combined upload of macroscopic and dermoscopic images. ChatGPT-4o was instructed to provide a preliminary diagnosis and three differential diagnoses for each lesion. Accuracy was assessed at four levels: Level 1: preliminary diagnosis using macroscopic images; Level 2: preliminary diagnosis using macroscopic and dermoscopic images; Level 3: three differential diagnoses using macroscopic images; Level 4: three differential diagnoses using macroscopic and dermoscopic images. Overall Level 1 accuracy was 73.3%, with Level 2, Level 3, and Level 4 accuracies of 66.6%, 75%, and 76.6%, respectively. Dermoscopic images improved accuracy for squamous cell carcinoma (72.7% vs 81.8%, p = 1.00), reduced overall and basal cell carcinoma accuracy (73.3% vs 66.6%, p = 0.180 and 79.6% vs 67.8%, p = 0.065, respectively), and did not affect malignant melanoma (84.6% vs 84.6%) or lentigo maligna (0% vs 0%). Statistical analysis revealed that the addition of dermoscopic images did not significantly influence diagnostic accuracy, either overall or within individual diagnostic categories. The model recommended biopsy for all lesions, suggesting potential as a supportive diagnostic tool. ChatGPT-4o showed variable diagnostic accuracy for melanoma and non-melanoma skin cancers. Dermoscopic images reduced performance for certain diagnostic categories. These misclassifications highlight the potential for unnecessary interventions and patient anxiety underscoring that AI-based systems should serve as supportive aids rather than standalone diagnostic tools.

Background: Demodex mites are believed to contribute to the pathogenesis of both rosacea and demodicosis. While standardized skin surface biopsy (SSSB) remains the gold standard for detecting Demodex density, it is invasive and time-consuming. Ultraviolet (UV) dermoscopy, a noninvasive technique that visualizes fluorescent structures, may offer a rapid alternative for identifying Demodex proliferation. Objectives: To investigate the relationship between Demodex folliculorum and Demodex brevis counts obtained by SSSB and fluorescent dots detected under UV dermoscopy, and to evaluate the diagnostic value of these findings in rosacea and demodicosis. Methods: Fifty-four patients with rosacea or demodicosis were evaluated using both UV dermoscopy and SSSB from the same facial region. Orange and bright blue fluorescent dots were recorded dermoscopically, and mite density and species were quantified via SSSB. Correlation analyses and receiver operating characteristic (ROC) curve analysis were performed to assess diagnostic performance. Results: A significant positive correlation was found between total Demodex count and bright blue fluorescent dots (r = 0.343; P = 0.013), but not with orange dots (r = –0.065; P = 0.649). Only D. folliculorum showed significant correlation with blue and total fluorescent dots. ROC analysis identified > 11 bright blue dots as the optimal threshold for predicting Demodex positivity, with a sensitivity of 82.1% and specificity of 71.4% (area under the curve 0.793; P = 0.003). Conclusions: Bright blue fluorescent dots observed under UV dermoscopy correlate significantly with Demodex density, particularly D. folliculorum. A threshold of > 11 blue dots demonstrated good diagnostic accuracy and may serve as a practical, noninvasive alternative or adjunct to SSSB in clinical settings. Orange fluorescence was not associated with Demodex density and most likely reflects unrelated sebaceous or microbial activity.

Background: Dietary strategies in chronic spontaneous urticaria (CSU) have primarily focused on restriction‐based interventions. The potential role of fluid‐restricted intermittent fasting (IF), which may exert immunomodulatory effects, remains underexplored in CSU. This study investigates the efficacy of IF as an adjunctive approach in patients with CSU. Methods: In this prospective observational study, 100 patients with CSU on stable guideline‐directed treatment were allocated based on patient preference to a fasting group ( n = 50, following daily fluid‐restricted IF, median 15.5 h) or a nonfasting control group ( n = 50) for one month. Disease control and activity were assessed using the urticaria control test (UCT) and urticaria activity score (UAS). Results: The fasting group achieved significantly higher UCT scores at one month compared to controls (13 vs. 12, p = 0.001). The change in UCT (ΔUCT) was significantly greater in the fasting group ( p < 0.001). While UAS decreased within the fasting group ( p < 0.001), the between‐group difference in ΔUAS was not significant. Multivariable regression confirmed fasting status as an independent predictor of improved control. Notably, significant improvements were observed even in patients with features of refractory disease, such as elevated CRP and eosinopenia. ROC analysis identified a 16‐h daily fasting threshold for optimal clinical improvement. Conclusions: A structured, prolonged daily fasting regimen is associated with significant improvements in CSU disease control, including in patients with refractory profiles. IF may serve as a practical adjunct to standard therapies.