Background: Rosacea is a chronic inflammatory disease with variable clinical presentations, including transient flushing, fixed erythema, papules, pustules, and phymatous changes on the central face. Owing to the diversity in the clinical manifestations of rosacea, the lack of objective biochemical examinations, and nonspecificity in histopathological findings, accurate identification of rosacea is a big challenge. Artificial intelligence has emerged as a potential tool in the identification and evaluation of some skin diseases such as melanoma, basal cell carcinoma, and psoriasis. Objective: The objective of our study was to utilize a convolutional neural network (CNN) to differentiate the clinical photos of patients with rosacea (taken from 3 different angles) from those of patients with other skin diseases such as acne, seborrheic dermatitis, and eczema that could be easily confused with rosacea. Methods: In this study, 24,736 photos comprising of 18,647 photos of patients with rosacea and 6089 photos of patients with other skin diseases such as acne, facial seborrheic dermatitis, and eczema were included and analyzed by our CNN model based on ResNet-50. Results: The CNN in our study achieved an overall accuracy and precision of 0.914 and 0.898, with an area under the receiver operating characteristic curve of 0.972 for the detection of rosacea. The accuracy of classifying 3 subtypes of rosacea, that is, erythematotelangiectatic rosacea, papulopustular rosacea, and phymatous rosacea was 83.9%, 74.3%, and 80.0%, respectively. Moreover, the accuracy and precision of our CNN to distinguish rosacea from acne reached 0.931 and 0.893, respectively. For the differentiation between rosacea, seborrheic dermatitis, and eczema, the overall accuracy of our CNN was 0.757 and the precision was 0.667. Finally, by comparing the CNN diagnosis with the diagnoses by dermatologists of different expertise levels, we found that our CNN system is capable of identifying rosacea with a performance superior to that of resident doctors or attending physicians and comparable to that of experienced dermatologists. Conclusions: The findings of our study showed that by assessing clinical images, the CNN system in our study could identify rosacea with accuracy and precision comparable to that of an experienced dermatologist.

Rosacea is an inflammatory skin disorder characterized by the release of inflammatory mediators from keratinocytes, which are thought to play a crucial role in its pathogenesis. Despite an incidence of approximately 5.5%, rosacea is associated with a poor quality of life. However, as the pathogenesis of rosacea remains enigmatic, treatment options are limited. To investigate the pathogenesis of rosacea and explore new therapeutic strategies. Transcriptome data from rosacea patients combined with immunohistochemical staining were used to investigate the activation of STAT3 in rosacea. The role of STAT3 activation in rosacea was subsequently explored by inhibiting STAT3 activation both in vivo and in vitro. The key molecules downstream of STAT3 activation were identified through data analysis and experiments. Dual-luciferase assay and ChIP-qPCR analysis were used to validate the direct binding of STAT3 to the IL-36G promoter. DARTS, in combination with experimental screening, was employed to identify effective drugs targeting STAT3 for rosacea treatment. STAT3 signaling was hyperactivated in rosacea and served as a promoter of the keratinocyte-driven inflammatory response. Mechanistically, activated STAT3 directly bind to the IL-36G promoter region to amplify downstream inflammatory signals by promoting IL-36G transcription, and treatment with a neutralizing antibody (α-IL36γ) could mitigate rosacea-like inflammation. Notably, a natural plant extract (pogostone), which can interact with STAT3 directly to inhibit its activation and affect the STAT3/IL36G signaling pathway, was screened as a promising topical medication for rosacea treatment. Our study revealed a pivotal role for STAT3/IL36G signaling in the development of rosacea, suggesting that targeting this pathway might be a potential strategy for rosacea treatment.

Rosacea is a chronic inflammatory skin disorder, whose underlying cellular and molecular mechanisms remain obscure. Here, we generate a single-cell atlas of facial skin from female rosacea patients and healthy individuals. Among keratinocytes, a subpopulation characterized by IFNγ-mediated barrier function damage is found to be unique to rosacea lesions. Blocking IFNγ signaling alleviates rosacea-like phenotypes and skin barrier damage in mice. The papulopustular rosacea is featured by expansion of pro-inflammatory fibroblasts, Schwann, endothelial and macrophage/dendritic cells. The frequencies of type 1/17 and skin-resident memory T cells are increased, and vascular mural cells are characterized by activation of inflammatory pathways and impaired muscle contraction function in rosacea. Most importantly, fibroblasts are identified as the leading cell type producing pro-inflammatory and vasodilative signals in rosacea. Depletion of fibroblasts or knockdown of PTGDS, a gene specifically upregulated in fibroblasts, blocks rosacea development in mice. Our study provides a comprehensive understanding of the aberrant alterations of skin-resident cell populations and identifies fibroblasts as a key determinant in rosacea development.