BACKGROUND: Atopic dermatitis (AD) is a chronically relapsing skin disease that is associated with a disturbance of the epidermal barrier function. Changes in the human skin microbiome have been suggested as a risk factor for AD. OBJECTIVE: The aim of this study was to explore the species distribution of microflora on the skin and in the oral cavity of healthy volunteers and patients with AD. METHODS: Samples for culture were obtained from both lesional skin and the oral cavity in 211 patients with AD and from both the normal skin and oral cavity of 24 healthy controls. Species identification was performed with the VITEK 2 system (bioMerieux Inc., Hazelwood, MO, USA). RESULTS: The isolation of Staphylococcus aureus from the skin was statistically more frequent among patients with AD than among healthy controls, while the isolation of Staphylococcus hominis and Micrococcus luteus were statistically more frequent among healthy controls than among patients with AD (p<0.05). In the oral cavity, S. aureus and Candida albicans were found more frequently in patients with AD, but the difference did was not statistically significant. CONCLUSION: This study provides an important insight into the species distribution of microorganisms on human skin and in the oral cavity. Further investigation is required to determine the role of specific microorganisms in the etiology and pathogenicity of AD.
Candida albicans ; Dermatitis, Atopic* ; Healthy Volunteers ; Humans ; Microbiota ; Micrococcus luteus ; Mouth ; Risk Factors ; Skin Diseases ; Skin* ; Staphylococcus aureus ; Staphylococcus hominis ; Virulence

Background and Objectives: There is limited evidence regarding machine-learning prediction for the recurrence of atrial fibrillation (AF) after electrical cardioversion (ECV).This study aimed to predict the recurrence of AF after ECV using machine learning of clinical features and electrocardiograms (ECGs) in persistent AF patients. Methods: We analyzed patients who underwent successful ECV for persistent AF. Machine learning was designed to predict patients with 1-month recurrence. Individual 12-lead ECGs were collected before and after ECV. Various clinical features were collected and trained the extreme gradient boost (XGBoost)-based model. Ten-fold cross-validation was used to evaluate the performance of the model. The performance was compared to the C-statistics of the selected clinical features. Results: Among 718 patients (mean age 63.5±9.3 years, men 78.8%), AF recurred in 435(60.6%) patients after 1 month. With the XGBoost-based model, the areas under the receiver operating characteristic curves (AUROCs) were 0.57, 0.60, and 0.63 if the model was trained by clinical features, ECGs, and both (the final model), respectively. For the final model, the sensitivity, specificity, and F1-score were 84.7%, 28.2%, and 0.73, respectively. Although the AF duration showed the best predictive performance (AUROC, 0.58) among the clinical features, it was significantly lower than that of the final machine-learning model (p<0.001).Additional training of extended monitoring data of 15-minute single-lead ECG and photoplethysmography in available patients (n=261) did not significantly improve the model’s performance. Conclusions Machine learning showed modest performance in predicting AF recurrence after ECV in persistent AF patients, warranting further validation studies.