Background: Artificial intelligence (AI) and convolutional neural networks (CNNs) represent rising trends in modern medicine. However, comprehensive data on the performance of AI practices in clinical dermatologic images are non‐existent. Furthermore, the role of professional data selection for training remains unknown.Objectives: The aims of this study were to develop AI applications for outlier detection of dermatological pathologies, to evaluate CNN architectures' performance on dermatological images and to investigate the role of professional pre‐processing of the training data, serving as one of the first anchor points regarding data selection criteria in dermatological AI‐based binary classification tasks of non‐melanoma pathologies.Methods: Six state‐of‐the‐art CNN architectures were evaluated for their accuracy, sensitivity and specificity for five dermatological diseases and using five data subsets, including data selected by two dermatologists, one with 5 and the other with 11 years of clinical experience.Results: Overall, 150 CNNs were evaluated on up to 4051 clinical images. The best accuracy was reached for onychomycosis (accuracy = 1.000), followed by bullous pemphigoid (accuracy = 0.951) and lupus erythematosus (accuracy = 0.912). The CNNs InceptionV3, Xception and ResNet50 achieved the best accuracy in 9, 8 and 6 out of 25 data sets, respectively (36.0%, 32.0% and 24.0%). On average, the data set provided by the senior physician and the data set provided in accordance with both dermatologists performed the best (accuracy = 0.910).Conclusions: This AI approach for the detection of outliers in dermatological diagnoses represents one of the first studies to evaluate the performance of different CNNs for binary decisions in clinical non‐dermatoscopic images of a variety of dermatological diseases other than melanoma. The selection of images by an experienced dermatologist during pre‐processing had substantial benefits for the performance of the CNNs. These comparative results might guide future AI approaches to dermatology diagnostics, and the evaluated CNNs might be applicable for the future training of dermatology residents.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: The burden of pruritus is high, especially among patients with dermatologic diseases. Estimating the prevalence rates of pruritus and the people’s medical needs is challeng-ing since not all affected people consult a physician. Objective: To investigate pruritus search behavior trends in Germany and identify associations with external factors. Methods: Google AdWords Keyword Planner was used to quantify pruritus-related search que-ries in 16 German cities from August 2014 to July 2018. All identified keywords were qualitatively categorized and pruritus-related terms were descriptively analyzed. The number of search queries per 100,000 inhabitants of each city was compared to envi-ronmental factors such as temperature, humidity, particulate matter (PM10), and sun-shine duration to investigate potential correlations. Results: We included 1,150 pruritus-related keywords, which resulted in 2,851,290 queries. “Pruritus” (n=115,680) and “anal pruritus” (n=102,390) were the most searched for keywords. The most populated cities had the lowest number of queries/100,000 inhab-itants (Berlin, n=13,641; Hamburg, n=18,303; and Munich, n=21,363), while smaller cities (Kiel, n=35,027; and Freiburg, n=39,501) had the highest. Temperature had a greater effect on search query number (β coefficient: -7.94, 95% confidence interval [CI] [-10.74; -5.15]) than PM10 (-5.13, [-7.04, -3.22]), humidity (4.73, [2.70, 6.75]), or sunshine duration (0.66, [0.36, 0.97]). The highest relative number of search queries occurred during the winter (December to February). Conclusions: Google data analysis provided good insight into general search behaviors. Examining different cities across Germany and comparing search volumes with weather data were valuable for identifying trends and respective inhabitants’ needs.

Background: Atopic dermatitis (AD) is a chronic inflammatory skin disease with a multifactorial genesis including genetic predispositions and environmental risk and trigger factors. One of the latter possibly is smoking, indicated by an increased prevalence of AD in adults and children that are actively or passively exposed to cigarette smoke.Objectives: In this study, AD characteristics and its atopic comorbidities are compared in smoking and non‐smoking AD patients.Methods: TREATgermany is a non‐interventional clinical registry which includes patients with moderate to severe AD in Germany. Baseline data of patients included in TREATgermany from inception in June 2016 to April 2020 in 39 sites across Germany was analysed comparing AD disease characteristics and comorbidities in smokers vs. non‐smokers.Results: Of 921 patients, 908 (male: 58.7%) with a mean age of 41.9 ± 14.4 reported their smoking status. The objective Scoring of Atopic Dermatitis (oSCORAD) did not differ between smokers (n = 352; 38.8%) and non‐smokers, however, lesions’ intensity of oozing/crusts and excoriations as well as patient global assessment scores (PGA) of AD severity were higher in smoking as opposed to non‐smoking patients. Smokers reported a lower number of weeks with well‐controlled AD and more severe pruritus than non‐smokers. Total IgE levels were more elevated in smokers and they displayed a younger age at the initial diagnosis of bronchial asthma. After adjustment for potential confounders, the increased intensity of oozing/crusts, the reduced number of weeks with well‐controlled AD and the greater pruritus remained different in smokers compared to non‐smokers. In addition, smoking patients with adult‐onset AD showed a 2.5 times higher chance of involvement of the feet.Conclusions: German registry data indicate that AD patients who smoke have a higher disease burden with a different distribution pattern of lesions in adult‐onset AD.

Background: Atopic dermatitis (AD) is the most common chronic inflammatory skin disease worldwide and displays many atopic, but also non‐atopic comorbidities. Among the latter, mental health disorders such as depression have been extensively studied. However, data on addictions are still rare.Objectives: The aim of this study was to assess the prevalence of different kinds of addictions in adult AD patients using a single‐centre approach.Methods: This non‐interventional cross‐sectional study was performed from 03/2020 to 05/2020 at the Department of Dermatology of a large German university hospital. Participants with a diagnosis of AD confirmed by a dermatologist answered questions about disease severity (patient‐oriented eczema measure, POEM), quality of life (Dermatology Life Quality Index, DLQI) and smoking habits. They were screened for problematic alcohol consumption, drug abuse, internet addiction and pathological gambling using internationally established and validated questionnaires.Results: 157 patients (56.1% female; mean age of 49.9 ± 20.4) with an average POEM of 13.7 ± 7.5 and DLQI of 6.1 ± 5.4 were evaluated. 14.1% were identified as regular smokers, 12.1% screened positive for alcohol dependency, 6.4% for drug use disorders, 4.5% for Internet addiction and 3.2% for pathological gambling. Co‐occurrences of different addictions were observed, and a positive correlation was noted between DLQI scores and smoking.Conclusions: In summary, this study hints at elevated positive screening rates for problematic alcohol consumption, drug use disorders, Internet addiction and problem gambling compared with the general population. Screening routinely for addictions may improve patient‐centred health care of AD patients.

Background: Stereotypes and false assumptions about chronic and visible skin diseases can determine the behaviour towards affected individuals and result in stigmatization or discrimination. Objective: The aim of this study was to analyze the perceived disease-related stigmatization of individuals with psoriasis, atopic dermatitis (AD) or mastocytosis. The study also aims to broaden people-centred knowledge of the effects of stigmatization in different areas of life, namely in everyday life, at work, in sports and in relationships. Methods: Qualitative in-depth semi-structured interviews were conducted among individuals with either psoriasis, AD or mastocytosis. Participants were recruited via self-help networks and were asked to express their experience of stigmatization in different areas of life. All interviews were audio recorded, transcribed verbatim and evaluated based on Mayring's content analysis. Results: In total, 24 individuals aged 19–79 years and living in Germany were included in the study—eight for each disease. Stigmatization was experienced in all three diseases in all mentioned areas of life as well as in interaction with medical professionals. Self-exclusion, negative self-perception and negative behaviour of others were the most frequent experiences with stigmatization. Conclusion: Stigmatization, both internal and external, is an important factor contributing to the mental burden of people with chronic skin diseases. More research is needed to gain deeper insight into stigmatization and its psychological burden in various contexts to enhance people-centred care in chronic skin diseases.

Background: Atopic dermatitis (AD) is one of the most common chronic skin diseases worldwide, showing various manifestations and having a severe impact on quality of life. As previous studies demonstrated, internet search analysis can help identify public interest in diseases and possible influencing factors on search behavior.Objective: To identify AD‐related topics of interest in Germany using internet search volume.Methods: Google Ads Keyword Planner was used to identify AD‐related search terms including their search volume in Germany on a national level as well as in 16 selected cities from January 2016 to December 2019. Identified keywords were qualitatively analyzed, and temporal trends as well as the influence of seasonal and environmental factors on search volume were assessed.Results: Overall, 1222 AD‐related search terms with a search volume of 8 842 360 searches were identified. An increase from 2016 to 2019 and seasonal peaks from January to April of each year were observed. Nationwide, the search volume correlated with mean monthly temperature and sun duration. With increasing temperature and sun duration, a significant decrease in search queries was observed. The most populated cities showed the lowest number of searches per 100 000 inhabitants (Berlin, Hamburg, and Munich). In the eight categories formed (comorbidities, general, influential factors, localization, stage of life, symptoms/severity, therapy/information, and questions on AD), the highest proportion of search queries were assigned to the category “therapy/information” in most cities. In this category, a focus on the topics of “alternative medicine” and “home remedies“ could be observed.Conclusion: The overall high and increasing search volume indicates a high interest in AD‐related topics, especially regarding treatment and disease education. Information provided by internet search volume analyses can optimize AD therapy and patient‐centered care by providing insight into patient needs and predicting potential climatic trigger factors.