Enhancing Urban Data Analysis: Leveraging Graph-Based Convolutional Neural Networks for a Visual Semantic Decision Support System.

The persistent increase in the magnitude of urban data, combined with the broad range of sensors from which it derives in modern urban environments, poses issues including data integration, visualization, and optimal utilization. The successful selection of suitable locations for predetermined commercial activities and public utility services or the reuse of existing infrastructure arise as urban planning challenges to be addressed with the aid of the aforementioned data. In our previous work, we have integrated a multitude of publicly available real-world urban data in a visual semantic decision support environment, encompassing map-based data visualization with a visual query interface, while employing and comparing several classifiers for the selection of appropriate locations for establishing parking facilities. In the current work, we challenge the best representative of the previous approach, i.e., random forests, with convolutional neural networks (CNNs) in combination with a graph-based representation of the urban input data, relying on the same dataset to ensure comparability of the results. This approach has been inspired by the inherent visual nature of urban data and the increased capability of CNNs to classify image-based data. The experimental results reveal an improvement in several performance indices, implying a promising potential for this specific combination in decision support for urban planning problems.

The Non-Coding RNA Journal Club: Highlights on Recent Papers-13.

We are delighted to share with you our thirteenth Journal Club and highlight some of the most interesting papers published recently [...].

The Non-Coding RNA Journal Club: Highlights on Recent Papers-12.

We are delighted to share with you our twelfth Journal Club and highlight some of the most interesting papers published recently [...].

Apremilast in Psoriasis Patients With Serious Comorbidities: a Case Series and Systematic Review of Literature.

Introduction: Patients with serious comorbidities are traditionally excluded from clinical trials. Apremilast is not contraindicated in active infections, malignancy and serious hepatic or renal impairment, but real-life data is needed to support this recommendation. Objectives: The aim of this paper is to present our personal as well as literature-sourced real-world evidenced on apremilast use in psoriasis patients with serious baseline comorbidities. Methods: A case-series and systematic literature review were performed. The psoriasis archives of a tertiary-care hospital, four electronic databases (MEDLINE, ScienceDirect, Cochrane Library, Google scholar) and other sources were searched (January 2014 - July 2021). Identified records were considered eligible, if they reported on the use of apremilast monotherapy in psoriasis patients with chronic infections, history of malignancy, serious liver, renal, psychiatric, or other disease(s). Results: At least 841 psoriasis patients with serious baseline diseases received apremilast. Only 3 cases of cancer progression and no infection reactivations or worsening of other diseases were documented. No increased frequency/severity of adverse events or reduced drug efficacy were noted. Main limitations of this study are the exclusion of a few reports due to inappropriately documented data and the fact that at least some patients might have been counted more than once. Conclusions: Apremilast is a safe and adequately efficacious option for psoriasis that cannot be treated/is challenging to treat with classic systemic agents and/or biologics.

New and Upcoming Topical Treatments for Atopic Dermatitis: A Review of the Literature.

Atopic dermatitis (AD) is a chronic inflammatory dermatosis with periods of exacerbation and remissions. AD is characterized by intense, persistent pruritus and heterogeneity in clinical symptomatology and severity. Therapeutic goals include the amelioration of cutaneous eruptions, diminishing relapses and eventually the disease burden. To date, topical corticosteroids (TCS) and calcineurin inhibitors (TCI) have yet been deemed the mainstay of topical treatments in AD management. Nevertheless, despite their indisputable efficiency, TCS and TCI are not indicated for continuous long-term use given their safety profile. While research in AD has concentrated predominantly on systemic therapies, more than 30 novel topical compounds are under development. The existing data appear encouraging, with some regimens that are already FDA-approved (ruxolitinib was the most recent in September 2021) and several pharmaceutical pipeline products for mild-to-moderate AD that are in an advanced stage of development, such as tapinarof, difamilast and roflumilast. Larger, long-term studies are still required to evaluate the efficacy and safety of these novel compounds in the long run and weigh their advantages over present treatments. In this review, we aim to provide an overview of the latest knowledge about AD topical treatments, echoing upcoming research trends.

LncRNAs in breast cancer: a link to future approaches.

Breast cancer affects millions of women each year. Despite recent advances in targeted treatments breast cancer remains a significant threat to women's health. In recent years the development of high-throughput sequencing technologies has advanced the field of transcriptomics shedding light on the role of non-coding RNAs (ncRNAs), including long ncRNAs (lncRNAs), in human cellular function and disease. LncRNAs are classified as transcripts longer than 200nt with no coding potential. These transcripts constitute a diverse group of regulatory molecules essential to the modulation of crucial cellular processes, which dysregulation of leads to disease. LncRNAs exert their regulatory functions through their sequences and by forming complex secondary and tertiary structures that interact with other transcripts, chromatin and/or proteins. Numerous studies have provided evidence of the involvement of LncRNAs in tumor development and disease progression. They possess multiple characteristics that make them novel therapeutic and diagnostic targets. Indeed, the discovery of a novel mechanism by which lncRNAs associated with proteins can induce the formation of phase-separated droplets broadens our understanding of the spatiotemporal control of cellular processes and opens up developing a new treatment. Nevertheless, the role and the molecular mechanisms of many lncRNAs in the regulation of cellular processes and cancer still remain elusive. This is due to the absence of a thorough characterization of the regulatory role of their loci and the functional impact of their aberrations in cancer biology. Here, we present some of the latest advances concerning the role of LncRNAs in breast cancer.

Extensive acquired macular hyperpigmentation in a teenager.

A teenage girl with phototype IV skin presented with extensive gradually progressing asymptomatic macular hyperpigmentation not responding to topical steroids for several months. Histopathology showed foci of increased numbers of melanophages and melanin in the dermis. Click here for the corresponding questions to this CME article.

Adalimumab Effect on Pain in Hidradenitis Suppurativa Patients: Systematic Review and Meta-Analysis.

Introduction: Pain is experienced by most patients with hidradenitis suppurativa (HS) and has a severe impact on their quality of life. Its management still presents a challenge. Adalimumab, a TNF-a antagonist, has shown promising results in HS-related pain reduction. Objectives: To aggregate and synthesize all existing evidence regarding the effect of adalimumab on HS-associated pain. Methods: We identified original controlled and uncontrolled studies with participants receiving adalimumab, which included change in pain score post-treatment compared to baseline as an end-point. We searched MEDLINE, ScienceDirect, the Cochrane Library, ClinicalTrials.gov and International Clinical Trials Registry Platform. The primary endpoint of our study was the mean change (continuous variable) of pain scores at week 12 compared to baseline. Results: We performed a meta-analysis of 4 randomized controlled trials (282 patients in the intervention group and 266 patients in the control group). Adalimumab brought about a 0.418 reduction in mean pain score at its worst with 95%CI [-0.588, -0.248] and P = 0.000 at 12 weeks after treatment commencement. Four more studies were included in a qualitative synthesis, 2 of which reported statistically significant reduction in pain scores at week 12. Conclusions: Adalimumab could be prescribed more readily in cases of HS associated with significant pain.

Apremilast Survival and Reasons for Discontinuation in Psoriasis: Five-Year Experience From a Greek Tertiary Care Centre.

Introduction: Drug survival is an indirect measure of efficacy and safety and its post-marketing assessment using real-life data is invaluable. Objectives: To investigate the survival of apremilast in a cohort of psoriasis patients treated with apremilast in a Greek hospital. Methods: A retrospective cross-sectional study examined adult psoriasis patients receiving apremilast (March 2016 to January 2021). Primary endpoint was the cumulative survival probability at 52 weeks. Kaplan-Meier analysis was used to calculate survival probability. Cox regression analysis was performed to investigate potential risk factors for apremilast discontinuation. Results: One hundred and two patients (29.4% females) with a mean age of 55.9 years (standard deviation 15.21) were included. Sixty-five patients (63.7%) had discontinued treatment by lock date: 19 (18.6%) due to lack of efficacy, 24 (23.5%) due to loss of efficacy, 15 (14.7%) due to adverse reactions, and 7 (6.9%) due to other reasons. Cumulative survival probability at 52 weeks was 52.1%. Median survival time for all reasons for discontinuation was 58 weeks (95% Confidence Interval 40.02, 75.98). Conclusions: Approximately half of patients remained on apremilast after 1 year of treatment. Secondary drug failure was the most common reason for discontinuation.

Treatment strategies for hidradenitis suppurativa: real-life data from a tertiary Greek hospital.

Hidradenitis suppurativa (HS) is a difficult-to-treat chronic relapsing skin disease, which greatly impacts the quality of life. To bring forward real-life challenges in the decision-making process regarding HS treatment. A retrospective observational study was performed with treatment-related data derived from the HS archive of tertiary hospital-based First Department of Dermatology and Venereology of Aristotle University, Greece. Data were available for 121 patients, 63 men (52.7%) and 58 women (47.93%) with a mean age of 38 years. Doxycycline 100 mg twice daily for 1-2 weeks and then once daily for up to a total of 12 weeks was the most popular treatment choice (80 patients, 66.12%), administered for mild-to-moderate disease. Biologics were the second most frequently prescribed treatment, reserved for moderate-to-severe disease (adalimumab: 26 patients, 14.88%, infliximab: 2 patients, 1.65%). All in all, a wide variety of treatment regimens were implemented, with various combinations of topical and systemic agents. Real-life practice reflects the relative paucity of high-quality evidence regarding HS treatment and the absence of a unanimously preferable therapeutic option, leaving both dermatologists and patients defenceless against disease progress and sequelae.

Elderly patients with psoriasis: long-term efficacy and safety of modern treatments.

OBJECTIVE: The increasing number of elderly psoriatic patients presents a challenge for dermatologists. Biologicals and small-molecule inhibitors in the general population have demonstrated a sufficient efficacy and safety profile; yet, studies about their use in the geriatric population are lacking. In this study, we evaluated the efficacy and safety of biological and apremilast among psoriatic patients ≥65 years old. MATERIALS AND METHODS: Clinical records of patients over 65 years old receiving biological drugs or apremilast were retrospectively reviewed. Efficacy was evaluated using Psoriasis Area and Severity Index (PASI) score at treatment onset and weeks 12, 24, 52 and 3 years. Adverse events were also recorded. RESULTS: A total of 154 patients with a mean age of 70.7 ± 6.3 years-old were included in our study. Secukinumab, ustekinumab and brodalumab showed fast-acting results, while the sustained efficacy of secukinumab, ustekinumab, infliximab, adalimumab and brodalumab was also notable. Overall, 30 out of 154 (19.5%) patients reported side effects. Lower respiratory system infections (n = 6; 3.9%) and hepatic enzyme elevation (n = 6; 3.9%) were the most frequently observed events. CONCLUSIONS: Biologicals and apremilast demonstrate adequate efficacy in elderly psoriatic patients. Incidence and severity of reported adverse events were similar to those reported among patients of younger age in relevant clinical studies.

Accuracy of dermoscopic criteria for the differential diagnosis between irritated seborrheic keratosis and squamous cell carcinoma.

BACKGROUND: Even with the addition of dermoscopy, a significant morphologic overlap exists between irritated seborrheic keratosis (ISK) and squamous cell carcinoma (SCC). OBJECTIVE: The aim of this study was to investigate the dermoscopic criteria that could serve as potent predictors for the differential diagnosis between ISK and SCC. METHODS: Dermoscopic images of histopathologically diagnosed ISKs and SCCs were evaluated by 3 independent investigators for the presence of predefined criteria. RESULTS: A total of 104 SCCs and 61 ISKs were included. The main dermoscopic predictors of SCC were dotted vessels (odds ratio [OR], 10.4), branched linear vessels (OR, 5.30), white structureless areas (OR, 6.78), white circles surrounding follicles (OR, 23.45), a diffuse irregular (OR, 2.55) or peripheral (OR, 2.8) vessel arrangement, and a central scale arrangement (OR, 3.35). Dermoscopic predictors of ISK were hairpin vessels (OR, 0.38), a diffuse regular vessel arrangement (OR, 0.39 and OR, 0.36), and white halos surrounding vessels covering more than 10% of the lesion (OR, 0.29 and OR, 0.12). LIMITATIONS: First, the retrospective design of the study; second, the differential diagnosis included in the study was restricted to ISK and SCC. CONCLUSIONS: We confirmed the significant morphologic overlap between ISK and SCC, but we also identified potent predictors for the differential diagnosis between these 2 entities.

Under Development JAK Inhibitors for Dermatologic Diseases.

Molecular targeting therapies represent a new exciting era in dermatology. A promising novel drug class, subject of intense research, is Janus kinase (JAK) inhibitors. Multiple cytokine receptors signal through the Janus kinase and signal transducer and activator of transcription (STAT) pathway. The pathway plays a central role in innate and adaptive immunity, and haematopoiesis. The understanding of the contribution of JAKs to the immunologic processes of inflammatory diseases led to the development of JAK inhibitors, initially for rheumatologic and hematologic diseases. Soon, their efficacy in some dermatologic conditions was also demonstrated, and today their role as therapeutic agents is thoroughly researched, mainly in atopic dermatitis, psoriasis, vitiligo, and alopecia areata. JAK inhibitors can be administered orally or used topically. As they are relatively new treatment modalities in dermatology, many questions concerning their efficacy and safety remain unanswered. Data from ongoing trials are eagerly awaited. Here, we summarize under development JAK inhibitors for dermatologic diseases.

Using Random Forests on Real-World City Data for Urban Planning in a Visual Semantic Decision Support System.

The constantly increasing amount and availability of urban data derived from varying sources leads to an assortment of challenges that include, among others, the consolidation, visualization, and maximal exploitation prospects of the aforementioned data. A preeminent problem affecting urban planning is the appropriate choice of location to host a particular activity (either commercial or common welfare service) or the correct use of an existing building or empty space. In this paper, we propose an approach to address these challenges availed with machine learning techniques. The proposed system combines, fuses, and merges various types of data from different sources, encodes them using a novel semantic model that can capture and utilize both low-level geometric information and higher level semantic information and subsequently feeds them to the random forests classifier, as well as other supervised machine learning models for comparisons. Our experimental evaluation on multiple real-world data sets comparing the performance of several classifiers (including Feedforward Neural Networks, Support Vector Machines, Bag of Decision Trees, k-Nearest Neighbors and Naïve Bayes), indicated the superiority of Random Forests in terms of the examined performance metrics (Accuracy, Specificity, Precision, Recall, F-measure and G-mean).