The Cross-Talk Between Atopic Dermatitis and Diabetes Mellitus: A Meta-Analysis.

INTRODUCTION: Atopic dermatitis (AD) is associated with various systemic diseases. However, its association with diabetes mellitus (DM) was discussed controversially. Few researchers reviewed the association of these two common morbid disorders. This meta-analysis aimed to assess the relationship between AD and DM. METHODS: We systematically searched PubMed including Epub and ahead of print (198 articles identified) and Cochrane (13 articles) databases. The searching engine was set to include case-control, prospective and retrospective cohorts, and cross-sectional studies from the first published up to February 12, 2021. Two hundred and eleven were identified, eighteen full texts were screened; of them, six were included in the final meta-analysis. The keywords used were AD, diabetes mellitus, type 1 diabetes, and type 2 diabetes. A datasheet was used to record the author's name, year of publication, country and type of the studies, number of events, and total number in the two arms (patients and controls). RESULTS: Out of the 211 references identified, six studies were pooled to test the association between diabetes mellitus and AD. The studies showed that AD is lower among patients with DM, odds ratio, 0.69, 95% CI, and 0.67-0.72. No heterogeneity was observed (Chi-Square, 4.12, degree of freedom (df.)= 5, and I2 = 0%, P-value), 0.53 and P-value for overall effect, <0.001. The included studies were published in Europe (five) and Canada (one study) and included 162,882 patients and 12,164 events, four of the studied articles were case-control studies, one retrospective, and one cross-sectional. CONCLUSION: AD was lower among patients with DM compared to their counterparts without the disease. Further studies focusing on the genetic and environmental factors linking AD and diabetes are needed.

Skin Cancer Detection: A Review Using Deep Learning Techniques.

Skin cancer is one of the most dangerous forms of cancer. Skin cancer is caused by un-repaired deoxyribonucleic acid (DNA) in skin cells, which generate genetic defects or mutations on the skin. Skin cancer tends to gradually spread over other body parts, so it is more curable in initial stages, which is why it is best detected at early stages. The increasing rate of skin cancer cases, high mortality rate, and expensive medical treatment require that its symptoms be diagnosed early. Considering the seriousness of these issues, researchers have developed various early detection techniques for skin cancer. Lesion parameters such as symmetry, color, size, shape, etc. are used to detect skin cancer and to distinguish benign skin cancer from melanoma. This paper presents a detailed systematic review of deep learning techniques for the early detection of skin cancer. Research papers published in well-reputed journals, relevant to the topic of skin cancer diagnosis, were analyzed. Research findings are presented in tools, graphs, tables, techniques, and frameworks for better understanding.