Search

Objectives: We aimed to study the characterizing clinical and biochemical profiles of Diabetic Ketoacidosis (DKA) in children with newly diagnosed Type 1 Diabetes Mellitus (Type 1DM) compared to children with established diagnosis of Type 1DM presenting with DKA admitted to the pediatric intensive care unit of a large university hospital in the eastern region of Saudi Arabia. Methods: We retrospectively reviewed the medical records of 211 patients who were admitted to the pediatric intensive care unit with diabetic ketoacidosis between 2010 and 2019. The diagnosis of diabetic ketoacidosis was based on symptoms of polydipsia, polyurea, weight loss, vomiting, dehydration, abdominal pain, breathing problems, lethargy or coma, biochemical hyperglycemia (blood glucose level of >200 mg/dL), venous pH of <7.3, serum bicarbonate level of ≤15 mEq/L, and ketonemia (blood β -hydroxybutyrate concentration of ≥3 mM) or moderate or severe ketonuria (diagnosed as newly acquired type 1 diabetes). Results: The rate of newly diagnosed Type 1 DM with DKA was 41.7%, out of them who got severe and moderate diabetic ketoacidosis were 61.6% and 38.4%, respectively. We observed significantly increased heart and respiratory rates in patients newly diagnosed with diabetic ketoacidosis and in those with severe diabetic ketoacidosis (p<0.001) compared to known cases with Type 1DM presenting with DKA. We also identified significantly increased biochemical indices including HbA1c, random blood sugar, serum osmolality, blood urea nitrogen, creatinine, chloride, lactate, and anion gap in relation to severe diabetic ketoacidosis and newly diagnosed type 1 diabetes (p ≤ 0.05). Conclusions: We found that the clinical and biochemical profiles of patients with newly diagnosed Type 1 DM children were significantly affected compared to children who were known Type 1DM presenting with DKA.

Deep Learning (DL) algorithms enabled computational models consist of multiple processing layers that represent data with multiple levels of abstraction. In recent years, usage of deep learning is rapidly proliferating in almost every domain, especially in medical image processing, medical image analysis, and bioinformatics. Consequently, deep learning has dramatically changed and improved the means of recognition, prediction, and diagnosis effectively in numerous areas of healthcare such as pathology, brain tumor, lung cancer, abdomen, cardiac, and retina. Considering the wide range of applications of deep learning, the objective of this article is to review major deep learning concepts pertinent to brain tumor analysis (e.g., segmentation, classification, prediction, evaluation.). A review conducted by summarizing a large number of scientific contributions to the field (i.e., deep learning in brain tumor analysis) is presented in this study. A coherent taxonomy of research landscape from the literature has also been mapped, and the major aspects of this emerging field have been discussed and analyzed. A critical discussion section to show the limitations of deep learning techniques has been included at the end to elaborate open research challenges and directions for future work in this emergent area.