Classification of Diabetes Using Feature Selection and Hybrid Al-Biruni Earth Radius and Dipper Throated Optimization.

INTRODUCTION: In public health, machine learning algorithms have been used to predict or diagnose chronic epidemiological disorders such as diabetes mellitus, which has reached epidemic proportions due to its widespread occurrence around the world. Diabetes is just one of several diseases for which machine learning techniques can be used in the diagnosis, prognosis, and assessment procedures. METHODOLOGY: In this paper, we propose a new approach for boosting the classification of diabetes based on a new metaheuristic optimization algorithm. The proposed approach proposes a new feature selection algorithm based on a dynamic Al-Biruni earth radius and dipper-throated optimization algorithm (DBERDTO). The selected features are then classified using a random forest classifier with its parameters optimized using the proposed DBERDTO. RESULTS: The proposed methodology is evaluated and compared with recent optimization methods and machine learning models to prove its efficiency and superiority. The overall accuracy of diabetes classification achieved by the proposed approach is 98.6%. On the other hand, statistical tests have been conducted to assess the significance and the statistical difference of the proposed approach based on the analysis of variance (ANOVA) and Wilcoxon signed-rank tests. CONCLUSIONS: The results of these tests confirmed the superiority of the proposed approach compared to the other classification and optimization methods.

The SARS-COV2 (COVID-19) Pandemic: What Clinicians should Know

In late 2019, a novel coronavirus, now designated SARS-CoV-2, emerged and was identified as the cause of an outbreak of acute respiratory illness in Wuhan, a city in China, named as COVID-19. Since then the waves of the virus exponentially hit many countries around the globe with high rates of spread associated with variable degrees of morbidity and mortality. The WHO announced the pandemic state of the infection in March 2020 and by June 1st 2020 more than 6 million individuals and more than 370 thousands case fatalities were documented worldwide. In this article, we discussed many aspects regarding this emerged infection based on the available evidence aiming to help clinician to improve not only their knowledge but also their practices toward this infection.

The role of procalcitonin as a guide for the diagnosis, prognosis, and decision of antibiotic therapy for lower respiratory tract infections.

OBJECTIVES: To assess the value of PCT as a rapid and sensitive marker for diagnosis, prognosis, and therapy of lower respiratory tract bacterial infections necessitating antimicrobial treatment and comparing this marker with other markers of infections including C-reactive protein (CRP) and total white-blood cell counts (WBCs). PATIENTS AND METHODS: Sixty Patients were enrolled in the study, they were subjected to complete history taking, physical examination, laboratory investigations including complete blood count, blood gases, blood chemistry, bacteriological culture for sputum and blood, serology for atypicals, and PCR for respiratory viruses, serum C-reactive protein (CRP) and PCT levels were measured. The patients were divided into two groups, group 1 included 26 patients who were culture negative for bacterial infection and group 2 included 34 patients who were culture positive. Group 2 patients were given antibiotic therapy according to the culture sensitivity. RESULT: The results revealed that, there was no significant difference between group 1 and group 2 patients as regards age, sex, clinical manifestations, final diagnosis, white blood cell counts, blood gases, number of admitted patients, intensive care unit admission and length of hospital stay. A significant increase of PCT and CRP levels was detected in group 2 compared to group 1 at initial diagnosis. At cutoff value >0.5 ng/ml, PCT gave a sensitivity of 94.1%, specificity of 88.4%, positive predictive value (PPV) of 91.4%, negative predictive value (NPV) of 92% and diagnostic efficiency of 91.6% for diagnosis of respiratory tract bacterial infections. However, at a cutoff value >8 mg/L, CRP gave a sensitivity of 85.2%, specificity of 76.9%, PPV of 82.8%, NPV of 80% and diagnostic efficiency of 81.7%. After antibiotic therapy PCT and CRP levels dropped in group 2 patients as compared to their pre-treatment levels. CONCLUSION: Serum PCT level could be used as a novel marker of lower respiratory tract bacterial infections for diagnosis, prognosis and follow up of therapy. This reduces side-effects of an unnecessary antibiotic use, lowers costs, and in the long-term, leads to diminishing drug resistance.