Artificial Intelligence and Deep Learning Assisted Rapid Diagnosis of COVID-19 from Chest Radiographical Images: A Survey.

Artificial Intelligence (AI) has been applied successfully in many real-life domains for solving complex problems. With the invention of Machine Learning (ML) paradigms, it becomes convenient for researchers to predict the outcome based on past data. Nowadays, ML is acting as the biggest weapon against the COVID-19 pandemic by detecting symptomatic cases at an early stage and warning people about its futuristic effects. It is observed that COVID-19 has blown out globally so much in a short period because of the shortage of testing facilities and delays in test reports. To address this challenge, AI can be effectively applied to produce fast as well as cost-effective solutions. Plenty of researchers come up with AI-based solutions for preliminary diagnosis using chest CT Images, respiratory sound analysis, voice analysis of symptomatic persons with asymptomatic ones, and so forth. Some AI-based applications claim good accuracy in predicting the chances of being COVID-19-positive. Within a short period, plenty of research work is published regarding the identification of COVID-19. This paper has carefully examined and presented a comprehensive survey of more than 110 papers that came from various reputed sources, that is, Springer, IEEE, Elsevier, MDPI, arXiv, and medRxiv. Most of the papers selected for this survey presented candid work to detect and classify COVID-19, using deep-learning-based models from chest X-Rays and CT scan images. We hope that this survey covers most of the work and provides insights to the research community in proposing efficient as well as accurate solutions for fighting the pandemic.

Applying international guidelines for calcium supplementation to prevent pre-eclampsia: simulation of recommended dosages suggests risk of excess intake in Ethiopia.

OBJECTIVE: To simulate impact of Ca supplementation on estimated total Ca intakes among women in a population with low dietary Ca intakes, using WHO recommendations: 1·5-2·0 g elemental Ca/d during pregnancy to prevent pre-eclampsia. DESIGN: Single cross-sectional 24 h dietary recall data were adjusted using IMAPP software to simulate proportions of women who would meet or exceed the Estimated Average Requirement (EAR) and Tolerable Upper Intake Level (UL) assuming full or partial adherence to WHO guidelines. SETTING: Nationally and regionally representative data, Ethiopia's 'lean' season 2011. SUBJECTS: Women 15-45 years (n 7908, of whom 492 pregnant). RESULTS: National mean usual Ca intake was 501 (sd 244) mg/d. Approximately 89, 91 and 96 % of all women, pregnant women and 15-18 years, respectively, had dietary Ca intakes below the EAR. Simulating 100 % adherence to 1·0, 1·5 and 2·0 g/d estimated nearly all women (>99 %) would meet the EAR, regardless of dosage. Nationally, supplementation with 1·5 and 2·0 g/d would result in intake exceeding the UL in 3·7 and 43·2 % of women, respectively, while at 1·0 g/d those exceeding the UL would be <1 % (0·74 %) except in one region (4·95 %). CONCLUSIONS: Most Ethiopian women consume insufficient Ca, increasing risk of pre-eclampsia. Providing Ca supplements of 1·5-2·0 g/d could result in high proportions of women exceeding the UL, while universal consumption of 1·0 g/d would meet requirements with minimal risk of excess. Appropriately tested screening tools could identify and reduce risk to high Ca consumers. Research on minimum effective Ca supplementation to prevent pre-eclampsia is also needed to determine whether lower doses could be recommended.

Iron, folate and vitamin B12 status of Ethiopian professional runners.

BACKGROUND: Better macro and micro nutrient status and their adequate intake by the athletes have great role in balancing losses associated with strenuous exercise, then for better performance. The objective of this study was to determine iron, folate and vitamin B12 status of Ethiopian professional athletes. METHODS: A cross sectional study was conducted using a point time convenient sample of 101 male and female Ethiopian professional athletes of different distance categories in the period of February to April 2014. Biochemical samples, detail health and exercise related interview, performance data, 24 h dietary diversity and weekly food frequency were collected. RESULTS: The low, medium and high dietary diversity terciles were 36.1, 60.9 and 3.3 % respectively. The mean ± Sd of dietary diversity was 5.44 ± 1.8. Prevalence of iron overload (Serum ferritin >200 µg/L) was 11 %, whereas that of anemia (Hb < 12 g/dL), iron deficiency (ferritin < 12 µg/L) and moderate folate deficiency (<5.9 ng/mL) was 3, 2 and 20.8 % respectively. There was no iron deficiency anemia case in the study. In this study, the mean serum vitamin B12 concentration was 561 ± 231 pg/ml with a minimum and maximum value of 210 and 1736 pg/ml respectively, and there was no deficiency for this nutrient (>210 pg/ml). The iron status of male athletes was significantly different by running-distance categories. In contrast, such difference was absent for female athletes. Performance of the athletes was associated with their red blood cell count (RBC) at p = 0.03. The high performer athletes exhibited high mean value of micronutrient status and hematological variables than their counter parts. However, the RBC of the athletes was the only parameter whose association was statistically significant. CONCLUSIONS: The observed gender difference in the association of running-distance category with iron and folate in this study needs further investigation. Given the 11 % iron overload in the present study; there is a need of awarance creation activities and diet intervention in the athletics federation, the athletes and the coaches in order not aggravate the present overload. Prescription of supplements such as iron-folate, multivitamins and minerals should not be based on broad spectrum rather it should be based on recent history of confirmed deficiency, clinical signs and/or laboratory testing to prevent trace element toxicity.