ABSTRACT
The coronavirus (COVID-19) disease appeared as a respiratory system disorder and has triggered pneumonia outbreaks globally. As this COVID-19 disease drastically spread around the world, computed tomography (CT) has helped to diagnose it rapidly. It is imperative to implement a faultless computer-aided model for detecting COVID-19-affected patients through CT images. Therefore, a detail extraction pyramid network (DEPNet) is proposed to predict COVID-19-affected cases from CT images of the COVID-CT-MD dataset. In this study, the COVID-CT-MD dataset is applied to detect the accuracy of the deep learning technique;the dataset has CT scans of 169 patients;among those, 60 patients are COVID-19 positive patients, and 76 cases are normal. These affected patients were clinically verified with the standard hospital. The deep learning-oriented CT diagnosis model is implemented to detect COVID-19-affected patients. The experiment revealed that the proposed model categorized COVID-19 cases from other respiratory-oriented diseases with 99.45% accuracy. Further, this model selected the exact lesion parts, mainly ground-glass opacity, which helped the doctors to diagnose visually. © 2022 SPIE and IS&T.
ABSTRACT
BACKGROUND: Our study aimed to identify the total costs of inpatient treatment for coronavirus disease 2019 (COVID-19) in a tertiary institution in Serbia, an upper-middle-income country in Southeast Europe. METHODS: An observational, retrospective, cost-of-illness study was performed from the perspective of the National Health Insurance Fund and included a cohort of 78 females and 118 males admitted to the COVID-19 ward units of a tertiary center during the first wave of the pandemic. RESULTS: The median of the total costs in the non-survivors subgroup (n =43) was 3,279.16 Euros [interquartile range (IQR): 4,023.34; range: 355.20-9,909.61) which is higher than in the survivors (n =153) subgroup 747.10 Euros (IQR: 1,088.21; 46.71-3,265.91). The cut-off value of 156.46 Euros regarding the total costs per day was estimated to have 95.3 % sensitivity and 91.5 % specificity for predicting patients' dismal prognosis, with the area under the curve (AUC) of 0.968 (95 % confidence interval: 0.940-0.996, p <0.001). CONCLUSIONS: Direct medical inpatient treatment costs for COVID-19 represent a significant economic burden. The link between increased costs and an ultimate unfavorable outcome should be further explored.HIPPOKRATIA 2022, 26 (2):62-69.
ABSTRACT
Case report Background: Giant cell arteritis (GCA) is an immune-mediated vasculitis affecting large arteries. It has been hypothesized that pathogens including viruses may trigger inflammation within the vessel walls. Human leukocyte antigens' (HLA) genetic studies have previously reported HLA-DR4 (HLA-DRB1* 04 and HLA-DRB1* 01) as susceptibility, and HLA-DR2 (HLA-DRB1* 15 and HLA-DRB1* 16) as protective alleles for GCA. Here we report two cases of large vessel (LV) GCA diagnosed in patients previously suffered from mild coronavirus disese 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV- 2). Case presentation: First case, a 69-year- old male, had a mild COVD-19 three months before the appearance of headache, malaise, and a febrile state associated with extremely increased inflammatory parameters (CRP 2847 mg/dl and IL-6 802.3 pg/ml). Computed tomography examination of the aorta (CTA) and the branches, performed in two occasions six months apart, showed an interesting picture of a migratory arteritis. HLA typing showed: HLA-A* 2,-A* 24;-B* 51,-B* 57;-DRB1* 15,-DRB1* 16;-DQB1* 05,-DQB1* 06;Second case, a 64-year- old female, was evaluated for LV-GCA two months after a mild COVID-19, when she presented with elevated CRP (183mg/dl) and systemic symptoms. Thickening of the ascending aorta and the aortic arch was seen on CTA. Typing of HLA revealed: HLA-A* 2,-A* 11;-B* 27,-B* 35;-DRB1* 14,-DRB1* 15;-DQB1* 05,-DQB1* 06;A whole-body 18F-FDG- PET/ CT performed in both cases revealed inflammation of the ascending, aortic arch, thoracic and abdominal aorta. The first patient had appearance of the inflammatory involvement of the iliac and femoral arteries, while the second patient had an additional pulmonary trunk inflammation. Corticosteroid treatment was introduced in both cases. Due to a progressive inflammatory course of LV-GCA in the first case, the IL-6 inhibitor (tocilizumab) was initiated, leading to a clinical and laboratory improvement. In conclusion, LV-GCA may be considered as an autoimmune disease triggered by SARS-CoV- 2, as one of the broad spectrum of manifestation within the post acute COVID-19. None of the previously known HLA susceptibility alleles for GCA were detected in our patients. In contrast, both patients had DRB1*15 allele, and one of them was DRB1*15/DRB1*16 carrier, suggesting a possibility of losing their protective effect in LV-GCA induced by COVID-19.
ABSTRACT
The onset of the Covid pandemic in 2020 changed the approach to work, research, and study. This period has been a wake-up call for public administrations, the private sector, and the academic community, to digitise their data. In Italy, digital and information technologies for the protection and enhancement of cultural heritage, which were an imperative for more than a decade, have been accelerated. This paper aims to collect and to process openly available data on patrimony from OpenStreetMap and the Lombardian Geoportal. The study is divided into two phases: a simple statistical analysis of cultural heritage in Monza is obtained, and the results are presented graphically. Firstly, built-in tools and Python Console of QGIS are evaluated, to filter attributes and add geometrical values to the downloaded material. Secondly, plug-in DataPlotly and an online coding application named Replit are assessed. The results are presented and compared in terms of their flexibility, quality of visual representation, customisation, and simplicity of use. Tools developed through and for QGIS are easy to use and available to everyone. Additionally, coding applications can be integrated for more refined results. This approach fosters interdisciplinarity, bridges the gap between professionals and non-expert users of GIS, and opens a range of opportunities for future collaborations. The citizen, as a mapper, can be involved in the administrative decision-making process, contributing with data collected in situ. Collaboration between these two sides can potentially produce the better for evaluating the contemporary built environment and its undividable part of cultural heritage.