NSAIDs in COVID-19, friend or foe?

At the beginning of COVID-19 pandemic the use of NSAIDS was avoided. This was because the previous studies suggesting that NSAIDs may be linked to an increased risk of lower respiratory tract infection consequences. Later on studies involved the patients who used NSAIDs for some chronic conditions and showed no additional harm among these patients. Then many studied assessed the benefit of using NSAIDs in COVID-19 patients for management of pain and fever and showed no additional risk among these patients.

Mortality and prognostic factors in hospitalized COVID-19 patients with cancer: An analysis from a large healthcare system in the United States

Background: Coronavirus 19 (COVID-19) is a severe global pandemic and a public health challenge. Patients with COVID-19 and cancer are at an increased risk of poor clinical outcomes. Data is lacking in evaluating outcomes in patients with different cancers, races and ages;particularly in Florida with high proportion of elderly and the largest racial/ethnic disparities. We evaluated the in-hospital mortality of COVID-19 positive cancer patients. Methods: We used retrospective data of COVID-19 patients hospitalized at the Memorial Healthcare System between March 1, 2020 and January 18, 2021. Over 4,870 patients with COVID-19 were evaluated, of which 265 (5.4%) had cancer. The primary endpoint was in-hospital mortality in patients with cancer and COVID-19. Mortality was analyzed in COVID- 19 patients with/without a cancer history. We used descriptive statistics to synthesize outcomes and characteristics from the study population. Univariate and multivariate logistic analysis were performed to define baseline clinical characteristics potentially associated with mortality in cancer patients with COVID-19. Results: 4,870 patients with COVID-19 were evaluated and 265 had malignancy. The study included all different races including Non-Hispanic Whites (NHW) 816 (16.8%), Hispanics 2,271 (46.6%), African-Americans (AA) 1,534 (31.5%) and other minorities 248 (5.1%). Of cancer patients, 24.1% NHW, 43% Hispanic, 28.7% AA and 4.2% other minorities. Amongst races, NHW with cancer accounted for the highest number of COVID-related deaths representing 37.5%, while Hispanics and AA accounted for 18.4% and 19.7% respectfully. Amid cancer subtypes, 24.6% of hematological cancers resulted in mortality and 23.5% of solid cancers resulted in mortality, but no statistical significance was seen. Additionally, after adjusting for age, gender, and race, cancer was linked to an increased in-hospital mortality. Lastly, older age (> 65), elevated creatinine levels (Cr) and elevated C-reactive protein (CRP) were associated with increased risk of death. Conclusions: Patients with COVID-19 and cancer had worse outcomes. Cancer subtypes included hematological and solid cancers, with similar in-hospital mortalities. Although NHW were the smallest group, they had the highest rate of in-hospital deaths amongst cancer patients with COVID-19, in comparison to Hispanics, the largest group in the study, had the least amount of in-hospital deaths. Additionally, factors such as advanced age, elevated Cr and CRP were associated with increased risk of COVID-related deaths. The findings indicate the need for close surveillance and monitoring of these patients as they are more likely to have complications such as mortality from COVID-19.

COVID-19 Diagnosis based on Data Mining Techniques

The basic goal of data mining (DM) in the medical field is to construct a system that can accurately assess medical problems. So when the accuracy of picture detection and identification inside an image processing technique approaches that of a person, most medical images are deemed to become as accurate to healthcare experts. The use of data mining techniques may assist specialists in identifying possible inaccuracies in the classification of a variety of illnesses. As a consequence, The model implementing COVID-19 diagnosis methods is based on the data mining approaches. Some types of machine learning are included in the term DM. a convolutional neural network is a unique computer vision architecture (CNN). It's made to acquire and analyze pixel data. To discover the optimum neural network design for COVID-19 diagnosis, several key factors that influence neural network training, including learning rate & optimization method, must be considered. The major goal of this thesis would be to explain why DM is important and to figure out which type of DM is best for diagnosing COVID-19 infection quickly and accurately. Alstom to figure out how many layers and neurons should be in each layer. CNN for the most up-to-date information. The proposed techniques for COVID-19 produced impressive results, particularly in CNN, and there's a clear superiority of CNN over the other techniques;the fact that CNN relies on convolution filters produced excellent results through feature extraction due to focusing also on the intended region of the screen without the surrounding area, which resulted in a reduced number of parameters and also the speed of extraction of results with the higher resolution. The collected findings showed that the CNN-based approach has a high accuracy rate when compared to other current methods, with a 99.54% accuracy rate (with 80% training and 20% testing).

A time series forecasting for the cumulative confirmed and critical cases of the covid-19 pandemic in Saudi Arabia using autoregressive integrated moving average (ARIMA) model

Abstract: Reviews at present, different machine learning techniques and algorithms have been applied for predicting significant factors of the Coronavirus Disease-2019 (COVID-19) such as the outbreak and diagnosis. In this study, the most accurate time series forecasting model, namely, the Autoregressive Integrated Moving Average (ARIMA) model is used to forecast the expected cumulative number of confirmed and critical cases in Saudi Arabia for the upcoming months. Additionally, the dataset is collected from the King Abdullah Petroleum Studies and Research Centre (KAPSARC). Acquiring the number of expected cases within a short period is considered crucial as it provides an important knowledge that can be applied by the health sector in containing the COVID-19 pandemic and forming the proper precautions and strategies that are concerned on the public health system. The main finding of this research is that the number of cumulative confirmed cases is expected to increase at a high rate in the upcoming two months, while the number of critical cases is forecasted to increase at a smaller rate compared to the total number of cases. To evaluate the performance of the adopted model, different statistical matrices as the R Squared, Mean Squarer Error, Root Mean Square Error and Mean Absolute Error are used in this research. It is found to be proven from the findings that the proposed model generates an accurate prediction of the expected number of cumulative confirmed and critical cases in the upcoming months. © 2020 Samer H. Atawneh, Osamah A.M. Ghaleb, Ahmad MohdAziz Hussein, Mohammad Al-Madi and Bilal Shehabat.