25Objectives 26 The current form of severe acute respiratory syndrome called coronavirus disease 2019 27 (COVID-19) caused by a coronavirus (SARS-CoV-2) is a major global health problem. The 28 aim of our study was to use the official epidemiological data and predict the possible outcomes 29 of the COVID-19 pandemic using artificial intelligence (AI)-based RNNs (Recurrent Neural 30 Networks), then compare and validate the predicted and observed data. 31 Materials and Methods 32We used the publicly available datasets of World Health Organization and Johns Hopkins 33 University to create the training dataset, then have used recurrent neural networks (RNNs) with 34 gated recurring units (Long Short-Term Memory -LSTM units) to create 2 Prediction Models. 35Information collected in the first t time-steps were aggregated with a fully connected (dense) 36 neural network layer and a consequent regression output layer to determine the next predicted 37 value. We used root mean squared logarithmic errors (RMSLE) to compare the predicted and 38 observed data, then recalculated the predictions again. 39 Results 40The result of our study underscores that the COVID-19 pandemic is probably a propagated 41 source epidemic, therefore repeated peaks on the epidemic curve (rise of the daily number of 42 the newly diagnosed infections) are to be anticipated. The errors between the predicted and 43 validated data and trends seems to be low. 44 Conclusions 45 3The influence of this pandemic is great worldwide, impact our everyday lifes. Especially 46 decision makers must be aware, that even if strict public health measures are executed and 47 sustained, future peaks of infections are possible. The AI-based predictions might be useful 48 tools for predictions and the models can be recalculated according to the new observed data, 49 to get more precise forecast of the pandemic. 50 51 52 53 54 55 56 57 58 59 60 61 4 62

Objectives The COVID-19 pandemic is considered a major threat to global public health. The aim of our study was to use the official epidemiological data to forecast the epidemic curves (daily new cases) of the COVID-19 using Artificial Intelligence (AI)-based Recurrent Neural Networks (RNNs), then to compare and validate the predicted models with the observed data. Methods We used publicly available datasets from the World Health Organization and Johns Hopkins University to create a training dataset, then we employed RNNs with gated recurring units (Long Short-Term Memory - LSTM units) to create two prediction models. Our proposed approach considers an ensemble-based system, which is realized by interconnecting several neural networks. To achieve the appropriate diversity, we froze some network layers that control the way how the model parameters are updated. In addition, we could provide country-specific predictions by transfer learning, and with extra feature injections from governmental constraints, better predictions in the longer term are achieved. We have calculated the Root Mean Squared Logarithmic Error (RMSLE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) to thoroughly compare our model predictions with the observed data. Results We reported the predicted curves for France, Germany, Hungary, Italy, Spain, the United Kingdom, and the United States of America. The result of our study underscores that the COVID-19 pandemic is a propagated source epidemic, therefore repeated peaks on the epidemic curve are to be anticipated. Besides, the errors between the predicted and validated data and trends seem to be low. Conclusion Our proposed model has shown satisfactory accuracy in predicting the new cases of COVID-19 in certain contexts. The influence of this pandemic is significant worldwide and has already impacted most life domains. Decision-makers must be aware, that even if strict public health measures are executed and sustained, future peaks of infections are possible. The AI-based models are useful tools for forecasting epidemics as these models can be recalculated according to the newly observed data to get a more precise forecasting.

No abstract

No abstract

Background Decreased physical activity significantly increases the probability of prevalent metabolic syndrome (MetS) with substantial impact on the expected course of COPD. Objective Our research aims to assess the metabolic consequences of chronic obstructive pulmonary disease (COPD) and evaluate the prevalence of MetS and its interrelations with age, sex, comorbidities, drug intake, degree of decreased lung function, nutritional status, physical activity and quality of life. Methods A cross-sectional study was performed on a random sample (n = 401) at the Department of Pulmonary Rehabilitation of the National Koranyi Institute of Pulmonology from March 1, 2019 to March 1, 2020 in Budapest, Hungary. Anthropometric and respiratory function tests and laboratory parameters of all patients were registered. Results MetS occurred in 59.1% of COPD patients with significant gender difference (male: 49.7% female: 67.6%). Concerning BMI, the prevalence of MetS was higher with BMI≥25 kg m−2 (P < 0.0001). Patients with this syndrome had significantly worse FEV1%pred (43 (30–56) vs. 47 (36–61); P = 0.028), lower quality of life (CAT: 26 (21–32) vs. 24.5 (19–29); P = 0.049) and significantly more frequent exacerbations (2 (1–3) vs.1 (0–2); P < 0.05), than patients without MetS. The prevalence of comorbidities were higher in overweight/obese patients (BMI> 25 kg m−2). Conclusions In COPD patients MetS negatively affect respiratory function and quality of life and promotes exacerbations of the disease. MetS is related to nutritional status and the level of systemic inflammation in COPD patients.