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.
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.
Összefoglaló. Bevezetés: Krónikus obstruktív tüdőbetegségben (COPD) az obesitas mellett a csökkent fizikai aktivitás nagymértékben fokozza a metabolikus szindróma kialakulásának valószínűségét. Célkitűzés: Kutatásunk célja volt felmérni a metabolikus szindróma prevalenciáját COPD-ben, valamint azt, hogy milyen mértékben függ össze az életkorral, a nemmel, a társbetegségekkel, a tüdőfunkció károsodásának mértékével, a tápláltsági állapottal, a fizikai terhelhetőséggel és az életminőséggel. Módszer: Keresztmetszeti vizsgálatot végeztünk az Országos Korányi Pulmonológiai Intézet Légzésrehabilitációs Osztályán fekvő betegek körében 2019. július 1. és december 31. között. A véletlenszerűen kiválasztott 300, 40 év feletti betegnek ismertük az antropometriai, légzésfunkciós vizsgálati eredményét és laboratóriumi paramétereit. Adatokat gyűjtöttünk a dohányzási szokásokról, az előző évi exacerbatiók számáról és a kortikoszteroidok használatáról is. Az életminőség mérésére a betegségspecifikus Szent György-féle Légzési Kérdőív magyar nyelvre validált változatát használtuk. A metabolikus szindrómát a Nemzetközi Diabetes Szövetség kritériumai alapján határoztuk meg. Eredmények: A metabolikus szindróma a betegek 72%-ánál fordult elő, férfi: 65,9% nő: 77,2% (p = 0,031). A metabolikus szindrómás betegek esetében rövidebb 6 perces sétatávolságot mértünk ([m] 250 [150–330] vs. 295 [162–360]; p = 0,384), és szignifikánsan több volt az előző évi exacerbatiók száma (3 [0–6] vs. 1 [1–2]; p<0,001) a nem metabolikus szindrómás betegekhez képest. A BMI-re történő stratifikáció után a metabolikus szindróma jelenléte nagyobb volt BMI≥25 kg/m2 esetén. A hasi elhízás, a magas vérnyomás, a hyperlipidaemia és a hyperglykaemia szignifikánsan gyakoribb volt BMI≥25 kg/m2 esetén (p<0,001). Következtetés: Eredményeink azt sugallják, hogy a metabolikus szindrómás betegekben megnő az együttes morbiditási index, különösen azok körében, akik túlsúlyosak vagy elhízottak. Ezért a COPD-s betegekben nagyon fontos időben felismerni és megfelelően kezelni a metabolikus szindrómát. Orv Hetil. 2021; 162(5): 185–191. Summary. Introduction: Both obesity and the lack of physical activity among chronic obstructive pulmonary disease (COPD) patients increase the risk of developing metabolic syndrome. Objective: The goal of our study was to assess the prevalence of metabolic syndrome among COPD patients and to examine its correlation with age, gender, comorbidities, lung function values, nutritional status, exercise capacity, and quality of life. Method: A cross-sectional study was performed at the Department of Pulmonary Rehabilitation of the Hungarian National Korányi Institute for Pulmonology between July 1st and December 31st, 2019. A total of 300 patients aged over 40 were selected at random. Anthropometric data were collected along with lung function values, laboratory parameters, smoking status, the number of exacerbations in the previous year, and the use of corticosteroids. Quality of life was measured by the validated Hungarian, COPD-specific Saint George Respiratory Questionnaire. Metabolic syndrome was defined according to the International Diabetes Federation criteria. Results: Metabolic syndrome affected 72% of COPD patients (male: 65.9%, female 77.2%; p = 0.031). In patients with metabolic syndrome, shorter 6-minute walking distance was measured ([m] 250 [150–330] vs. 295 [162–360]; p = 0.384) and the number of exacerbations in the previous year was significantly higher (3 [0–6] vs. 1 [1–2]; p<0.001) compared to patients with no metabolic syndrome. After stratification for BMI, metabolic syndrome was more frequent in the case of BMI≥25 kg/m2. Central adiposity, hypertension, hyperlipidemia, and hyperglycemia were also significantly more frequent among patients with BMI≥25 kg/m2 (p<0.001). Conclusion: Our results suggest that the co-morbidity index increases in patients with metabolic syndrome, especially in overweight or obese patients. Therefore, early detection and appropriate treatment of metabolic syndrome in patients with COPD is very important. Orv Hetil. 2021; 162(5): 185–191.
BackgroundAntimicrobial resistance (AMR) is an increasing public health problem worldwide.We studied some patient-related factors that might influence the antimicrobial resistance.and whether the volume of antibiotic prescribing of the primary care physicians correlate with the antibiotic resistance rates of commensal nasal Staphylococcus aureus and Streptococcus pneumoniae.MethodsThe socio-demographic questionnaires, the antibiotic prescription and resistance data of commensal nasal S. aureus and S. pneumoniae were collected in the 20 participating Hungarian practices of the APRES study.Multivariate logistic regression analyses were performed on the patient-related data and the antimicrobial resistance of the S. aureus and S. pneumoniae on individual, patient level.Ecological analyses were performed with Spearman’s rank correlations at practice level, the analyses were performed in the whole sample (all practices) and in the cohorts of primary care practices taking care of adults (adult practices) or children (paediatric practices).ResultsAccording to the multivariate model, age of the patients significantly influenced the antimicrobial resistance of the S. aureus (OR = 0.42, p = 0.004) and S. pneumoniae (OR = 0.89, p < 0.001). Living with children significantly increased the AMR of the S. pneumoniae (OR = 1.23, p = 0.019). In the cohorts of adult or paediatric practices, neither the age nor other variables influenced the AMR of the S. aureus and S. pneumoniae.At practice level, the prescribed volume of penicillins significantly correlated with the resistance rates of the S. aureus isolates to penicillin (rho = 0.57, p = 0.008). The volume of prescribed macrolides, lincosamides showed positive significant correlations with the S. pneumoniae resistance rates to clarithromycin and/or clindamycin in all practices (rho = 0.76, p = 0.001) and in the adult practices (rho = 0.63, p = 0.021).ConclusionsThe age is an important influencing factor of antimicrobial resistance. The results also suggest that there may be an association between the antibiotic prescribing of the primary care providers and the antibiotic resistance of the commensal S. aureus and S. pneumoniae. The role of the primary care physicians in the appropriate antibiotic prescribing is very important to avoid the antibiotic resistance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.