U.S. Unemployment Rate Prediction by Economic Indices in the COVID-19 Pandemic Using Neural Network, Random Forest, and Generalized Linear Regression

Artificial neural network (ANN) has been showing its superior capability of modeling and prediction. Neural network model is capable of incorporating high dimensional data, and the model is significantly complex statistically. Sometimes, the complexity is treated as a Blackbox. However, due to the model complexity, the model is capable of capture and modeling an extensive number of patterns, and the prediction power is much stronger than traditional statistical models. Random forest algorithm is a combination of classification and regression trees, using bootstrap to randomly train the model from a set of data (called training set) and test the prediction by a testing set. Random forest has high prediction speed, moderate variance, and does not require any rescaling or transformation of the dataset. This study validates the relationship between the U.S. unemployment rate and economic indices during the COVID-19 pandemic and constructs three different predictive modeling for unemployment rate by economic indices through neural network, random forest, and generalized linear regression model.

Emotions in online rumor diffusion

Emotions are regarded as a dominant driver of human behavior, and yet their role in online rumor diffusion is largely unexplored. In this study, we empirically study the extent to which emotions explain the diffusion of online rumors. We analyze a large-scale sample of 107,014 online rumors from Twitter, as well as their cascades. For each rumor, the embedded emotions were measured based on eight so-called basic emotions from Plutchik’s wheel of emotions (i.e., anticipation–surprise, anger–fear, trust–disgust, joy–sadness). We then estimated using a generalized linear regression model how emotions are associated with the spread of online rumors in terms of (1) cascade size, (2) cascade lifetime, and (3) structural virality. Our results suggest that rumors conveying anticipation, anger, and trust generate more reshares, spread over longer time horizons, and become more viral. In contrast, a smaller size, lifetime, and virality is found for surprise, fear, and disgust. We further study how the presence of 24 dyadic emotional interactions (i.e., feelings composed of two emotions) is associated with diffusion dynamics. Here, we find that rumors cascades with high degrees of aggressiveness are larger in size, longer-lived, and more viral. Altogether, emotions embedded in online rumors are important determinants of the spreading dynamics.

Determinants of practice of preconception care among women of reproductive age group in southern Ethiopia, 2020: content analysis

Background Preconception care (PCC) is a series of biomedical, mental, and psycho-social health services provided to women and a couple before pregnancy and throughout subsequent pregnancies for desired outcomes. Millions of women and new-borns have died in low-income countries due to impediments that arise before and exaggerate during pregnancies that are not deal with as part of pre-conception care. To the best of our knowledge, however, there is a lack of information about preconception care practice and its determinants in southern Ethiopia, including the study area. This study was therefore planned to assess the practice of preconception care and its determinants among mothers who recently gave birth in Wolkite town, southern Ethiopia, in 2020. Methods A community-based cross-sectional study was conducted from February 1 to 30, 2020. A total of 600 mothers who have given birth in the last 12 months have been randomly selected. A two-stage sampling technique was employed. For data collection, a pre-tested, semi-structured questionnaire was used. The data was encoded and entered into Epi-Data version 3.1 and exported for analysis to SPSS version 23. Household wealth status was determined through the application of principal component analysis(PCA). The practice PCC was considered as a count variable and measured as a minimum score of 0 and a maximum of 10. A bivariable statistical analysis was performed through analysis of variance (ANOVA) and independent t-tests and variables with a p-value of < 0.05 were eligible for the generalized linear regression model. To see the weight of each explanatory variable on PCC utilization, generalized linear regression with a Poisson link was done. Results Of the sampled 600 participants, 591 took part in the study, which yielded a response rate of 98.8%.The mean (± SD) score of the practice of PCC was 3.94 (± 1.98) with minimum and maximum scores of 0 and 10 respectively. Only 6.4% (95%CI: 4.6, 8.6) of mothers received all selected items of PCC services. Thecommonest item received by 67.2% of mothers was Folic acid supplementation, while 16.1% of mothers received the least item of optimizing psychological health. Education status of mother[AOR 0.74, 95%CI 0.63, 0.97], time spent to access nearby health facilities [AOR 0.69, 95%CI 0.58, 0.83], availability of PCC unit [AOR 1.46; 95%CI 1.17, 1.67], mother’s knowledge on PCC [AOR 1.34, 95%CI 1.13, 1.65], being a model household [AOR 1.31, 95%CI 1.18, 1.52] and women’s autonomy in decision making [AOR 0.75, 95%CI 0.64, 0.96] were identified as significant predictors of practice of PCC. Conclusion The uptake of WHO-recommended PCC service elements in the current study area was found to be unsatisfactory. Stakeholders must therefore increase their efforts to align PCC units with existing MNCH service delivery points, improve women's decision-making autonomy, and focus on behavioral change communication to strengthen PCC practice. Plain language summary Preconception care (PCC) is a series of biomedical, mental, and psycho-social health services provided to women and a couple before pregnancy and throughout subsequent pregnancies for better endings. The main goal of the PCC is to improve maternal and child health outcomes, by-promoting wellness and providing preventive care. It can also be seen as an earlier chance for teenage girls, mothers, and children to live a better and longer-term healthy life. Pieces of PCC service packages suggested by the World Health Organization(WHO) are, micronutrient supplementation (Folate supplementation), infectious disease (STI/HIV) screening and testing, chronic disease screening and management, healthy diet therapy, vaccination, prevention of substance use (cessation of cigarette smoking and too much alcohol consumption), optimizing psychological health, counseling on the importance of exercise and reproductive health planning and implementation. Millions of women and new-borns have died in low-income countries due to impediments that arise before and exaggerate during pregnancies that are not deal with as part of pre-conception care. To the best of our knowledge, however, there is a lack of information about preconception care practice and its determinants in southern Ethiopia, including the study area. This study was therefore planned to evaluate the practice of preconception care and its determinants among mothers who recently gave birth in Wolkite town, southern Ethiopia, in 2020. Mothers who have given birth in the last 12 months have been randomly selected Household wealth status was determined through the application of principal component analysis(PCA). To see the weight of each explanatory variable on PCC, generalized linear regression with a Poisson type was done. Accordingly, the Education status of the mother, time spent to access nearby health facilities, availability of PCC unit, mother’s knowledge on PCC, being a model household, and women’s autonomy in decision making were identified as significant predictors of practice of PCC. Stakeholders must therefore increase their efforts to align PCC units with existing MNCH service delivery points, improve women's decision-making autonomy, and focus on behavioral change communication to strengthen PCC practice.

Outcomes associated with comorbid diabetes among patients with COPD exacerbation: findings from the ACURE registry

Background Diabetes is a common comorbidity among patients with exacerbation of chronic obstructive pulmonary disease (AECOPD). Diabetes has been reported to be associated with length of stay (LOS), death, and cost among AECOPD patients. However, most studies are retrospective or have small sample sizes. The association for cost has not been researched using diabetes as a main analytic factor. This study aimed to fill gaps mentioned above, to compare basic characteristics between the diabetic and non-diabetic group, and to detect associations between diabetes and clinical outcomes among patients hospitalized with AECOPD. Methods A total of 5334 AECOPD patients, classified into diabetic and non-diabetic group, were included from a prospective multicenter patient registry study. Generalized linear regression and logistic regression were separately used for the association between diabetes and direct hospitalization cost and the association between diabetes and LOS. Results Generally, diabetic patients had a more severe profile, including being older, more overweight or obese, having more former smokers, more emergency room visits in the past 12 months, and more comorbidities occurrence. Diabetic patients also had worse clinical outcomes, including higher cost and longer LOS. Additionally, the generalized linear regression indicated that the marginal mean cost difference between diabetic and non-diabetic patients was RMB (¥) 775.7. Conclusions AECOPD patients with comorbid diabetes had a more severe profile and higher direct hospitalization cost. Diabetes screening and integrated care programs might help reduce the heavy comorbidity and economic burden. Moreover, corticosteroids and metformin could be considered in the treatment of these patients. Trial registration Clinicaltrials.gov with the identifier NCT0265752.

PLS Generalized Linear Regression and Kernel Multilogit Algorithm (KMA) for Microarray Data Classification Problem

This study involves the implentation of the extensions of the partial least squares generalized linear regression (PLSGLR) by combining it with logistic regression and linear discriminant analysis, to get a partial least squares generalized linear regression-logistic regression model (PLSGLR-log), and a partial least squares generalized linear regression-linear discriminant analysis model (PLSGLRDA). A comparative study of the obtained classifiers with the classical methodologies like the k-nearest neighbours (KNN), linear discriminant analysis (LDA), partial least squares discriminant analysis (PLSDA), ridge partial least squares (RPLS), and support vector machines(SVM) is then carried out. Furthermore, a new methodology known as kernel multilogit algorithm (KMA) is also implemented and its performance compared with those of the other classifiers. The KMA emerged as the best classifier based on the lowest classification error rates compared to the others when applied to the types of data are considered; the un- preprocessed and preprocessed.

Does affordability matter? Examining the trends and patterns in health care expenditure in India

Background Absence of better financing mechanism results in higher out of pocket expenditure and catastrophe, which leads to impoverishment and poverty especially among low- and middle-income countries like India. This paper examines the major characteristics associated with the higher out of pocket expenditure and provides an insight from Andersen’s behavioural model that how predisposing, enabling and need factors influence the level and pattern of out of pocket expenditure in India. Methods Data has been extracted from three rounds of nationally representative consumer expenditure surveys, i.e. 1993–1994, 2004–2005 and 2011–2012 conducted by the Government of India. States were categorized based on regional classification, and adult equivalent scale was used to adjust the household size. Multiple Generalized-Linear-Regression-Model was employed to explore the relative effect of various socio-economic covariates on the level of out of pocket expenditure. Results The gap has widened between advantaged and disadvantaged segment of the population along with noticeable regional disparities among Indian states. Generalized-Linear-Regression-Model indicates that the most influential predisposing and enabling factor determining the level of out of pocket expenditure were age composition, religion, social-group, household type, residence, economic status, sources of cooking and lighting arrangements among the households. Conclusions Present study suggests the need for strengthening the affordability mechanism of the households to cope with the excessive burden of health care payments. Furthermore, special consideration is required to accommodate the needs of the elderly, rural, backward states and impoverishment segment of population to reduce the unjust burden of out of pocket expenditure in India.