Regressive Class Modelling for Predicting Trajectories of COVID-19 Fatalities Using Statistical and Machine Learning Models.

The COVID-19 (SARS-CoV-2 virus) pandemic has led to a substantial loss of human life worldwide by providing an unparalleled challenge to the public health system. The economic, psychological, and social disarray generated by the COVID-19 pandemic is devastating. Public health experts and epidemiologists worldwide are struggling to formulate policies on how to control this pandemic as there is no effective vaccine or treatment available which provide long-term immunity against different variants of COVID-19 and to eradicate this virus completely. As the new cases and fatalities are recorded daily or weekly, the responses are likely to be repeated or longitudinally correlated. Thus, studying the impact of available covariates and new cases on deaths from COVID-19 repeatedly would provide significant insights into this pandemic's dynamics. For a better understanding of the dynamics of spread, in this paper, we study the impact of various risk factors on the new cases and deaths over time. To do that, we propose a marginal-conditional based joint modelling approach to predict trajectories, which is crucial to the health policy planners for taking necessary measures. The conditional model is a natural choice to study the underlying property of dependence in consecutive new cases and deaths. Using this model, one can examine the relationship between outcomes and predictors, and it is possible to calculate risks of the sequence of events repeatedly. The advantage of repeated measures is that one can see how individual responses change over time. The predictive accuracy of the proposed model is also compared with various machine learning techniques. The machine learning algorithms used in this paper are extended to accommodate repeated responses. The performance of the proposed model is illustrated using COVID-19 data collected from the Texas Health and Human Services.

Regressive models for risk prediction of repeated multinomial outcomes: An illustration using Health and Retirement Study data.

Life expectancy is increasing in many countries and this may lead to a higher frequency of adverse health outcomes. Therefore, there is a growing demand for predicting the risk of a sequence of events based on specified factors from repeated outcomes. We proposed regressive models and a framework to predict the joint probabilities of a sequence of events for multinomial outcomes from longitudinal studies. The Markov chain is used to link marginal and sequence of conditional probabilities to predict the joint probability. Marginal and sequence of conditional probabilities are estimated using marginal and regressive models. An application is shown using the Health and Retirement Study data. The bias of parameter estimates for all models from all bootstrap simulation is less than 1% in most of the cases. The estimated mean squared error is also very low. Results from the simulation study show negligible bias and the usefulness of the proposed model. The proposed model and framework would be useful to solve real-life problems from various fields and big data analysis.

A generalized right truncated bivariate Poisson regression model with applications to health data.

A generalized right truncated bivariate Poisson regression model is proposed in this paper. Estimation and tests for goodness of fit and over or under dispersion are illustrated for both untruncated and right truncated bivariate Poisson regression models using marginal-conditional approach. Estimation and test procedures are illustrated for bivariate Poisson regression models with applications to Health and Retirement Study data on number of health conditions and the number of health care services utilized. The proposed test statistics are easy to compute and it is evident from the results that the models fit the data very well. A comparison between the right truncated and untruncated bivariate Poisson regression models using the test for nonnested models clearly shows that the truncated model performs significantly better than the untruncated model.

Factors influencing patient satisfaction in primary healthcare clinics in Kuwait.

PURPOSE: To measure the quality of health care services patient satisfaction is used as one of the most important indicators. The study aims to identify factors affecting patient's satisfaction at primary health care clinics. DESIGN/METHODOLOGY/APPROACH: The data was collected during January 2007 and May 2007 through a randomly-distributed questionnaire. The questionnaires were distributed in primary healthcare clinics that represent all heath care regions in Kuwait. A total of 426 completed questionnaires, out of 500, were returned resulting in a response rate of 85.2 percent. FINDINGS: The majority (87 percent) of the patients responded that the time for communication between physician and patient was not enough. Seventy-nine-percent of the surveyed patients said they would go to the emergency room of the hospital in future if needed instead of going to the primary care clinic. Regarding the quality of the communication relationship between physician and patients most of the patients responded negatively. Exploratory factor analysis identified six factors and reliability of overall scale was found to be 0.61. RESEARCH LIMITATIONS/IMPLICATIONS: One limitation to this study was the exclusion of the private sector. ORIGINALITY/VALUE: The authors hope that this study identifies areas of dissatisfaction that can be quickly remedied and ensures enhancement in the areas of satisfaction with ongoing attention and emphasis.

Delivery complications and healthcare-seeking behaviour: the Bangladesh Demographic Health Survey, 1999-2000.

Maternal health services have a potentially critical role in the improvement of reproductive health. The use of health services is related to the availability, quality and cost of the services, as well as to social structure, health beliefs and the personal characteristics of the users. The present paper examined the factors that influence the use of maternal health services for some selected pregnancy-related complications (e.g. prolonged labour, excessive bleeding, high fever/discharge and convulsions) in Bangladesh by using data from the Bangladesh Demographic Health Survey, 1999-2000. It was found that younger mothers were significantly less likely to seek professional healthcare at the time of birth. The odds for rural women seeking healthcare services from a doctor, nurse and/or midwife were half those of urban women. The strong influence of the mothers' education and parity on the utilisation of healthcare services is consistent with findings from other studies. The possession of assets emerged as an important predictor of seeking care from health professionals at the time of birth. Another factor, i.e. a husband's concern about pregnancy complications, showed a significant and positive impact on the utilisation of healthcare services, which is very important for rural women when they are dependent on their spouses. It was observed that the respondents living in urban areas, who had higher levels of education and lower parity, and more assets (used as a proxy for income), visited trained healthcare providers more often and were more likely to use healthcare facilities provided by trained personnel at the time of delivery. This is a reflection of the fact that, irrespective of their needs, only people from higher economic or educational groups can afford to seek healthcare from trained personnel in Bangladesh. In other words, predisposing and enabling factors appear to have a strong association with women's healthcare utilisation during pregnancy.

Factors influencing nurses' attitudes towards the use of computerized health information systems in Kuwaiti hospitals.

AIM: This paper reports a survey of nurses' attitudes towards computerized health information systems, the characteristics that influence these attitudes and the level of nurses' skills in computer use. BACKGROUND: The use of such systems in developed countries and in some developing countries has already become a reality. However, nurses as a group of care providers have been found to resist computerization, seeing computerized health information systems as dehumanizing, confusing and uncaring. Nurses with more computer experience tend to have more positive views; education and training positively influence attitudes; and younger and less experienced nurses may have more positive attitudes. METHODS: A structured questionnaire was used to measure the attitudes of nurses working in Kuwait towards computerization. A random sample of 574 nurses working in Ministry of Health hospitals were sent a questionnaire, and 530 replies were received (response rate 92.3%). The data were collected from November 2002 to January 2003. FINDINGS: Respondents generally had positive attitudes toward computerized health information systems. Analysis of variance revealed statistically significant differences in attitudes in relation to nationality, level of education, previous experience in computer use, and computer skills (P < 0.05). Multiple regression analysis showed that gender, nationality, education levels, and duration of computer use were statistically significant predictors of attitudes toward computerized health information systems (P < 0.05). CONCLUSION: With adequate computerized health information system training, the implementation of computerized health information systems could be effective for nurses in providing quality health care, as found in other studies.

Complications during pregnancy, delivery, and postnatal stages and place of delivery in rural Bangladesh.

The utilization of safe motherhood services including maternity care in Bangladesh is very poor. Only a very small proportion of deliveries takes place in a hospital/clinic. This study is based on data from a follow-up study on maternal morbidity in rural Bangladesh. Analysis is performed on the nature of complications by place of delivery. Most of the deliveries have taken place in the women's own or her mother's home. In addition, home deliveries are mostly assisted either by an untrained birth attendant or by relatives or others. Education, economic status, whether pregnancy was wanted or not, regular visits for antenatal care, past history of breathing problems and liver diseases, and palpitation during pregnancy appear to have significant association with place of delivery in rural Bangladesh. The utilization of a hospital/clinic instead of birth at home is higher among women with secondary or higher level of education, who desired the pregnancy, and who made regular visits for antenatal care. Delivery at a mother's home appears to be positively associated with higher economic status, desired pregnancy, gainful employment, and visits for antenatal care. If the respondents suffer from diseases/symptoms, then it is more likely that the delivery would take place in the mother's home.

Statistical methods for analysis of repeated measures on maternal morbidity.

OBJECTIVES: This paper applies statistical methods to identify factors associated with pregnancy-related complications in rural Bangladesh. The results are examined in order to identify the factors that can help formulate policy for reducing pregnancy-related morbidity. METHODS: Two statistical methods are used in this study to analyse the repeated-measures data on pregnancy-related complications in rural Bangladesh. One method is based on the application of linear logistic regression at each follow up, and the results are compared to identify the potential risk factors. Then the generalised estimating equation (GEE) approach is used, and the results based on each follow up are compared with those obtained from the application of the GEE approach. The maternal morbidity data collected by the Bangladesh Institute of Research for Promotion of Essential and Reproductive Health and Technologies are used in this paper. RESULTS: Economic status, visit for antenatal care, and histories of sexually transmitted disease, hypertension, heart disease and breathing problem are positively associated with the complications during pregnancy, while wanted pregnancy, household type, primary and secondary schooling, and five or more pregnancies are associated negatively with the response variable. Involvement with gainful employment shows a negative association by the first technique. The GEE approach failed to identify some important factors such as history of anaemia, previous pregnancy and gainful employment. However, duration of pregnancy appears to have an association with pregnancy complications, which was not found from the conditional model based on each follow up. CONCLUSION: It appears that unwanted pregnancies need to be reduced through a well-organised and targeted family planning campaign for potential mothers of all ages in rural Bangladesh. Nutritional anaemia may cause various complications, and suggestions are given for reducing anaemia among pregnant women. In the rural areas of Bangladesh, first births usually occur at teenage. The first-birth pregnancy among teenagers can be a source of severe complications. There can be special programs to address the need for delay in the first pregnancy of those who marry at an early age.