Comparative study of physical activity of hypertensives and normotensives: A cross-sectional study of adults in Saudi Arabia

Improving Accuracy for Diabetes Mellitus Prediction by Using Deepnet

Diabetes is a salient issue and a significant health care concern for many nations. The forecast for the prevalence of diabetes is on the rise. Hence, building a prediction machine learning model to assist in the identification of diabetic patients is of great interest. This study aims to create a machine learning model that is capable of predicting diabetes with high performance. The following study used the BigML platform to train four machine learning algorithms, namely, Deepnet, Models (decision tree), Ensemble and Logistic Regression, on data sets collected from the Ministry of National Guard Hospital Affairs (MNGHA) in Saudi Arabia between the years of 2013 and 2015. The comparative evaluation criteria for the four algorithms examined included; Accuracy, Precision, Recall, F-measure and PhiCoefficient. Results show that the Deepnet algorithm achieved higher performance compared to other machine learning algorithms based on various evaluation matrices.

A systematic review of physical activity and sedentary behaviour research in the oil-producing countries of the Arabian Peninsula

BACKGROUND

The dramatic rise in Noncommunicable Diseases (NCD) in the oil-producing countries of the Arabian Peninsula is driven in part by insufficient physical activity, one of the five main contributors to health risk in the region. The aim of this paper is to review the available evidence on physical activity and sedentary behaviour for this region. Based on the findings, we prioritize an agenda for research that could inform policy initiatives with regional relevance.

METHODS

We reviewed regional evidence on physical activity and sedentary behaviour to identify the needs for prevention and policy-related research. A literature search of peer-reviewed publications in the English language was conducted in May 2016 using PubMed, Web of Science and Google Scholar. 100 studies were identified and classified using the Behavioural Epidemiology Framework.

RESULTS

Review findings demonstrate that research relevant to NCD prevention is underdeveloped in the region. A majority of the studies were epidemiological in approach with few being large-scale population-based studies using standardised measures. Correlates demonstrated expected associations with health outcomes, low levels of physical activity (particularly among young people), high levels of sedentary behaviour (particularly among men and young people) and expected associations of known correlates (e.g. gender, age, education, time, self-motivation, social support, and access). Very few studies offered recommendations for translating research findings into practice.

CONCLUSIONS

Further research on the determinants of physical activity and sedentary behaviour in the Arabian Peninsula using standard assessment tools is urgently needed. Priority research includes examining these behaviours across the four domains (household, work, transport and leisure). Intervention research focusing on the sectors of education, health and sports sectors is recommended. Furthermore, adapting and testing international examples to the local context would help identify culturally relevant policy and programmatic interventions for the region.

Economic costs of diabetes in Saudi Arabia

BACKGROUND

Diabetes imposes a large economic burden on the individual, national healthcare systems, and countries.

OBJECTIVE

To determine the economic impact of diabetes mellitus on Saudi healthcare system, both now and in the future.

MATERIALS AND METHODS

This research study uses a prevalence-based approach that combines the demographics of the population (classified by nationality, sex and age group) with and without diagnosed diabetes in 1992 and 2010. The economic impact of diabetes is estimated in this study, using secondary sources of information provided by Ministry of Health, Ministry of Finance and Central Department of Statistics and Information databases.

RESULTS

People diagnosed with diabetes, on average, have medical healthcare expenditures that are ten times higher ($3,686 vs. $380) than what expenditures would be in the absence of diabetes. Over 96% of all medical healthcare expenditures attributed to diabetes are incurred by persons of Saudi nationality, with the remaining 4% incurred by persons of non-Saudi nationality. The population age 45-60 incurs 45% of diabetes-attributed costs, with the remaining population under age 15 incurs 3.8%, age 15-44 incurs 27.5%, and age 60 and above incurs 23.8%.

CONCLUSION

The actual national healthcare burden because of diabetes is likely to exceed the $0.87 billion estimated in this study, because it omits the indirect costs associated with diabetes, such as absenteeism, lost productivity from disease-related absenteeism, unemployment from disease-related disability, lost productivity due to early mortality by disease. The social cost of intangibles such as pain and suffering and care provided by non-paid caregivers as well as healthcare system administrative costs, cost of medications, clinician training programs, and research and infrastructure development is also omitted from this research study. Further studies are needed to confirm the present findings and to improve our understanding of economic costs of diabetes and its related complications.