Fat mass prediction equations and reference ranges for Saudi Arabian Children aged 8-12 years using machine technique method

Background

The number of children with obesity has increased in Saudi Arabia, which is a significant public health concern. Early diagnosis of childhood obesity and screening of the prevalence is needed using a simple in situ method. This study aims to generate statistical equations to predict body fat percentage (BF%) for Saudi children by employing machine learning technology and to establish gender and age-specific body fat reference range.

Methods

Data was combined from two cross-sectional studies conducted in Saudi Arabia for 1,292 boys and girls aged 8-12 years. Body fat was measured in both studies using bio-electrical impedance analysis devices. Height and weight were measured and body mass index was calculated and classified according to CDC 2,000 charts. A total of 603 girls and 374 boys were randomly selected for the learning phase, and 153 girls and 93 boys were employed in the validation set. Analyses of different machine learning methods showed that an accurate, sensitive model could be created. Two regression models were trained and fitted with the construction samples and validated. Gradient boosting algorithm was employed to achieve a better estimation and produce the equations, then the root means squared error (RMSE) equation was performed to decrease the error. Body fat reference ranges were derived for children aged 8-12 years.

Results

For the gradient boosting models, the predicted fat percentage values were more aligned with the true value than those in regression models. Gradient boosting achieved better performance than the regression equation as it combined multiple simple models into a single composite model to take advantage of that weak classifier. The developed predictive model archived RMSE of 3.12 for girls and 2.48 boys. BF% and Fat mass index charts were presented in which cut-offs for 5th, 75th and 95th centiles are used to define 'under-fat', 'normal', 'overfat' and 'subject with obesity'.

Conclusion

Machine learning models could represent a significant advancement for investigators studying adiposity-related issues in children. These models and newly developed centile charts could be useful tools for the estimation and classification of BF%.

Lifestyle Habits: Diet, physical activity and sleep duration among Omani adolescents

OBJECTIVES

This study aimed to investigate the lifestyle habits-physical activity (PA), eating habits (EH), and sleep duration (SD)-of Omani adolescents, and to examine gender differences in such variables.

METHODS

802 Omani adolescents (442 females and 360 males), aged 15-18 years were randomly recruited. Anthropometric indices, PA level, and EH and SD were evaluated by the Arab Teenage Lifestyle questionnaire. A semi-quantitative food frequency questionnaire for dietary assessment was also administered.

RESULTS

The results showed that although the study subjects had a sedentary lifestyle (lack of PA, average of 6.7 hours sleep, and consumption of high calorie foods), they maintained a normal body mass (less than 25 Kg/m(2)). Males were more than twice as active as females. With respect to EH, there were few gender differences, except in dairy and meat consumption where 62.5% and 55.5% of males consumed more than 3 servings, respectively, compared to 18.78 % and 35.2% of females, respectively. In addition, waist/height ratio, height, reasons for being active, energy drinks, potato consumption, eating sweets, vigorous PA and breakfast EHs were statistically significant independent predictors for BMI, P <0.05 for both males and females.

CONCLUSION

This study revealed a high prevalence of sedentary behaviors and a low level of physical activity, especially among females. Unhealthy dietary habits were also widely found among both genders. There is an urgent need for more research as well as a national policy promoting active living and healthy eating and discouraging sedentary behaviour among Omani adolescents.

Female university students' physical activity levels and associated factors--a cross-sectional study in southwestern Saudi Arabia

Background: The high prevalence of physical inactivity in Saudi Arabia is a growing challenge to public health. This study aimed to examine the prevalence of physical activity (PA) and associated factors among female university students. Methods: This cross-sectional study involved 663 randomly selected female university students who completed the Arab Teens Life Style questionnaire. Data included measurements of anthropometric, socioeconomic and environmental factors, as well as self-reported PA. Ordinal regression was used to identify associated factors with low, moderate and high PA levels. Results: The mean age of participants was 20.4 years (SD 1.5). Mean BMI of the students in relation to PA were 23.0, 22.9, 22.1 for high, moderate and low levels of activity, respectively. The analysis revealed significantly higher PA levels among married students, those with high educated mothers, and those who lived far from parks, and lower activity levels among underweight students. Conclusions: This study raises four important determinants for female university students’ PA levels. These factors could be of great importance in the endeavor to prevent the health-threatening increase in physical inactivity patterns and thus non-communicable diseases and obesity where the focus should be on the specific situation and needs of women in Saudi Arabia.

Obesity, physical activity and sedentary behavior amongst British and Saudi youth: a cross-cultural study

This study explores differences in weight status, obesity and patterns of physical activity (PA) in relation to gender and age of youth from two culturally, environmentally and geographically diverse countries, the United Kingdom (UK) and Saudi Arabia (SA). A total of 2,290 males and females (15-17 years) volunteered to participate in this study. Participants completed a validated self-report questionnaire that contained 47 items relating to patterns of PA, sedentary activity and eating habits. The questionnaire allows the calculation of total energy expenditure in metabolic equivalent (MET-min) values per week. Significant differences in percentage of overweight/obese and levels of PA were evident between the youth from the two countries, with males being generally more physically active than females. Additionally, there were significant associations between Body Mass Index (BMI), PA and sedentary behaviors; the youth with higher BMI reported lower levels of PA and higher amounts of sedentary time. These findings highlight the diverse nature of lifestyle of youth living in different geographical areas of the world and the need for further research to explore the socio-cultural factors that impact on the prevalence of obesity and patterns of PA of youth in different populations.