Abstract:Background
Nutritional status is an important indicator of health status among adults. However, to date, there exists scanty information on the nutritional status of tribal populations of Bangladesh. The aim of the study was to investigate the nutritional status of tribal (T) and non-tribal (NT) adult people living in the rural area of Rajshahi district, Bangladesh.
Methods
A total of 420 (72 T and 348 NT) households were studied. The samples were selected using multistage stratified sampling with proportion… Show more
“…Calculate the BMI for each respondent in the study using the formula (pre-pregnancy weight in kg/height in meters squared), which categorizes as underweight (<18.5 kg/m2), normal weight (18.5�BMI�24.9 kg/m2), and overweight (�25.0 kg/m2). Previous literature conducted in Asian countries has used the BMI categories recommended by the World Health Organization (WHO) [2,[29][30][31][32][33]. Following this literature, we have used the WHO-recommended BMI categories in our analysis.…”
Section: Study Variables and Measurementmentioning
Aim
Malnutrition in pregnant women significantly affects both mother and child health. This research aims to identify the best machine learning (ML) techniques for predicting the nutritional status of pregnant women in Bangladesh and detect the most essential features based on the best-performed algorithm.
Methods
This study used retrospective cross-sectional data from the Bangladeshi Demographic and Health Survey 2017–18. Different feature transformations and machine learning classifiers were applied to find the best transformation and classification model.
Results
This investigation found that robust scaling outperformed all feature transformation methods. The result shows that the Random Forest algorithm with robust scaling outperforms all other machine learning algorithms with 74.75% accuracy, 57.91% kappa statistics, 73.36% precision, 73.08% recall, and 73.09% f1 score. In addition, the Random Forest algorithm had the highest precision (76.76%) and f1 score (71.71%) for predicting the underweight class, as well as an expected precision of 82.01% and f1 score of 83.78% for the overweight/obese class when compared to other algorithms with a robust scaling method. The respondent’s age, wealth index, region, husband’s education level, husband’s age, and occupation were crucial features for predicting the nutritional status of pregnant women in Bangladesh.
Conclusion
The proposed classifier could help predict the expected outcome and reduce the burden of malnutrition among pregnant women in Bangladesh.
“…Calculate the BMI for each respondent in the study using the formula (pre-pregnancy weight in kg/height in meters squared), which categorizes as underweight (<18.5 kg/m2), normal weight (18.5�BMI�24.9 kg/m2), and overweight (�25.0 kg/m2). Previous literature conducted in Asian countries has used the BMI categories recommended by the World Health Organization (WHO) [2,[29][30][31][32][33]. Following this literature, we have used the WHO-recommended BMI categories in our analysis.…”
Section: Study Variables and Measurementmentioning
Aim
Malnutrition in pregnant women significantly affects both mother and child health. This research aims to identify the best machine learning (ML) techniques for predicting the nutritional status of pregnant women in Bangladesh and detect the most essential features based on the best-performed algorithm.
Methods
This study used retrospective cross-sectional data from the Bangladeshi Demographic and Health Survey 2017–18. Different feature transformations and machine learning classifiers were applied to find the best transformation and classification model.
Results
This investigation found that robust scaling outperformed all feature transformation methods. The result shows that the Random Forest algorithm with robust scaling outperforms all other machine learning algorithms with 74.75% accuracy, 57.91% kappa statistics, 73.36% precision, 73.08% recall, and 73.09% f1 score. In addition, the Random Forest algorithm had the highest precision (76.76%) and f1 score (71.71%) for predicting the underweight class, as well as an expected precision of 82.01% and f1 score of 83.78% for the overweight/obese class when compared to other algorithms with a robust scaling method. The respondent’s age, wealth index, region, husband’s education level, husband’s age, and occupation were crucial features for predicting the nutritional status of pregnant women in Bangladesh.
Conclusion
The proposed classifier could help predict the expected outcome and reduce the burden of malnutrition among pregnant women in Bangladesh.
Background
Child marriage remains an important problem around the world with young mothers and their under-five children often experiencing under-nutrition. The problem is rarely studied in the Bangladeshi population. This paper was designed to identify the association between child marriage and nutritional status of mothers and their under-five children in Bangladesh.
Methods
Nationally representative secondary data was used for this study, data was extracted from the Bangladesh Demographic and Health Survey (BDHS) 2017–18. The sample consisted of 7235 mothers aged 18–49 years and their under-five children. The mothers were classified into two classes according to their age at first marriage: (i) child marriage (marriage at < 18 years) and (ii) not child marriage (marriage at ≥ 18 years). The nutritional status of mothers was measured by body mass index (BMI), and under-five children’s nutritional status was measured by (i) height-for-age (z-score) (stunting), (ii) weight-for-age (z-score) (underweight), and (iii) weight-for-height (z-score) (wasting). The chi-square test and two-level logistic regression model were used for data analysis using SPSS software (IBM version 20).
Results
The prevalence of child marriage among Bangladeshi women was 69.0%, with the mean and median of age at the first marriage being 16.57 ± 2.83 years and 16 years, respectively. Of the mothers, 15.2% suffered from chronic energy deficiency (underweight), and 72.8% were married at < 18 years. The prevalence of stunting, underweight, and wasting among under-five children in Bangladesh was 31.0%, 22.0%, and 8.5%, respectively. Compared to women married at the age of ≥ 18 years, there was a significantly higher likelihood of chronic energy deficiency among women who married at < 18 years [Adjusted OR = 1.27, CI: 1.05–1.82; p < 0.05]. Under-five children of mothers married before the age of 18 were more likely to have stunting [Adjusted OR = 1.201, CI: 1.11–1.72; p < 0.05], wasting [Adjusted OR = 1.519, CI: 1.15-2.00; p < 0.01], and underweight [Adjusted OR = 1.150, CI: 1.09–1.82; p < 0.05] compared to children of mothers who married at age ≥ 18.
Conclusion
The rate of child marriage among Bangladeshi women is high, and it is significantly associated with malnutrition among mothers and their under-five children. The Bangladesh government can use the findings of this study to prevent and reduce child marriage and malnutrition among mothers and their under-five children to achieve sustainable development goals by 2030.
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.