Machine learning models for prediction of double and triple burdens of non-communicable diseases in Bangladesh.

Increasing prevalence of non-communicable diseases (NCDs) has become the leading cause of death and disability in Bangladesh. Therefore, this study aimed to measure the prevalence of and risk factors for double and triple burden of NCDs (DBNCDs and TBNCDs), considering diabetes, hypertension, and overweight and obesity as well as establish a machine learning approach for predicting DBNCDs and TBNCDs. A total of 12,151 respondents from the 2017 to 2018 Bangladesh Demographic and Health Survey were included in this analysis, where 10%, 27.4%, and 24.3% of respondents had diabetes, hypertension, and overweight and obesity, respectively. Chi-square test and multilevel logistic regression (LR) analysis were applied to select factors associated with DBNCDs and TBNCDs. Furthermore, six classifiers including decision tree (DT), LR, naïve Bayes (NB), k-nearest neighbour (KNN), random forest (RF), and extreme gradient boosting (XGBoost) with three cross-validation protocols (K2, K5, and K10) were adopted to predict the status of DBNCDs and TBNCDs. The classification accuracy (ACC) and area under the curve (AUC) were computed for each protocol and repeated 10 times to make them more robust, and then the average ACC and AUC were computed. The prevalence of DBNCDs and TBNCDs was 14.3% and 2.3%, respectively. The findings of this study revealed that DBNCDs and TBNCDs were significantly influenced by age, sex, marital status, wealth index, education and geographic region. Compared to other classifiers, the RF-based classifier provides the highest ACC and AUC for both DBNCDs (ACC = 81.06% and AUC = 0.93) and TBNCDs (ACC = 88.61% and AUC = 0.97) for the K10 protocol. A combination of considered two-step factor selections and RF-based classifier can better predict the burden of NCDs. The findings of this study suggested that decision-makers might adopt suitable decisions to control and prevent the burden of NCDs using RF classifiers.

Double and triple burden of non-communicable diseases and its determinants among adults in Bangladesh: Evidence from a recent demographic and health survey.

BACKGROUND: Globally, non-communicable diseases (NCDs) are a significant public health problem. NCDs are the leading cause of death in Bangladesh. This study aimed to estimate the prevalence of double burden of NCDs (DBNCDs) and triple burden of NCDs (TBNCDs) such as hypertension, diabetes and overweight or obesity and to explore the risk factors of DBNCDs and TBNCDs in Bangladesh. MATERAILS AND METHODS: This study included 12 685 participants (5465 male and 7220 female) from 2017 - 2018 nationally representative Bangladesh Demographic and Health Survey. Descriptive statistics were calculated for the distribution and prevalence of DBNCDs and TBNCDs. Bivariate and multilevel logistic regression analyses were used to assess the individual- and community-level determinants of DBNCDs and TBNCDs. RESULTS: The prevalence of DBNCDs and TBNCDs was 21.4% and 6.1%, respectively. At individual-level, higher age, female, currently and formerly/ever married, richest, higher education were more likely to suffer from the DBNCDs and TBNCDs. Furthermore, at the community level, the division had a significant association with DBNCDs and TBNCDs. In addition, family size had a significant effect on DBNCDs, and caffeinate drinks and poverty significantly affected TBNCDs. CONCLUSION: Overall, there is a low prevalence of TBNCDs compared with DBNCDs in Bangladesh. Age, gender, marital status, wealth index, education level and division are significantly associated with DBNCDs and TBNCDs. The government and non-government health organisations should pay proper attention to handle the burden of NCDs in Bangladesh.

Socio-demographic factors affecting the first and second dose of measles vaccination status among under-five children: Perspectives from South Asian countries.

Background: The measles vaccine is crucial in preventing fatalities and reducing widespread childhood infections worldwide, yet achieving the desired immunization rates remains a challenge in developing countries. Our study aims to identify the impact of socio-demographic factors on measles vaccination among children in South Asian countries. Methods: Participants (89513) were taken from the most recent Demographic and Health Survey (DHS) datasets of South Asian countries between 2015 and 2021. Descriptive statistics and multivariable analyses were employed to find out the factors associated with measles vaccination among South Asian countries. Results: Our study found that the first dose of vaccinated children was 51.7 % in Afghanistan which is the lowest among South Asian countries. The key determinants related to two doses of measles vaccination include parental characteristics, media access, and antenatal care (ANC). Mothers who had done baby postnatal checkups (AOR = 1.22, CI = 1.17-1.26) and made more than four ANC (AOR = 1.77, CI: 1.65-1.89) were more likely to fully immunize their child than mothers with no postnatal and antenatal checkups. Conclusion: The complete dose of measles vaccination rate in South Asia is still low compared to the first dose of measles vaccination among children. The government and stakeholders should organize frequent awareness programs through media and health personnel to inform people about routine vaccinations to eliminate measles.