Introduction: The purpose of this research was to predict mental illness among university students using various machine learning (ML) algorithms. Methods: A structured questionnaire-based online survey was conducted on 2121 university students (private and public) living in Bangladesh. After obtaining informed consent, the participants completed a web-based survey examining sociodemographic variables and behavioral tests (including the Patient Health Questionnaire (PHQ-9) scale and the Generalized Anxiety Disorder Assessment-7 scale). This study applied six well-known ML algorithms, namely logistic regression, random forest (RF), support vector machine (SVM), linear discriminate analysis, K-nearest neighbors, Naïve Bayes, and which were used to predict mental illness among university students from Dhaka city in Bangladesh. Results: Of the 2121 eligible respondents, 45% were male and 55% were female, and approximately 76.9% were 21–25 years old. The prevalence of severe depression and severe anxiety was higher for women than for men. Based on various performance parameters, the results of the accuracy assessment showed that RF outperformed other models for the prediction of depression (89% accuracy), while SVM provided the best result than other models for the prediction of anxiety (91.49% accuracy). Conclusion: Based on these findings, we recommend that the RF algorithm and the SVM algorithm were more moderate than any other ML algorithm used in this study to predict the mental health status of university students in Bangladesh (depression and anxiety, respectively). Finally, this study proposes to apply RF and SVM classification when the prediction of mental illness status is the core interest.

This study aims to investigate factors influencing the adoption of clean energy among households in Bangladesh, using Blinder-Oaxaca decomposition and extended probit regression model with data from the 2019 Bangladesh multiple indicator cluster survey. Small households, primarily Muslim and urban dwellers, who speak the Bengali language and are Internet and mobile users, were likelier to adopt cleaner fuels than their counterparts. On the contrary, households residing in the Barisal, Khulna, Rajshahi, and Rangpur divisions, belonging to poor and middle-class households, with household heads aged 15–64 and without formal education, were less likely to adopt cleaner fuels than their counterparts. The concentration curve revealed socioeconomic inequality in the adoption of clean energy, particularly favouring richer households in urban and rural areas. Further analysis using the Blinder-Oaxaca decomposition showed that urban residents showed a higher probability of adopting clean energy, with a significant difference of 0.508 compared to rural areas. Regarding the endowment effect, poor wealth quintile contributed the most, followed by the ownership of rented dwellings and the middle wealth quintile. The Bengali differential effect made the largest contribution to this aspect of the disparity, followed by the exposure of the Internet and the influence of the Dhaka and Chattogram divisions. The detailed analysis provides valuable insights for policymakers and practitioners on the issue of disparities in the adoption of clean energy between urban and rural areas in Bangladesh.

Introduction. In recent times, Bangladesh has made significant improvements in various health outcomes, but not so much in maternal death. The current flat trend in reducing maternal mortality in Bangladesh has been mainly due to the lower coverage of maternal health care. To improve the coverage, it is essential to find biosocial factors related to adequate maternal health care. Therefore, this study is aimed at finding out the socioeconomic correlates of adequate maternal health care in Bangladesh. Methods. The study used data from the Bangladeshi demographic and health survey 2017‐18. The total unweighted sample of 4012 women who reported pregnancy before three years of the survey was analyzed. A composite binary indicator of adequate maternal care has been constructed using the variables—access to maternal care service, four antenatal care visits, at least one visit with qualified providers, and institutional delivery. A binary logistic regression model was employed to find out the socioeconomic correlate of adequate maternal care. Results. Only 24.4% percent of sample women received adequate maternal care. The result of the logistic regression model shows that urban, Khulna, Rajshahi, and Rangpur were associated with an increase in the odds of having adequate maternal care. High education and health care decisions taken by the partner or husband were also associated with an increased odd of adequate maternal care. Islam and lower wealth status were associated with a lower probability of adequate maternal care. Conclusions. Policymakers and health administration should pay attention to the variation in the utilization of maternal health care across residence, region, religion, education, and wealth status to ensure safe motherhood.

Early development is a vital phase in childhood life. The study aimed to identify factors that were associated with the early development of 36–59 months children in Bangladesh. The findings of this study will formulate the design of appropriate policy and programmed responses.

Purpose: Malnutrition is one of the serious public health problems especially for children and pregnant women in developing countries such as Bangladesh. This study aims to identify the risk factors associated with child nutrition for both male and female children in Bangladesh.Design/methodology/approach: This study was conducted among 23,099 mothers or caretakers of children under five years of age from a nationally representative survey named Bangladesh Multiple Indicator Cluster Survey, 2019. This study used chi-square test statistic for bivariate analysis and multinomial logistic regression was used to evaluate the adjusted effects of those covariates on child nutritional status.Findings: The prevalence of severely malnourished, nourishment was higher for males than females (5.3% vs 5.1%, 77.4% vs 76.8%) while moderately malnourished were higher for females (18.1% vs 17.4%). The findings from the multinomial model insinuated that the mother’s education level, wealth index, region, early child development, mother’s functional difficulties, child disability, reading children's books and diarrhea had a highly significant effect on moderate and severe malnutrition for male children. For the female children model, factors such as mother’s education level, wealth index, fever, child disability, rural, diarrhea, early child development and reading less than three books were significant for moderate and severe malnutrition.Originality/value: There is a solution to any kind of problem and malnutrition is not an exceptional health problem. So, to overcome this problem, policymakers should take effective measures to improve maternal education level, wealth status, child health.

Background. Most maternal deaths occur during childbirth and after childbirth. This study was aimed at determining the trends of health facilities during delivery in Bangladesh, as well as their influencing factors. Methods. This study used secondary data from three Bangladesh Multiple Indicator Cluster Surveys (MICSs) in 2006, 2012–13, and 2019. The study’s target sample was those women who gave birth in the last two years of the survey. A two‐level logistic regression was applied to determine the effects on health facility delivery separately in these two survey points (MICSs 2012–13 and 2019). Results. The results show that the delivery of health facilities has increased by almost 37.4% in Bangladesh, from 16% in 2006 to 53.4% in 2019. The results of two‐level logistic regression show that the total variation in health facility delivery across the community has decreased over recent years. After adding community variables, various individual‐level factors such as women with secondary education (OR = 0.55 in 2012‐13 vs. OR =0.60 in 2019), women from middle wealth status (OR = 0.49 in 2012‐13 vs. OR = 0.65 in 2019), religion, and child ever born showed a strong relationship with health facility delivery in both survey years. At the community level, residents showed significant association only in the 2012‐13 survey and indicated a 43% (OR = 1.43 for 2012‐13) greater availability of health facilities in urban residences than in rural residences. Using media showed a highly significant connection with health facility delivery in both years as well as an increasing trend over the years in Bangladesh (OR = 1.19 in 2012‐13 vs. OR = 1.38 in 2019). However, division, prenatal care, and skilled services all contribute greatly to increasing the delivery of health facilities in Bangladesh. Conclusions. The results of this study suggest that policymakers need to pay attention to individual and community‐level factors, especially women’s education, poverty reduction, and adequate prenatal care provided by well‐trained caregivers.