Data Modeling, Non-parametric Estimation, Bio-informatics, Econometrics, Big Data.

https://www.researchgate.net/profile/Md-Uddin-205

https://scholar.google.com/citations?hl=en&user=zcG1Ej8AAAAJ

Dr. Md. Mahabubur Rahman is a Professor of Statistics and Data Science, Islamic University, Kushtia, Bangladesh. He received the Ph.D. degree in Statistics from the King Abdulaziz University, KSA. His research interests are in the areas of mathematical statistics as well as transmuted distribution theory. He has published several research articles extensively in internationally refereed journals. He is the referee of several mathematical journals.

Distribution Theory; Mathematical Statistics, Data Science

https://www.researchgate.net/profile/Md-Mahabubur-Rahman

https://scholar.google.com/citations?user=GpJsqPoAAAAJ

In this article, we have proposed a general transmuted family of distributions with an emphasis on the cubic transmuted family of distributions. This new class of distributions provides additional flexibility in modeling the bi-modal data. The proposed cubic transmuted family of distributions has been linked with the T-X family of distributions proposed by Alzaatreh et al. (2013). Some members of the proposed family of distributions have been discussed. The cubic transmuted exponential distribution has been discussed in detail and various statistical properties of the distribution have been explored. The maximum likelihood estimation for parameters of cubic transmuted exponential distribution has also been discussed alongside the Monte Carlo simulation study to assess the performance of the estimation procedure. Finally, the cubic transmuted exponential distribution has been fitted to real datasets to investigate its applicability.

In this paper, we have introduced a new family of general transmuted distributions and have studied the cubic transmuted family of distributions in detail. This new class of distributions offers more distributional flexibility when bi-modality appears in the data sets. Some special members of the proposed cubic transmuted family of distributions have been discussed. We have investigated, in detail, the proposed cubic transmuted family of distributions for parent exponential distribution. The statistical properties along with the reliability behavior for the cubic transmuted exponential distribution have been studied. We have obtained the expressions for single and joint order statistics when a sample is available from the cubic transmuted exponential distribution. Maximum likelihood estimation of parameters for cubic transmuted exponential distribution has also been discussed. We have also discussed the simulation and real data applications of the proposed distribution.

In this article, we have proposed the cubic transmuted Pareto distribution, by using the cubic transmuted family of distributions introduced by Rahman et al. (in Pak J Stat Oper Res 14:451–469, 2018). We have explored the distribution in detail and statistical properties of the distribution have been studied. The parameter estimation for the distribution has been discussed and the performance of estimators is studied by conducting an extensive simulation study. Finally, the cubic transmuted Pareto distribution has been fitted on two real datasets to investigate its applicability.

In this paper, a cubic transmuted Weibull (CTW ) distribution has been proposed by using the general family of transmuted distributions introduced by Rahman et al. (Pak J Stat Oper Res 14:451–469, 2018). We have explored the proposed CTW distribution in detail and have studied its statistical properties as well. The parameter estimation and inference procedure for the proposed distribution have been discussed. We have conducted a simulation study to observe the performance of the estimation technique. Finally, we have considered two real-life data sets to investigate the practicality of the proposed CTW distribution.

In this article, a new cubic transmuted (CT) family of distributions has been proposed by adding one more parameter. We have introduced cubic transmuted uniform (CTU) distribution by using the proposed class. We have also provided a detailed description of the statistical properties of the proposed CTU distribution along with its estimation and real-life application.

Transmutation is the functional composition of the cumulative distribution function (cdf) of one distribution with the inverse cumulative distribution function (quantile function) of another. Shaw and Buckley(2007), first apply this concept and introduced a quadratic transmuted family of distributions. In this article, we have presented a review of the transmuted families of distributions. We have also listed the transmuted distributions, available in the literature along with some concluding remarks.

In this paper, a cubic transmutation approach, proposed by Rahman et al. (EJPAM, 12(3):1106-1121, 2019), is used to introduce the cubic transmuted Burr-XII distribution. The distributional properties like moments, moment generating function, characteristic function, quantile function, reliability function, and hazard rate function are discussed for the proposed distribution along with the distributions of different order statistics. The maximum likelihood estimation of the model parameters has been discussed for the proposed distribution. In order to investigate the applicability of the proposed distribution two real-life applications have been considered.

In this paper, we propose a new cubic transmuted Pareto (CTP) distribution via employing the cubic transmuted family introduced by Rahman et al. (PJSOR, 14(4): 807-829). Derivation of statistical properties along with the distribution of order statistics have been discussed for the CTP distribution. Certain characterizations of the CTP distribution are presented. Maximum likelihood estimation of the model parameters has been conducted alongside an extensive Monte Carlo simulation study to assess the performance of the estimation procedure. Finally, two real-life applications have been considered to investigate the applicability of the CTP distribution.

In this paper, we have given some general results for the general transmuted families of distributions introduced by Rahman et al. (2018a,b). These results are helpful to obtain the results for any member of the general families of distributions and their special cases. We have given some examples for illustration.

In the present study, we propose a new family of distributions namely the Pareto-X family. A sub model of the proposed family called Pareto-Weibull (PW) distribution is discussed. The maximum likelihood estimators of the model parameters are obtained. Different distributional properties of the distribution are described. In order to assess the applicability of the model, two real-life applications from environmental and biological study are considered. The practical applications show that the proposed model provides better fitness than any other models used in this study.

Statistician always tries to find an easy method that gives a suitable fit. However, proposing a new distribution always solves many statistical problems. In this paper, we introduce a new extension of the Lindley distribution. We made a statistical inference under complete and Type-II censored sample on a new extension of the Lindley distribution. We have deduced its PDF and CDF using a cubic transmuted family that is because the new equations are very easy in computation. We called the new form the cubic transmuted Lindley distribution. The probability distribution function and the cumulative distribution function were also written as a closed form along with some mathematical properties. The classical method, which is the maximum likelihood estimation technique and maximum product of spacing technique, was used to find the estimators of the unknown model parameters. At last, to prove the superiority and applicability of the model, three real data sets are implemented and compared using the proposed method. We made a comparison with some of its baseline distributions and some other extensions, and our model outperforms the published ones.

Background and aimsThe key interest of this research is to identify the causes of the ongoing increasing trends in caesarean section or C-section (CS) deliveries in both urban and rural areas of Bangladesh.Methods This study analyzed all Bangladesh Demographic and Health Survey (BDHS) datasets through Chi-square and z tests and the multivariable logistic regression model.ResultsCS deliveries were found to be more prevalent in urban than in rural areas of Bangladesh. Mothers above 19 years, above 16 years at first birth, overweight mothers, those with higher educational levels, those who received more than one antenatal care (ANC) visit, fathers having secondary/higher education degrees and employed as workers or in business, and mothers living in wealthy households in the cities of Dhaka, Khulna, Mymensingh, Rajshahi, and Rangpur divisions had a significantly higher likelihood of CS deliveries in urban areas. Contrastingly, mothers with ages between 20 and 39 years, above 20 years at first birth, normal weight/overweight mothers, those with primary to higher level of education, those in the business profession, fathers who also received primary to higher education, mothers who received more than one ANC visit, and those living in wealthy households in Dhaka, Khulna, Mymensingh, Rajshahi, and Rangpur divisions were more likely to have CS deliveries in rural areas. The 45–49 age group mothers had a five times higher likelihood of CS deliveries [odds ratio (OR): 5.39] in urban areas than in rural areas. Wealthy mothers were more likely to be CS-delivered in urban (OR: 4.84) than in rural areas (OR: 3.67).Conclusion The findings reveal a gradual upward alarming trend in CS deliveries with an unequal contribution of significant determinants in urban and rural areas of Bangladesh. Therefore, integrated community-level awareness programs are an urgent need in accordance with the findings on the risks of CS and the benefits of vaginal deliveries in this country.

In order to improve the inverse Lindley distribution's data modeling abilities in a variety of fields (such as biology, engineering, mortality, etc.), a new adaptation of the inverse Lindley distribution known as the Cubic Transmuted Inverse Lindley (CTIL) distribution has been developed in this article using the cubic transmutation approach. Several statistical and mathematical properties are extracted for this proposed model. The parameters of this proposed model are achieved through the method of maximum likelihood. Finally, the generated model's potential can be proven here by the comprehensive study of the data analysis and graphical representation with the others selected model.

Statistical methodologies have a wider range of practical applications in every applied sector including education, reliability, management, hydrology, and healthcare sciences. Among the mentioned sectors, the implementation of statistical models in health sectors is very crucial. In the recent era, researchers have shown a deep interest in using the trigonometric function to develop new statistical methodologies. In this article, we propose a new statistical methodology using the trigonometric function, namely, a new trigonometric sine-G family of distribution. A subcase (special member) of the new trigonometric sine-G method called a new trigonometric sine-Weibull distribution is studied. The estimators of the new trigonometric sine-Weibull distribution are derived. A simulation study of the new trigonometric sine-Weibull distribution is also provided. The applicability of the new trigonometric sine-Weibull distribution is shown by considering a data set taken from the biomedical sector. Furthermore, we introduce an attribute control chart for the lifetime of an entity that follows the new trigonometric sine-Weibull distribution in terms of the number of failure items before a fixed time period is investigated. The performance of the suggested chart is investigated using the average run length. A comparative study and real example are given for the proposed control chart. Based on our study of the existing literature, we did not find any published work on the development of a control chart using new probability distributions that are developed based on the trigonometric function. This surprising gap is a key and interesting motivation of this research.

I am Dr. Md. Sazzad Hossain, Professor in the Department of Statistics and Data Science at Islamic University, Kushtia, Bangladesh. I hold a PhD in Economics and have over 14 years of academic and research experience. My research interests include applied statistics, econometrics, time series forecasting, agricultural economics, and socioeconomic analysis. I have published numerous research articles in national and international journals, contributing to statistical modeling and evidence-based research.

Econometrics, Public Finance, Agricultural Economics

https://www.researchgate.net/profile/Md-Sazzad-Hossain-29

https://scholar.google.com/citations?user=_muOZL0AAAAJ&hl=en

Although it is a topic of global concern, climate change implementation is typically regional. Finding an adequate Vector Autoregression (VAR) model to predict temperature, rainfall, and cloud coverage for the Jessore region of Bangladesh was the goal of this research project. The stationarity of variables was determined by ADF, PP, and KPSS unit root tests. Granger causality test was used to verify the endogenity among the variables. Employing AIC, VAR (11) model found best. The parameters associated with the model were estimated using the ordinary least square approach. Forecast error variance decomposition and impulse response function were utilized to reveal structural analysis, and the outcome revealed endogenous in the future. The predicted value showed a trend toward increasing temperature and a trend toward decreasing rainfall and cloud coverage.

Australia is a leading developed country which is indispensable a proper planning and management of power generation. To take a unique planning decision forecasting of electricity production is badly in need so that electricity generation copes with the demand of the electricity smoothly. The main task of this study is to assess the performance of two time series models in forecasting electricity generation in Australia. Two time series forecasting methods such as ARIMA and Holt-Winter’s additive trend and seasonality smoothing methods are considered. Applying Theil’s U-statistic as the key performance measure, the study concludes that Holtwinter’s method is more appropriate model.

Islamic University, Bangladesh Abstract-The main objective of this study is to examine the existing situation of results of the graduate students at Islamic University in Kushtia, Bangladesh as well as to identify the factors associated behind this issue. An analysis has been performed by using the primary data which collected form the graduate students of Islamic University under simple random sampling technique. Chi-square test for dependency checking has been performed as Bivariate analysis. After performing Bivariate analysis Multinomial logistic regression analysis has been performed. The result of the study has revealed that the factors like SSC and HSC results of the student, Parental academic qualification, Higher family income, residential in hall, student’s class attendance, study time without class period have a positive impact and the factors like students’ internet use for non-academic purpose, political status, mobile phone using for non academic purpose in the University have a negative impact of students academic resu

The main objective of the current study is to examine the existing situation of female early age at first cohabitation in Bangladesh as well as to identify the factors associated behind this issue. An analysis has been performed by using the secondary data of Bangladesh Demographic and Health Survey (BDHS), 2011. Chi-square test for dependency checking has been performed as bivariate analysis. After performing bivariate analysis, binary logistic regression analysis has been performed. To identify the significant variable, stepwise regression method has also been performed. The result of the study has revealed that women education, household economic status, area of residence, religion and geographical location have significant contribution for adolescent cohabitation. From this study it can be concluded that females who has low education and low socioeconomic status are more likely to enter into cohabitation at early adulthood.

Under-five mortality has remained a significant public health concern in Bangladesh despite a consistent decline over the previous few years. The purpose of this study was to identify the socioeconomic and demographic risk factors for under-five mortality in Bangladesh. Data from the 2017–18 Bangladesh Demographic and Health Survey are used in the study. The study outcome variable was survival time, which was obtained from the variable age at death for the event and the current age of the child for the censored observation. Based on literature assessment, nine covariates were chosen for this study. Product-Limit (P-L) estimator and Log-Rank tests were performed to assess the association between the outcome variables and the selected covariates. The Cox proportional hazard model was also employed in this study to identify potential risk factors for under-five mortality. After fitting the Cox PH model, the factors that significantly affect under-5 mortality include mother's age at birth (< 20), mother's age at birth (> 30), and Sylhet division. Children whose mothers were under 20 and over 30 years old have mortality rates that are 47.5% and 68.7% higher, respectively, than children whose mothers were between the ages of 20 and 30. Regional differences had an impact on child mortality as well. Children in the divisions of Barisal, Rangpur, Khulna, Mymensingh, and Sylhet had death rates that were, in comparison to children in the division of Dhaka, 5.5%, 7.8%, 9.6%, 11.2%, and 55.3% higher.

The study examines the impact and signs of key macroeconomic factors on Bangladesh’s economic growth from 1980 to 2016 using VAR, the Johansen cointegration test, and the Vector Error Correction Model (VECM). Results show that the inflation rate has a slightly positive impact on economic growth, but it is not statistically significant. The real interest rate has a significant negative impact on economic growth, while the exchange rate has a significant positive impact. This work concludes that all variables have long-term effects and long-run causality, as well as a weak short-run influence on the economic growth rate.

In this paper, we discuss some major applications of Kakutani’s fixed point theorem in game theory. In the course of research work we mostly use the idea of mathematical set, functions, topological properties and Brouwer’s fixed point theorem to make the Kakutani’s fixed point theorem more conspicuous. In the key point of idea, we include how this theory can play the effective role to highlight new fixed point results and their applications in different fields of game theory.

ARIMA modelling has become a key tool of analysing climatic variables. To forecast rainfall of a particular region adequately time series ARIMA model may help the farmer as well as water management authority indispensably. For our study purpose, we take data from Bangladesh Meteorological Department (BMD) of Faridpur region for the period January1983 to December 2014. From our analysis ARIMA(0,0,0)(2,0,2)12 model was found that’s why this developed model were used for forecasting monthly Precipitation for next three years to take proper decision of water development management authority. The Akike information criteria, MSE, MAD, and MAPE were applied to test the accuracy and applicability of the developed ARIMA model at different stages

This study attempts to explore the impacts of some demographic, economic and cultural factor's effects on overseas employment of female workers as well as on overseas employment of total workers from Bangladesh. The Gravity model of trade is applied here with the panel data of 12 countries and 22 years. The random effect analysis is applied since some variables which are time-invariant and important for the study.  The main gravity variables – Gross Domestic Product (GDP), population and distance- are found to be well fitted with literatures with expected signs and level of significance. The magnitude of impacts differs for female overseas workers than total overseas workers. The study reveals that while the effect of religion is insignificant in case of total overseas employment its impact on female overseas employment is highly significant. The negative effects of language variables for both types of employments reflect the fact that most of the workers specially women workers migrated to abroad as home maid and didn't get the training on official language of Bangladesh, English. Furthermore, the opportunity of earnings at destination countries proxied by remittances flows from those countries to Bangladesh has highly positive impact and the magnitude is higher for female overseas workers. The study suggests policies and required support services should be provided to mitigate the migration cost. Also, countries with higher GDP, similar religion and higher income, networking and employment opportunities should be chosen as potential new labour market for the female workers of Bangladesh. Keywords: Female worker's overseas Employment, Gravity Model, Panel Data, Random Effect Analysis, BangladeshJEL Classifications: E24, C130DOI: https://doi.org/10.32479/ijefi.11626

Health Economics, Applied Microeconomics, Economic Geography, Empirical Macroeconomics, Statistical Learning

0

https://scholar.google.com/citations?user=O5TNuzcAAAAJ&hl=en

Abstract: The use of GARCH type models and computational-intelligence-based techniques for forecasting financial time series has been proved extremely successful in recent times. In this article, we apply the finite mixture of ARMA-GARCH model instead of AR or ARMA models to compare with the standard BP and SVM in forecasting financial time series (daily stock market index returns and exchange rate returns). We do not apply the pure GARCH model as the finite mixture of the ARMA-GARCH model outperforms the pure GARCH model. These models are evaluated on five performance metrics or criteria. Our experiment shows that the SVM model outperforms both the finite mixture of ARMA-GARCH and BP models in deviation performance criteria. In direction performance criteria, the finite mixture of ARMA-GARCH model performs better. The memory property of these forecasting techniques is also examined using the behavior of forecasted values vis-à-vis the original values. Only the SVM model shows long memory property in forecasting financial returns.

This paper aims to examine the impacts of remittances on the economic development of four South Asian countries: Bangladesh, India, Pakistan and Sri Lanka. The study considers the World Bank’s balanced panel data (1977–2017). The dynamic ordinary least-square approach finds mixed results, which explain the realisation of the pluralistic approach. Evidence shows that remittances directly increase gross domestic product, household consumption and expenditure and decreases government consumption expenditure, inflation and population growth. However, the flow of remittances is not promoting private bank credit; rather it increases import-dominated trade. Besides, remittances are yet to be significant at gross capital formation. Therefore, we recommend that policymakers should find a way to bring remittance through formal channels for capital formation and investment. Fortunately, remittance inflows indirectly cause population control and sustainability. Decision-makers should also formulate policies that will modify remittance-induced current production and consumption patterns to promote the process of sustainable development further.

Cancer epidemiology, HIV, Hepatitis C Virus (HCV) and sexually-transmitted infections (STIs); sexual risk behaviors, apply statistical methods on infectious diseases

0

Md. Matiur Rahman Molla is currently serving as an Associate Professor in the Department of Statistics and Data Science at Islamic University, Bangladesh—the largest university in the southwestern region of the country. Before holding his current position, he served in the same department as a Lecturer and later as an Assistant Professor. Earlier in his career, he worked as a Teaching Assistant (TA) at East West University, Dhaka, one of the country’s premier private universities known for academic excellence. He is deeply interested in collaborative and interdisciplinary research, particularly in the fields of machine learning, deep learning, and the development of automated software tools using generative AI, API integration, and AI-driven decision-support systems. A firm believer in interdisciplinary collaboration, he actively engages in cross-domain research, combining classical statistical techniques with modern computational intelligence. Mr. Molla has published several research articles in peer-reviewed international journals, reflecting his ongoing contributions to the advancement of data science and artificial intelligence in academic and applied settings.

Time Series Analysis, Machine Learning, Deep Learning, NLP, Generative AI

Abstract

The aim of the study was to detect trends in salient key climate variables in the Jessore region of Bangladesh for the years 1985–2014, and the data was collected from the Bangladesh Meteorological Department (BMD). Annual rainfall, annual maximum temperature, and annual cloud coverage were analyzed using the non-parametric Mann-Kendall test, linear regression, and LOWESS curve to detect trends in the series. The rainfall and cloud coverage showed a decline trend at a rate of (4.50 mm/year; 45.02 mm/decade) and (0.045 octas/year; 0.45829 oktas/decade), respectively, whereas temperature manifested an increment trend (0.0285°C/year; 0.2854°C/decade), where cloud coverage was the only significant variable. The structural breakdown point was found using the graphical method and the Chow test, which showed in 2004 that both the series containing breakdown points and cloud coverage exhibit statistical significance.

ABSTRACT: Although it is a topic of global concern, climate change implementation is typically regional. Finding an adequate Vector Autoregression (VAR) model to predict temperature, rainfall, and cloud coverage for the Jessore region of Bangladesh was the goal of this research project. The stationarity of variables was determined by ADF, PP, and KPSS unit root tests. Granger causality test was used to verify the endogenity among the variables. Employing AIC, VAR (11) model found best. The parameters associated with the model were estimated using the ordinary least square approach. Forecast error variance decomposition and impulse response function were utilized to reveal structural analysis, and the outcome revealed endogenous in the future. The predicted value showed a trend toward increasing temperature and a trend toward decreasing rainfall and cloud coverage.

Abstract: Under-five mortality has remained a significant public health concern in Bangladesh despite a consistent decline over the previous few years. The purpose of this study was to identify the socioeconomic and demographic risk factors for under-five mortality in Bangladesh. Data from the 2017–18 Bangladesh Demographic and Health Survey are used in the study. The study outcome variable was survival time, which was obtained from the variable age at death for the event and the current age of the child for the censored observation. Based on literature assessment, nine covariates were chosen for this study. Product-Limit (P-L) estimator and Log-Rank tests were performed to assess the association between the outcome variables and the selected covariates. The Cox proportional hazard model was also employed in this study to identify potential risk factors for under-five mortality. After fitting the Cox PH model, the factors that significantly affect under-5 mortality include mother's age at birth (< 20), mother's age at birth (> 30), and Sylhet division. Children whose mothers were under 20 and over 30 years old have mortality rates that are 47.5% and 68.7% higher, respectively, than children whose mothers were between the ages of 20 and 30. Regional differences had an impact on child mortality as well. Children in the divisions of Barisal, Rangpur, Khulna, Mymensingh, and Sylhet had death rates that were, in comparison to children in the division of Dhaka, 5.5%, 7.8%, 9.6%, 11.2%, and 55.3% higher.

Abstract

SARS-CoV-2, a novel coronavirus discovered in Wuhan, China is spreading quickly and has a high incidence rate around the globe. As a result, everyone on the planet is having difficulty adjusting to the effects of Corona and is unable to foresee the devastation and disaster caused by COVID-19. In this work, we predict the survival status of patients infected with coronavirus using three distinct machine learning (ML) techniques: Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR). We also assess the classification performances of these algorithms. Here, we put out a hybrid model and evaluated it against the three previously discussed machine learning techniques. The outcomes demonstrated the 97.85% prediction accuracy of our suggested hybrid model. Aside from our suggested hybrid model, the random forest machine learning method demonstrated the highest accuracy of 94.62% among the three. Nonetheless, the prediction accuracy of the hybrid model outperforms that of the random forest and is significantly better than that of the other three ML techniques. The classification performances were assessed using the F-score, sensitivity, specificity, and precision metrics. Using 10-fold cross-validation, ROC assessments and confusion matrices produced by these machine learning algorithms were provided and examined. to assess the effectiveness of the classification. These machine learning algorithms' ROC assessments and confusion matrices are shown and examined by 10-fold cross-validation.

Dr. Md. Shohel Rana is an Associate Professor in the Department of Statistics and Data Science at Islamic University, Kushtia, Bangladesh. He holds a Ph.D. in Statistics, with research interests in probability distributions, stochastic modeling, applied statistics, time series analysis, data science, artificial intelligence, and machine learning. His research focuses on developing and applying statistical distributions, statistical modeling, simulation, and data-driven methods to real-world problems. He has authored and co-authored research publications in statistical theory, probability distributions, forecasting, and machine learning applications. He is also actively involved in teaching undergraduate and postgraduate courses in statistics and related disciplines.

Distribution Theory, Stochastic Modeling, Time Series Analysis, Mathematical Statistics, Data Science , Biostatistics, Public Health

https://www.researchgate.net/profile/Md-Rana-26?ev=hdr_xprf

Abstract

Background Premenstrual tension (PMT) syndrome is an important condition that affects women’s psychological, physical, and behavioral well-being, as well as their academic performance. This study investigates the association between premenstrual tension (PMT) symptom severity and academic performance among female university students.

Methods A cross-sectional study was conducted over an 8-month from January to August 2025 among 273 female students of Islamic University, Bangladesh. A reliable, self-administered, bilingual questionnaire was developed based on the Diagnostic and Statistical Manual of Mental Disorders, Fifth edition (DSM-5) criteria to collect the primary data. It was used to assess the prevalence and severity of psychological, behavioral, and physical symptoms as well as their impact on academic performance. Data were analyzed using SPSS (version 25.0) and Python (Pandas, NumPy, SciPy, and Matplotlib). The Chi-square test was used to examine the association between PMT and academic outcomes.

Results A total of 273 participants were selected from 976 eligible female students. The age of the participants ranged from 17 to ≥ 25 years, with a median age category of 23–24 years. The prevalence of premenstrual tension (PMT) symptoms was 65.2%, while 8.1% of participants met the criteria for premenstrual dysphoric disorder (PMDD). Severe mood swings (39.6%) and irritability (37.0%) were identified as the most frequently reported symptoms. A statistically significant association was observed between PMT and academic performance indicators, including difficulty concentrating in class (69.6%, p = 0.013), negative impact on examination performance (64.4%, p = 0.012), and difficulty participating in extracurricular activities (60.0%, p = 0.009). Overall, 54.9% of the female university students reported that their academic performance was negatively affected by premenstrual symptoms.

Conclusion Our study revealed a high prevalence of premenstrual tension (PMT) and premenstrual dysphoric disorder (PMDD) among female university students, with severe psychological symptoms such as mood swings and irritability negatively affecting concentration, examination performance, and participation in extracurricular activities. The findings underscore the importance of raising awareness, implementing targeted mental health support, and providing appropriate interventions to improve academic performance and overall well-being.

Keywords Premenstrual tension syndrome, Premenstrual dysphoric disorder, Academic performance, Female students, Bangladesh

ABSTRACT

Background: Hepatitis B virus (HBV) infection is a significant public health problem globally. In Bangladesh, viral hepatitis is the most common liver disease, with approximately 10 million people infected with HBV.

Methods: The study was a cross‐sectional survey in which 440 respondents were randomly selected using Cochran's formula. The duration of the study was about 6 month (24th August 2024 to 28th February 2025). Data was gathered using a predesigned and structured questionnaire, which was distributed among the students. The collected data were then analysed utilizing Microsoft Excel 2016 and Stata 17 software for statistical processing and interpretation.

Results: Overall, the study found that respondents had a high level of awareness of hepatitis B, with most participants recognizing the disease and its major transmission routes and health consequences. Vaccine‐related knowledge was moderate, whereas hepatitis B vaccination uptake remained relatively low among the respondents and their family members. The mean (±SD) awareness, vaccine knowledge, and perception scores were 37.18 ± 11.16, 25.00 ± 10.88, and 22.38 ± 4.71 (each measured on a 50‐point scale), respectively. Multivariable logistic regression analysis showed that male participants were more likely to be vaccinated against hepatitis B than female participants (aOR = 1.74, 95% CI: 1.14–2.67). Participants with low awareness also had higher odds of being vaccinated than those with high awareness (aOR = 2.17, 95% CI: 1.09–4.36), while no significant association was observed for moderate awareness.

Conclusion: Less than half of the respondents had received the hepatitis B vaccine, with the most common reason for non‐ vaccination being a lack of awareness of their vaccination status. Slightly over half of the respondents demonstrated satisfactory knowledge, attitudes, and practices regarding hepatitis B. These findings underscore the need for targeted education on hepatitis B infection, its risk factors, and the importance of vaccination among students in Bangladesh.

Public Health, Biostatistics and Bioinformatics

0

https://scholar.google.com/citations?user=Fb4XtZgAAAAJ&hl=en

Tobacco is identified as leading modifiable global disease risk factor. The main objective of this paper is to determine the level of knowledge of the health consequences of smoking among Bangladeshi adults and its correlates. Another objective is to observe attitudes towards tobacco use. The study is based on secondary data of size 9629 aged 15 years and above collected by the Global Adult Tobacco Survey (GATS), 2010. Binary logistic regression model has been used to identify the correlates of knowledge about the adverse effect of tobacco use in Bangladesh. Attitudes towards tobacco use have been analyzed, too.

Background: Tobacco use is a manmade manner which causes severe chronic diseases and Bangladesh is one of the most tobacco prevalent countries in the world. Advertisement and promotion events may have a big contribution to accelerate this. Therefore, this study aimed to analyze the advertisement and promotion events that encouraged the tobacco user. 

Data and methods: Secondary data of sample size 9629 collected by the Global Adult Tobacco Survey (GATS), 2010 has been used. Along with descriptive analysis, binary logistic regression has been used to analyze the sociodemographic and economic correlates to be encouraged by marketing policy. 
Results: The most common site for noticing cigarette, bidi and smokeless tobacco product advertisements was in stores (49.90%, 26.25% and 13.97%). From logistic regression it has been found that rural respondents are 1.17 times more inspired to smoke (OR=1.17, 95% CI=1.06, 1.30) from marketing policy than urban respondents. Female respondents are less inspired to smoke (OR=0.24, 95% CI=0.20, 0.28) than male respondents. Older respondents are less inspired to smoke by marketing policy than younger respondents (OR=0.98, 95% CI=0.98, 0.99). On the other hand, Rural respondents are 1.15 times more likely to be inspired to use smokeless product than urban respondents (OR=1.15, 95% CI=1.02, 1.31). Female respondents are 0.63 times less inspired to use smokeless tobacco product than male respondents (OR=0.63, 95% CI=0.51, 0.77) by marketing policy. Older respondents are less inspired to use smokeless tobacco products by marketing policy than younger respondents (OR=0.99, 95% CI=0.98, 0.99). 
Conclusion: To reduce tobacco use in Bangladesh, Government, policy makers and research institutions that are working for reduction of tobacco use should pay attention more on young, student and female to advocate more. Also, Government could take action to limit advertisement in selling store.

Bangladesh experiences mild to devastating floods during the monsoon season of every year due to its geographical location. Whatever nature these floods may possess, they can be both a curse and a blessing for the people of this country. Self-reporting of Bangladesh Household Income and Expenditure Survey (HIES) 2016 provides us with an opportunity to analyze the direct impact of the flood on the households’ development outcomes, such as income, expenditure, assets, and labor market outcomes at a microlevel. We also use the government report to identify the households that were treated in the report as being flooded but did not report as so in the HIES 2016. We use these two measures of flood exposure to estimate the full economic impact of monsoon floods and investigate any spillover effect to verify the preciseness of flood identification measure of self-reporting. Our modified control group meticulously strengthen the argument of flood impact and inaccuracy of its self-reporting by revealing households’ inhuman displacement in education and health expenditures. Though some river-centric trade centers offer employment and income increases for households, Bangladesh seems to lose its antique blessing of silt-laden flood water to replenish the fertility of flooded crop fields.

Objectives The study aimed to determine the prevalence and identify the associated factors of undernutrition among children under 5 years of age living in riverbank erosion areas in Bangladesh. Study design A community- based cross- sectional study. Setting The study was carried out in riverbank erosion- prone areas of the Tangail and Kushtia districts of Bangladesh, which were selected because they are highly vulnerable to riverbank erosion and related livelihood disruptions. Participants Participants were selected using a two- stage cluster sampling technique based on the criterion that mothers had at least one child under the age of 5 years. Outcomes Stunting, wasting and underweight were considered independently as outcome variables to assess nutritional status. Methods Descriptive analysis was performed to determine the prevalence of undernutrition, while the χ² test and multivariable Poisson regression model were used to identify significantly associated factors with undernutrition among children under 5 years of age in riverbank erosion areas. Results The average prevalence of stunting, wasting and underweight was 37.74%, 22.64% and 9.81%, respectively. Results from the Poisson regression model showed that children who were average or large in size at birth had a much lower prevalence of all forms of undernutrition compared with those born very small. Female children had a 30% lower prevalence of stunting compared with male children. In addition, having educated parents, receiving four or more antenatal care visits and household livestock ownership were each associated with a lower prevalence of undernutrition. Conclusion The prevalence of stunting in this study was higher than that reported in the most recent Bangladesh Demographic and Health Survey 2022. Child size at birth, sex, parental education, antenatal care visits and household livestock ownership were identified as significantly associated factors with undernutrition in riverbank erosion areas of Bangladesh.

Background: Child malnutrition remains a major global public health concern, with a disproportionately higher burden in developing countries such as Bangladesh. It is a leading contributor to childhood morbidity and mortality and has long-term consequences for physical growth, cognitive development, educational attainment, and adult productivity. Multiple socioeconomic and demographic factors are responsible for this condition. Therefore, this study aims to identify the factors associated with child malnutrition in Bangladesh using multivariate analytical approaches. Methods: In this study, malnutrition-related data from the Bangladesh Demographic and Health Survey (BDHS) 2022 were used. Multivariate analysis of variance (MANOVA) and multivariate linear regression models were performed to identify significant factors of child malnutrition in Bangladesh (p < 0.05). Results: Multivariate linear regression analysis showed that the Z-scores for heightfor-age (HAZ), weight-for-age (WAZ), and weight-for-height (WAH) among children aged 12–23 months were significantly lower compared to those aged È

Suman Biswas is currently working as an Assistant Professor at the Department of Statistics of Islamic University, Kushtia. Before joining his recent position, he worked as a Lecturer at the same department. He worked as a Scientific Officer (Statistics) at the Bangladesh Agricultural Research Institute—the largest multi-crop research institute in Bangladesh. He has also research working experience in the Centre for Policy Dialogue (CPD) which is the leading institution for in-depth research and dialogue to promote inclusive policymaking in Bangladesh. Biswas has expertise in applying advanced methodologies, tools and techniques for solving real-life examples. He is fascinated by collaborative and interdisciplinary research including the recent advances in machine learning and cloud-based computational facilities. He has published several research articles in different peer-reviewed international journals.

Machine Learning, Deep Learning, Data Science, Public Health

https://www.researchgate.net/profile/Suman-Biswas-2

https://scholar.google.com/citations?user=carHN6EAAAAJ&hl=en

Extreme temperature is the key indicator of extreme climatic events. The goal of this research was to better understand the long-term trends and shifting behaviors associated with Bangladesh’s record-breaking high temperatures in the country’s atmosphere. Data from 26 Bangladeshi meteorological stations collected between 1981 and 2018 was analyzed with RClimDex. The annual count of warm (cold) spell duration increased, according to the findings (decrease). In the coastal regions, this rising temperature trend is more pronounced. There were longer (shorter) periods of warm (cold) weather in the twentieth century than there were in the previous decade. As a result, the length of warm (cold) spells has become longer since the beginning of the twenty-first century, as compared to the last quarter of the twentieth century. There is little fluctuation in diurnal temperatures, but they are getting smaller and smaller. There is a 13% decrease in the Cold Spell Duration Indicator (CSDI), which indicates that we are in for a long, cold winter. At a rate of 14% per year, the Warm Spell Duration Indicator (WSDI) annual count suggests an extremely hot summer is imminent. Diurnal temperature range (DTR) values decreased by 1.1% year-round, raising the specter of climate extremes like the CSDI and WSD. An increasing (decreasing) trend in indicators of how long hot (cold) weather lasts indicates an increase (decrease) in Bangladesh’s warm atmosphere. As a result, an increase in the number of extreme weather events, particularly along the coasts, should be expected across the country.

Burmese grape (Baccaurea ramiflora Lour.) is a minor fruit plant grown in subtropical countries and is rich in different vitamins and minerals. In this study, fruit traits diversity of 23 Burmese grape accessions were assessed through multivariate analysis and application of covariance matrix in locating promising parents for an auspicious crossing program. Among the four clusters, assemblages III and VI dominated maximum number of fruit traits constitutions. Surrounded by the fruit traits constitution, the first principal axis largely affords 46.14% of the variation. Intergenotypic gap was observed highest (30.42) between the fruit traits constitution BS004 and BS019, followed by genetic constitution BS003 and BS004 (29.40). The maximum intracluster distance was noticed (40.50) for cluster IV, whereas cluster I showed the lowest intracluster distance (35.32). In between assemblages I and V, the highest interassemblage distance (835.77) was computed. On the other hand, the lowest distance (105.75) was computed between assemblages II and assemblage V. Observation indicated that higher intercluster differences were noticed than intracluster differences, and this recommended ample fruit traits variation among the fruit traits constitution of different clusters. With respect to both quantitative parameters’ assemblage, CL004, CL010 from cluster I was quite diverse compared with all other assemblages, which is pertinent for a productive crossing program.

To meet the demand for an appropriate soaking duration and priming type, there is a need to embrace cheap, fast, natural, accessible, and adaptable physiological techniques as soaking of seeds in water and fresh cow milk. Fresh cow milk contains hormones that relieve seeds from photo, thermo, physiological and mechanical dormancy. In light of this, this study was conducted to assess the effect of hydration and fresh cow milk on different seed quality attributes like germination percentage, mean germination time, the uncertainty of germination process, and synchrony of germination process of bitter gourd seeds. The study involved two factors namely hydropriming and different concentrations of fresh cow milk (viz. 60%, 80% and 100%), and the other factor was seed soaking duration with 4 levels (i. e., 0, 12, 18 and 24 hours). The experiment was conducted in a Complete Randomized Design (CRD) with three replicates. Results revealed that the percentage germination value of seeds soaked in all concentrations of fresh cow milk was better than hydropriming. A significant germination percentage value of 96% and 93% were recorded for seeds treated for 18 hours in 80% and 100% concentrations of fresh cow milk respectively. Maximum uncertainty of the germination process and minimum synchrony of germination the process was recorded in untreated seed.

Applying an alternative econometric approach, this paper evaluates the long-run causal relationship between the Quantum Index of Manufacturing (QIM) and financial development. We use monthly data of Bangladesh for the period from 2004 to 2017 and apply dynamic factor model (DFM) and vector auto-regression (VAR) based Granger causality approach. Following the results of DFM, two factors, named as ‘Stock Market’ and ‘Banking Sector’ are formed with their respective variables or indicators. Results of factors-and-VAR based Granger causality exhibit a bidirectional relationship between QIM and ‘Banking Sector’ significantly causing each other. There are strong evidences that Bangladesh government has long been employing huge policy efforts (under neoliberal structural adjustment) on fostering supply leading approach, to increase industrial production by developing its stock market. But result shows a unidirectional and demand following relationship; the stock market is being developed in response to the demand of industrial production only. Since the existing relationship does not support government’s policy, its efforts might be missing due to the market’s deregulation-led inefficient and instable deepening. So, Bangladesh government should leave the ideology of fostering supply leading approach to economic growth and adopt policy efforts to let the demand following relationship function.

This study examines the structural dependency between the developments of banking sector and stock market of Bangladesh using canonical correlation analysis. The main objective is to check whether the developments of these two financial sectors independently behave in the economic activities of Bangladesh using monthly data from 2006 to 2015. The development of banking sector is measured by a set of four indicators or variables, private sector credit, total number of branches of scheduled banks, interest rate spread and non-performing loan. Similarly another set of indicators, stock market capitalization, number of listed companies, turnover ratio and stock price volatility are used to explain the development of stock market. The multivariate time series of the two set of indicators are ensured first to be the stationary one. Then the canonical correlation analysis between the two set of indicators show that private sector credit, total No. of branches of scheduled banks are the first set of variables contribute more to construct the first canonical variate of banking sector. Market capitalization and number of listed companies are the second set of variables contribute more to construct the first canonical variate of stock market development. Finally, the correlation between the first pair of canonical variates is 0.293. Since the correlation is positive but not significant, banking and stock market developments do not significantly complement each other. Thus it is concluded that the developments of the two financial systems have been independently running during the period in financing economic activities of Bangladesh from 2006 to 2015.

To understand the finance-growth nexus, this paper is intended to find a fewer number of important financial factors using Factor Analysis on some selected indicators of Bangladesh financial sector during the period 1988-2013. This paper then tries to check whether the identified financial factors cause economic growth or economic growth causes financial factors using the Granger – Causality test. Factor Analysis shows that financial indicators under the dimensions, depth and stability form Factor 1, and the indicators under the dimensions, use/access and efficiency form Factor 2. Being consistent with economic sense, Granger – Causality test shows that no financial factor significantly causes economic growth; rather economic growth causes “depth/stability” (‘private credit + capitalization’ /non-performing loan) factor of financial sector during the period. In summary, on average, financial sector of Bangladesh is being unstably (being increased non-performing loan) deepened with response to the demand of economic growth since 1988.

The main objective of this study is to examine the existing situation of results of the graduate students at Islamic University in Kushtia, Bangladesh as well as to identify the factors associated behind this issue. An analysis has been performed by using the primary data which collected form the graduate students of Islamic University under simple random sampling technique. Chi-square test for dependency checking has been performed as Bivariate analysis. After performing Bivariate analysis Multinomial logistic regression analysis has been performed. The result of the study has revealed that the factors like SSC and HSC results of the student, Parental academic qualification, Higher family income, residential in hall, student’s class attendance, study time without class period have a positive impact and the factors like students’ internet use for non-academic purpose, political status, mobile phone using for non academic purpose in the University have a negative impact of students academic results.

Bangladesh wants to achieve the millennium development goals which is related to infant and under-five mortality by the year 2015. To achieve the goals it is needed to reduce the child mortality and to reduce mortality in Bangladesh it is needed to determine the determinants of mortality. Thus the main purpose of this study is to find the determinants of under-five mortality in Bangladesh. The objective of this study is to determine the impact of parental, socioeconomic, demographic, environmental, and nutritional and health seeking variables on under-five mortality. This study used the data extracted from Bangladesh demographic and health survey (BDHS). Chi-square test for dependency checking and multivariate proportional hazard analysis techniques are used to investigate the effects of those variables on under-five mortality. The study results show that several socioeconomic, demographic, nutritional, environmental and health related variables affect on under-five mortality. Multivariate hazards analysis results show that father’s education, region of residence, preceding birth interval, number of children under-five years of age, mother’s age, contraceptive use and breastfeeding have significant effect on under-five mortality. In this study it has revealed that the environmental, demographic, nutritional and health seeking variables have highly significant impact on under-five mortality than the socioeconomic variables. So we should give attention to these influencing variables to reduce the rate of under-five mortality in Bangladesh.

Determination of the critical limit (CL) for nutritionally essential zinc (Zn) is very important in developing fertilizer recommendations for crops and soils. However, the CL of Zn for the lentil crop has not been determined yet in Bangladesh, leading to the use of a fertilizer rate for the crop estimated on the basis of old critical limit generalised for all crops. A study was conducted in the Greenhouse facilities of the Soil Science Division of BARI, Gazipur, from October to April (Rabi season) of 2018/2019 and 2019/2020, to determine Zinc CL for soils and lentil crop in soils collected at twenty locations encompassing the six Agro-Ecological Zones (AEZs) of Bangladesh. For extraction of available Zn concentrations from soils and lentil biomass, a diethylene triamine penta acetic acid (DTPA)(0.005 M) solution was used. The DTPA-extractable Zn (mg kg-1) in the soils were from 0.43 to 4.10 and from 0.52 to 4.20 in 2018/2019 and 2019/2020, respectively. In all seasons, accessible Zn had negative but substantial correlations with soil pH, soil P, Ca, and Mg in available forms, but the association between available Zn and lentil dry matter was positive and significant (DM). Soil Zn had also a positive significant correlation with Zn concentration of lentil tissue Zn (0.501**). In 2018-2019 and 2019-2020, the CL of EDTA-extractable Zn was determined to be 0.75 mg kg-1 and 0.68 mg kg-1 in soils for lentil crop (0.72 mg kg-1 on an average), respectively, while it was 48.6 mg kg-1 for lentil tissue. The revised CL can be used for fertilizer recommendation for the lentil crop in the entire Gangetic Plains and other Agro-Ecological Zones of Bangladesh.

Heat stress is a major abiotic constraint limiting barley (Hordeum vulgare L.) productivity in regions experiencing rising temperatures. This study evaluated the genetic variability and morphophysiological as well as yield responses of 50 barley genotypes under control and heat-stressed conditions to identify superior lines for thermotolerance breeding. A completely randomized design (CRD) with replications was used, and data was collected for ten morpho-physiological and yield traits. Analysis of variance (ANOVA) indicated highly significant (p ≤ 0.001) effects of genotype, treatment, and their interaction on most of the measured traits. Wide phenotypic variation was observed for grain yield (1.62–9.60 g plant⁻¹) and thousand-grain weight (19.18–40.02 g). High genotypic and phenotypic coefficients of variation, heritability, and genetic advance for grain yield plant⁻¹, total biomass accumulation plant⁻¹, and leaf area plant⁻¹ indicated strong additive genetic control. Correlation and network analyses showed strong positive associations among plant height, total biomass accumulation plant⁻¹, chlorophyll content, leaf area plant⁻¹, thousand-grain weight, and grain yield plant⁻¹. Heatmap clustering and the multi-trait genotype-ideotype distance index (MGIDI) identified BD7194, BD7188, BD8579, BD9681, and IBON14 as best heat-tolerant genotypes. Principal component analysis (PCA) revealed variation primarily driven by grain yield plant⁻¹, leaf area plant⁻¹, and number grains spike⁻¹. Overall, these findings demonstrate substantial genetic variation for heat tolerance and identify promising genotypes that can be used as valuable resources for developing climate-resilient barley cultivars suited to heating environments.

Breast cancer (BC) remains a leading cause of mortality worldwide, highlighting the urgent need for accurate and early diagnosis. Although deep learning models have shown promise in automating histopathological image classification, traditional CNNs often struggle to capture global contextual information and may suffer from issues such as vanishing gradients. This paper proposes SNM-TransNet, a novel hybrid architecture designed to address these limitations for precise BC classification. The model combines a CNN backbone for local feature extraction with a multi-head self-attention Transformer encoder to model long-range dependencies within tissue structures. A key innovation is the Dual Statistical Normalized Mish (SNMish) activation function, a normalized variant of the Mish activation function, which enhances gradient flow, stabilizes training, and improves feature representation compared to the standard ReLU. Evaluated on the BreakHis dataset across multiple magnifications (40X, 100X, 200X, 400X), SNM-TransNet consistently outperforms a ReLU-based variant, ReLU-TransNet, and several pre-trained state-of-the-art models. At 100 X magnification, it achieved a peak accuracy of 97.60 %, a precision of 99.33 %, and an ROC-AUC value of 99.24 %. To ensure clinical trust and interpretability, LIME was integrated, providing transparent visualizations by highlighting diagnostically relevant regions. These results demonstrate that SNM-TransNet offers a robust, accurate, and interpretable framework for BC diagnosis.

Overweight/obesity has become a critical global health issue, as these conditions are strongly associated with elevated risk of diabetes, stroke, cardiovascular disorders, and certain types of cancer. In recent decades, Bangladesh has faced a notable rise in overweight/obesity prevalence—women are more prone to obesity than men. This study presents a comprehensive strategy for identifying risk factors and predicting overweight and obesity through machine learning (ML) classifiers among ever-married Bangladeshi women aged 15–49 years. Data from the 2017–2018 BDHS, a nationally representative survey, were examined. The data were pre-processed and subsequently balanced using the synthetic minority over-sampling technique and edited nearest neighbors (SMOTE-ENN) approach. Various feature identification techniques, including Chi-Square, LASSO, and Sequential Forward Selection, were employed to determine the key risk features. Later, permutation feature importance and SHAP analysis were employed to assess the influence of these risk factors on overweight/obesity. The classification of overweight and obesity was conducted using seven machine learning models: Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), K-nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Multilayer Perceptron (MLP). Among the evaluated models, SVM performed best, reaching 95.79% accuracy and 97.32% precision when combined with SMOTE-ENN and hyper-parameter tuning. The study found that key factors contributing to being overweight/obese include age, division, type of residence, educational levels of both the respondent and her partner, number of children, frequency of television viewing, and wealth status; where wealth status, age, and frequency of watching television have strong influences. Therefore, integrating the balancing algorithm with the embedded feature selection strategy was effective in classifying overweight/obese women and could enhance decision-making for preventive measures in public health through timely predictions of overweight/obesity.

Despite substantial improvements in institutional delivery rates, significant socioeconomic and regional disparities persist in Bangladesh. Addressing these inequalities remains crucial to ensuring equitable maternal healthcare and achieving the Sustainable Development Goals (SDGs).

This study used nationally representative data from the 2022 Bangladesh Demographic and Health Survey (BDHS), comprising 4,433 women aged 15–49 years. Multilevel binary logistic regression models were estimated within a Bayesian framework via the brms package in R. We specified five hierarchical models—null, individual, household, community, and full—to identify factors associated with institutional delivery. Adjusted odds ratios (AORs) with 95% credible intervals (CrIs) are reported. Model adequacy was evaluated via the widely applicable information criterion (WAIC) and leave-one-out information criterion (LOOIC). Weakly informative priors were applied, and sensitivity analyses using alternative prior specifications were conducted to evaluate the robustness of posterior estimates.

The full model showed a proportional change in variance (PCV) of approximately 59.9%, indicating a substantial reduction in between-cluster variance after adjustment for socioeconomic and demographic characteristics. The overall prevalence of institutional delivery was 63.5%. Antenatal care (ANC) visits and household wealth were the strongest predictors. Women who attended 4 + ANC visits (AOR = 7.83; 95% CrI: 5.51–11.26) and those in the richest wealth quintile (AOR = 2.76; 95% CrI: 1.94–3.89) had higher odds of delivering in a health facility. Higher maternal education (AOR = 2.87) and lower birth order (AOR = 0.57) were significant predictors. Conversely, women in paid employment had 17% lower odds of institutional delivery (AOR = 0.83). Pronounced divisional (e.g., Khulna vs. Sylhet) and significant religious disparities were also observed.

Institutional delivery in Bangladesh is associated with a complex interplay of individual-, household-, and community-level factors, with antenatal care (ANC) visits and household wealth demonstrating the strongest associations. Persistent socioeconomic and geographic disparities, particularly in Barishal, Sylhet, and Mymensingh, highlight the need for targeted, multilevel interventions. MOR = 2.09 and PCV = 59.9% indicate the need for policies targeting cluster-level inequalities, household wealth, and education through combined efforts in poverty reduction and health promotion.

Autism spectrum disorder (ASD) is a neurodevelopmental illness that impairs children’s cognitive, linguistic, and social abilities. While a cure for ASD remains elusive, determining its crucial risk factors and corresponding preventive measures can aid in lessening its incidence and severity. Therefore, the objective of this study is to determine the most significant sociodemographic risk factors associated with ASD among Bangladeshi children and adolescents. In particular, it evaluates the effectiveness of various machine learning classifiers and explores feature selection techniques to identify the most dominant predictors of ASD. To accomplish this, two feature selection strategies—chi-square and F-classify—were applied to extract the most significant features, followed by training eight different machine learning algorithms on full and reduced datasets. Rigorous evaluation using eight distinct metrics revealed that the tree-based algorithm, especially the decision tree, when trained on the F-classify feature subset, exhibited superior performance, achieving the highest accuracy and precision of 99.4%. The most influential features associated with ASD included maternal age, stress during pregnancy, parental illness, family history of ASD, birth asphyxia, and consanguinity.

Integrating multi-omics data can improve breast cancer subtype classification by capturing complementary molecular information from mRNA, miRNA, and DNA methylation profiles. However, many existing approaches rely on single- or pairwise-omics integration and do not explicitly model hierarchical regulatory interactions across molecular layers, limiting biological interpretability and predictive performance. In this study, we propose HCAM-BRCA, a Hierarchical Cross-Attention Multi-omics framework for breast cancer subtype classification and biomarker discovery. The proposed architecture integrates mRNA, miRNA, and DNA methylation data using modality-specific self-attention and cross-attention mechanisms to capture both intra-omics feature dependencies and inter-omics regulatory relationships. The learned low-dimensional embeddings were subsequently evaluated using multiple machine learning classifiers. Across all classifiers, HCAM-BRCA consistently demonstrated improved performance pairwise RNA-miRNA and RNA-CpG integration strategies. Among the evaluated models, CatBoost achieved the highest macro-average MCC (0.7628 ± 0.0130), while Extra Trees attained the highest AUPRC (0.8925 ± 0.0032). The proposed framework demonstrated strong and stable subtype discrimination, particularly for the clinically challenging Luminal B and Her2-enriched subtypes. Performance metrics were reported as mean ± standard deviation across five-fold cross-validation. Attention-based feature prioritization identified biologically relevant genes associated with transcriptional regulation, chromatin organization, immune signaling, and cancer-related pathways. Survival analysis further revealed several subtype-specific prognostic associations, including CUX1, MYZAP, and CEBPA in Basal-like tumors, HOXA10 and HLA-DQA2 in Luminal B, and GDF10 and ZNF879 in Her2-enriched tumors. Overall, HCAM-BRCA provides an interpretable and biologically informed multi-omics integration framework that combines robust subtype classification with clinically relevant biomarker prioritization, demonstrating its potential utility for computational oncology and precision breast cancer research.

Silvia Khanam is an Assistant Professor in the Department of Statistics at Islamic University, Kushtia, Bangladesh. She obtained her B.S. and M.S. degrees in Applied Statistics from the Institute of Statistical Research and Training (ISRT), University of Dhaka. Her research interests include generalized linear models, bias reduction, statistical theory, and statistical modelling. She is also interested in the application of statistical methods to real-world problems and has experience in statistical research and university teaching.

Generalized linear models, bias reduction, statistical theory, and statistical modelling

https://www.researchgate.net/profile/Silvia-Khanam?ev=hdr_xprf