Papers by Md. Akhtarul Islam
Vaccination against measles still stands as a highly impactful public health strategy for mitigat... more Vaccination against measles still stands as a highly impactful public health strategy for mitigating childhood morbidity and mortality. Relatively poor immunization coverage among children has been observed in low and middle-income countries (LMICs). Our study intended to determine socio-demographic factors associated with the 1st dose of measles vaccination among South Asian (SA) and SubSaharan African (SSA) countries children. Study design: This was a cross-sectional study. Methods: This study utilized demographic and health survey data from 42 low-and middle-income countries (LMICs) in SA and SSA. The children's dataset yielded 255,775 children between the ages of 12 and 59 months. The independent predictors were determined by using crude and adjusted odds ratios with 95% confidence intervals (CI). Results: The prevalence of first-dose measles-immunized children was 55.5% for the selected LMICs. The multivariable analysis for combined regions (SA and SSA) showed that parents with a higher level of education, rich wealth quintile, mothers with media access, mothers with more than four antenatal care (ANC) visits and baby postnatal checkup (PNC) within two months were significantly associated with the first dose of measles vaccination among children. Conclusion: The first dose measles immunization coverage in the selected LMICs was considerably low. To boost the uptake of childhood measles vaccination, public health interventions particularly need to focus on children born to uneducated parents, poor families, and those who have not used health services (ANC and PNC). Financial funding is crucial for establishing mobile vaccination clinics to improve immunization rates among the impoverished.
Sexual & Reproductive Healthcare, 2021
This study intended to reveal the effectiveness of Antenatal Care (ANC) and Postnatal care (PNC) ... more This study intended to reveal the effectiveness of Antenatal Care (ANC) and Postnatal care (PNC) services on infant mortality in 24 developing countries by utilizing the recent Demographic and Health Survey (DHS) data. Design: This study utilized the most recent DHS data from 2013 to 2019 of 24 different developing countries. Meta-analysis techniques were was implemented to congregate cross-sectional studies to integrate data from 24 countries to fulfill the study's objective. ParticipantsChildren's Recode (KR) data was used as this study is based on infants aged 0-11 months. Results: Results of this study uncovered for 24 developing countries that taking ANC and PNC had a statistically significant association in lowering infant death. These two covariates were found to significantly impact all 24 developing countries' infant mortality (OR: 0.356, 95% CI: 0.311; 0.407 for taking ANC and OR: 0.302, 95% CI: 0.243; 0.375 for taking PNC). Additionally, taking ANC was more effective in Asian countries, while taking PNC was more effective for African countries. Conclusion: In this study, taking ANC and PNC services was significant in reducing the risk of infant mortality in developing countries. So, anticipation and advancement in health care services ought to be taken to lessen the chance of infant mortality.
IEEE Access, 2021
Asthma is a chronic and airway-induced disease, causing the incidence of bronchus inflammation, b... more Asthma is a chronic and airway-induced disease, causing the incidence of bronchus inflammation, breathlessness, wheezing, is drastically becoming life-threatening. Even in the worst cases, it may destroy the quality to lead. Therefore, early detection of asthma is urgently needed, and machine learning can help identify asthma accurately. In this paper, a novel machine learning framework, namely BOMLA (Bayesian Optimisation-based Machine Learning framework for Asthma) detector has been proposed to detect asthma. Ten classifiers have been utilized in the BOMLA detector, where Support Vector Classifier (SVC), Random Forest (RF), Gradient Boosting Classifier (GBC), eXtreme Gradient Boosting (XGB), and Artificial Neural Network (ANN) are state-of-the-art classifiers. In contrast, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QLDA), Naive Bayes (NB), Decision Tree (DT), and K-Nearest Neighbor (KNN) are conventional popular classifiers. ADASYN algorithm has also been employed in the BOMLA detector to eradicate the issues created due to the imbalanced dataset. It has even been attempted to delineate how the ADASYN algorithm affects the classification performance. The highest accuracy (ACC) and Matthews's correlation coefficient (MCC) for an Asthma dataset provide 94.35% and 88.97%, respectively, using BOMLA detector when SVC is adapted, and it has been increased to 96.52% and 93.04%, respectively, when ensemble technique is adapted. The one-way analysis of variance (ANOVA) has also been performed in the 10-fold cross-validation to measure the statistical significance. A decision support system has been built as a potential application of the proposed system to visualize the probable outcome of the patient. Finally, it is expected that the BOMLA detector will help patients in their early diagnosis of asthma. INDEX TERMS Classification, clinical and non-clinical data, asthma, ADASYN, ANOVA.
IEEE Access, 2021
Feature selection plays a crucial role in order to mitigate the high dimensional feature space in... more Feature selection plays a crucial role in order to mitigate the high dimensional feature space in different classification problems. The computational cost is reduced, and the accuracy of the classification is improved by reducing the dimension of feature space. Hence, in the classification task, finding the optimal subset of features is of utmost importance. Metaheuristic techniques have proved their efficacy in solving many real-world optimization issues. One of the recently introduced physics-inspired optimization methods is Archimedes Optimization Algorithm (AOA). This paper proposes an Enhanced Archimedes Optimization Algorithm (EAOA) by adding a new parameter that depends on the step length of each individual while revising the individual location. The EAOA algorithm is proposed to improve the AOA exploration and exploitation balance and enhance the classification performance for the feature selection issue in real-world data sets. Experiments were performed on twenty-three standard benchmark functions and sixteen real-world data sets to investigate the performance of the proposed EAOA algorithm. The experimental results based on the standard benchmark functions show that the EAOA algorithm provides very competitive results compared to the basic AOA algorithm and five well-known optimization algorithms in terms of improved exploitation, exploration, local optima avoidance, and convergence rate. In addition, the results based on sixteen real-world data sets ascertain that reduced feature subset yields higher classification performance when compared with the other feature selection methods.
Axioms, 2022
Instance reduction is a pre-processing step devised to improve the task of classification. Instan... more Instance reduction is a pre-processing step devised to improve the task of classification. Instance reduction algorithms search for a reduced set of instances to mitigate the low computational efficiency and high storage requirements. Hence, finding the optimal subset of instances is of utmost importance. Metaheuristic techniques are used to search for the optimal subset of instances as a potential application. Antlion optimization (ALO) is a recent metaheuristic algorithm that simulates antlion’s foraging performance in finding and attacking ants. However, the ALO algorithm suffers from local optima stagnation and slow convergence speed for some optimization problems. In this study, a new modified antlion optimization (MALO) algorithm is recommended to improve the primary ALO performance by adding a new parameter that depends on the step length of each ant while revising the antlion position. Furthermore, the suggested MALO algorithm is adapted to the challenge of instance reduction to obtain better results in terms of many metrics. The results based on twenty-three benchmark functions at 500 iterations and thirteen benchmark functions at 1000 iterations demonstrate that the proposed MALO algorithm escapes the local optima and provides a better convergence rate as compared to the basic ALO algorithm and some well-known and recent optimization algorithms. In addition, the results based on 15 balanced and imbalanced datasets and 18 oversampled imbalanced datasets show that the instance reduction proposed method can statistically outperform the basic ALO algorithm and has strong competitiveness against other comparative algorithms in terms of four performance measures: Accuracy, Balanced Accuracy (BACC), Geometric mean (G-mean), and Area Under the Curve (AUC) in addition to the run time. MALO algorithm results show increment in Accuracy, BACC, G-mean, and AUC rates up to 7%, 3%, 15%, and 9%, respectively, for some datasets over the basic ALO algorithm while keeping less computational time.
Dr. Sulaiman Al Habib Medical Journal , 2022
The study aimed to identify the factors influencing the utilization of antenatal care (ANC) servi... more The study aimed to identify the factors influencing the utilization of antenatal care (ANC) services among pregnant women to fulfill the Sustainable Development Goals (SDG) for maternal mortality ratio (MMR) by 2030; we also investigated the consistency of these factors. We have used the Demographic and Health Survey (DHS) data from 29 developing countries for analysis. A binary logistic regression model was run using Demographic and Health Survey data from Bangladesh to determine the factors influencing ANC utilization in Bangladesh. In addition, a random-effects model estimation for metaanalysis was performed using DHS data from 29 developing to investigate the overall effects and consistency between covariates and the utilization of ANC services. Logistic regression revealed that residence (odds ratio [OR] 1.436; 95% confidence interval [
PLOS ONE, 2022
Background Skilled birth attendants (SBAs) play a crucial role in reducing infant and maternal mo... more Background Skilled birth attendants (SBAs) play a crucial role in reducing infant and maternal mortality. Although the ratio of skilled assistance at birth has increased in Bangladesh, factors associated with SBA use are unknown. The main goal of our study was to reveal the individualand community-level factors associated with SBA use during childbirth in Bangladesh. We also showed the prevalence and trend of SBA use and related independent variables in Bangladesh over the past decade. Methods This study utilized the Bangladesh Health and Demographic Survey (BDHS) 2017-2018, a cross-sectional study. We used binary logistic regression to examine the extent of variation in SBA use attributable to the individual-and community-level variables. Results Overall, 53.35% of women received assistance from SBAs during childbirth. The average annual rate of increase (AARI) in the number of SBA-assisted births over the past 10 years was 8.88%. Respondents who gave birth at or above 19 years had 1.40 times (AOR = 1.40; 95% CI: 1.21-1.62) greater odds of having skilled delivery assistance than respondents aged 18 years old or less. Women and their husband's education levels were significantly associated with using skilled assistance during delivery, with odds of 1.60 (AOR = 1.60; 95% CI: 1.45-2.01) and 1.41 (AOR = 1.41; 95% CI: 1.21-1.66), respectively compared to those with education up to primary level. Women from rich families and those receiving better antenatal care (ANC) visits were more likely to have professional delivery assistance. Community-level factors also showed significance towards having professional assistance while giving birth. Women from urban communities and those who utilized more than four
Dr. Sulaiman Al Habib Medical Journal (2022) 4:145–152, 2022
Neonatal mortality is high in developing countries, and reducing neonatal mortality is an indispe... more Neonatal mortality is high in developing countries, and reducing neonatal mortality is an indispensable part of the third Sustainable Development Goal. This study estimated the prevalence of neonatal mortality and the impact of maternal education, economic status, and utilization of antenatal care (ANC) services on neonatal mortality in developing countries. We used a cross-sectional study design to integrate data from 21 developing countries to acquire a wider perspective on neonatal mortality. A meta-analysis was conducted using the latest Demographic and Health Survey data from 21 developing countries. In addition, sensitivity analysis was adopted to assess the stability of the meta-analysis. The random-effects model indicated that women with higher education were less likely to experience neonatal death than mothers with up to primary education (odds ratio [OR] 0.820, 95% confidence interval [CI] 0.740-0.910). Women with higher socioeconomic status were less likely to experience neonatal death than mothers with lower socioeconomic status (OR 0.823, 95% CI 0.747-0.908). Mothers with ANC were less likely to experience neonatal death than those with no ANC (OR 0.374, 95% CI 0.323-0.433). Subgroup analysis showed that maternal education and ANC were more effective in Asian countries. In this study, mothers' lower educational level, poor economic status, and lack of ANC were statistically significant factors associated with neonatal death in developing countries. The effect of these factors on neonatal death differed in different regions.
Dr. Sulaiman Al Habib Medical Journal (2022) 4:159–167, 2022
The primary goal of this study was to investigate the severity of being overweight/obese among no... more The primary goal of this study was to investigate the severity of being overweight/obese among non-pregnant women and its trend for change over the last 10 years in Bangladesh. This research featured 16,398 female participants and used the chi-Squared test to investigate the association between different socioeconomic variables and dependent variables. We applied the average annual rate of increase (AARI) to determine the trends of selected variables over the last decade. Next, we applied a multilevel logistic regression model to determine specific trigger factors at the individual and community levels; for this, we used the 2017-2018 data from the Bangladesh Demographic and Health Survey (BDHS). Individually, women between the ages of 40 and 44 years (odds ratio [OR] 5.68; 95% confidence interval [95% CI] 4.68-6.89) with better education (OR 1.55; 95% CI 1.34-1.80) and from the wealthiest households (OR 3.65; 95% CI 3.17-4.20) had a higher risk for being overweight or obese. On the other hand, working women (OR 0.80; 95% CI 0.75-0.87) had a lower risk of becoming overweight or obese. Respondents from affluent communities had a higher probability of being overweight or obese (OR 1.93; 95% CI 1.72-2.18) whereas women in rural areas were less likely (OR 0.63; 95% CI 0.57-0.69) to be overweight or obese. The efforts of both individuals and communities are expected to raise awareness among wealthy and educated women.
International Journal of Environmental Research and Public Health , 2022
Diabetes is one of the most rapidly spreading diseases in the world, resulting in an array of sig... more Diabetes is one of the most rapidly spreading diseases in the world, resulting in an array of significant complications, including cardiovascular disease, kidney failure, diabetic retinopathy, and neuropathy, among others, which contribute to an increase in morbidity and mortality rate. If diabetes is diagnosed at an early stage, its severity and underlying risk factors can be significantly reduced. However, there is a shortage of labeled data and the occurrence of outliers or data missingness in clinical datasets that are reliable and effective for diabetes prediction, making it a challenging endeavor. Therefore, we introduce a newly labeled diabetes dataset from a South Asian nation (Bangladesh). In addition, we suggest an automated classification pipeline that includes a weighted ensemble of machine learning (ML) classifiers: Naive Bayes (NB), Random Forest (RF), Decision Tree (DT), XGBoost (XGB), and LightGBM (LGB). Grid search hyperparameter optimization is employed to tune the critical hyperparameters of these ML models. Furthermore, missing value imputation, feature selection, and K-fold cross-validation are included in the framework design. A statistical analysis of variance (ANOVA) test reveals that the performance of diabetes prediction significantly improves when the proposed weighted ensemble (DT + RF + XGB + LGB) is executed with the introduced preprocessing, with the highest accuracy of 0.735 and an area under the ROC curve (AUC) of 0.832. In conjunction with the suggested ensemble model, our statistical imputation and RF-based feature selection techniques produced the best results for early diabetes prediction. Moreover, the presented new dataset will contribute to developing and implementing robust ML models for diabetes prediction utilizing population-level data. Keywords: artificial intelligence; diabetes prediction; ensemble ML classifier; filling missing value; outlier rejection; South Asian diabetes dataset
Family Medicine & Primary Care Review , 2022
Background. Infant mortality is a salient indicator for appraising the quality of the healthcare ... more Background. Infant mortality is a salient indicator for appraising the quality of the healthcare infrastructures of a country. To achieve the sustainable development goal, the infant mortality rate should be reduced to the indicated level. On account of this, it is requisite to point out the associated factors of infant mortality and provide action plans for monitoring them. Objectives. This study aimed to discover the prevalence of infant mortality and assess how different factors influence infant mortality in 24 developing countries by utilising the latest Demographic and Health Survey (DHS) data. Material and methods. This study used a mixed-method design to assemble cross-sectional studies to integrate data from 24 other countries due to the widening perspective of infant mortality. Descriptive analysis, binary logistic regression model, random-effect meta-analysis and forest plot have been used for the analyses. Results. The binary logistic regression model for Bangladesh revealed that a higher education level of fathers (OR: 0.344, 95% CI: 0.147; 0.807), being 2 nd born or above order infant (OR: 0.362, 95% CI: 0.248; 0.527), undergoing antenatal care (ANC) (OR: 0.271, 95% CI: 0.192; 0.382 for 1-4 visits) and undergoing postnatal care (PNC) (OR: 0.303, 95% CI: 0.216; 0.425) were statistically significant determinants of lowering infant death. While carrying multiple foetuses (OR: 6.634, 95% CI: 3.247; 13.555) was shown to be a risk factor of infant mortality. The most significant factors influencing infant mortality for developing countries were the number of foetuses (OR: 0.193, 95% CI: 0.176; 0.213), undergoing ANC (OR: 0.356, 95% CI: 0.311; 0.407), undergoing PNC (OR: 0.302, 95% CI: 0.243; 0.375) and the size of the children (OR: 0.653, 95% CI: 0.588; 0.726). Conclusions. In this study, the number of the foetuses, undergoing ANC and PNC, mother's education, fathers' education and size of the children were the most significant factors affecting infant mortality in developing countries. Thusly, anticipation and control projects need to be taken considering the outcome of this study to reduce the infant mortality.
Sexual & Reproductive Healthcare, 2022
Background: In recent decades, the number of C-section deliveries has increased over the world, i... more Background: In recent decades, the number of C-section deliveries has increased over the world, including Bangladesh. The study aimed to identify individual-and community-level factors associated with C-section childbirth in Bangladesh and investigate the annual average increase rate of C-section childbirth. C-section. Methods: Data were derived from four waves of the Bangladesh Demographic and Health Survey (BDHS) conducted between 2007 and 2017-18. Chi-square test of association was run to check the bivariate association between dependent and independent factors. For the individual-and community-level factors deliveries among Bangladeshi married women, a multilevel logistic regression model was carried out. Result: Over the last ten years, the average annual increase of C-section rates during delivery was 13.09% in Bangladesh, while this rate was 33.25%according to 2017-18 BDHS.C-section 33.25% of women have access to C-section birth. Women who had four or more than four ANC visits, women and their husbands with secondary and above education, middle and rich-wealth households, and community-level factors such as high media access, secondary and above educational experience women used C-sectionC-section delivery compared to their respective counterpart. Conclusion: The findings of the study revealed the association of some individual and community-level factors that need to be taken into account to minimize the rising rate of C-section deliveries in Bangladesh, which has increased drastically over the survey years.
International Journal of Clinical Practice, 2022
Background. Te most prominent form of cancer in women is breast cancer, and modifable lifestyle r... more Background. Te most prominent form of cancer in women is breast cancer, and modifable lifestyle risk factors, including smoking, alcohol consumption, and induced abortion, can all contribute signifcantly to this disease. Objectives. Tis study's primary purpose was to assess the prevalence of breast cancer among women in developed and developing countries and the association between three modifable hazard factors (induced abortion, smoking behavior, and alcohol use) and breast cancer. Methods. Tis study performed a systematic literature database review up to September 21, 2021. We employed meta-analytic tools such as the random efects model, forest plot, and subgroup analysis to conduct the research. Additionally, we conducted a sensitivity analysis to assess the infuence of outliers. Results. According to the random efects model, smoker women have a higher risk of developing breast cancer from diferent countries (OR � 1.46; 95% CI: 1.08-1.97). In the case of induced abortion, the pooled estimate (OR � 1.25; 95% CI: 1.01-1.53) indicated a signifcant link between abortion and breast cancer. Subgroup analysis revealed that smoking substantially infuences breast cancer in developing and developed countries. Breast cancer was more common among women who smoked in developed countries than in developing nations. Conclusion. Te observed fndings give sufcient support for the hypothesis that smoking and abortion have a signifcant infuence on breast cancer in diferent nations. Health organizations should individually design comprehensive scientifc plans to raise awareness about the risks of abortion and smoking in developed and developing countries.
Electronics, 2022
Abstract: The emergency of the pandemic and the absence of treatment have motivated researchers i... more Abstract: The emergency of the pandemic and the absence of treatment have motivated researchers in
all the fields to deal with the pandemic situation. In the field of computer science, major contributions
include the development of methods for the diagnosis, detection, and prediction of COVID-19 cases.
Since the emergence of information technology, data science and machine learning have become
the most widely used techniques to detect, diagnose, and predict the positive cases of COVID-19.
This paper presents the prediction of confirmed cases of COVID-19 and its mortality rate and then
a COVID-19 warning system is proposed based on the machine learning time series model. We
have used the date and country-wise confirmed, detected, recovered, and death cases features for
training of the model based on the COVID-19 dataset. Finally, we compared the performance of time
series models on the current study dataset, and we observed that PROPHET and Auto-Regressive
(AR) models predicted the COVID-19 positive cases with a low error rate. Moreover, death cases
are positively correlated with the confirmed detected cases, mainly based on different regions’
populations. The proposed forecasting system, driven by machine learning approaches, will help the
health departments of underdeveloped countries to monitor the deaths and confirm detected cases of
COVID-19. It will also help make futuristic decisions on testing and developing more health facilities,
mostly to avoid spreading diseases.
PLOS ONE, 2022
Background In many low-and middle-income countries (LMICs), including Bangladesh, socioeconomic i... more Background In many low-and middle-income countries (LMICs), including Bangladesh, socioeconomic inequalities in access to maternity care remain a substantial public health concern. Due to the paucity of research, we attempted to determine the factors affecting the facility delivery, quantify wealth-related inequality, and identify potential components that could explain the inequality. Methods We used the latest Bangladesh Demographic and Health Survey (BDHS 2017-18) data in this study. We utilized logistic regression to investigate the associated factors of facility delivery. The concentration curves (CC), concentration index (CIX) and decomposition of CIX techniques were used to analyze the inequality in-facility delivery. Results Women living in the urban areas, age at first birth after (18-24 years �25 years), being overweight/obese, having secondary and higher-level education of the women and their husband, seeking four or more ANC, coming from more affluent households, and women with high enlightenment were significant determinants of facility delivery. The concentration curve was below the line of equality, and the relative concentration index (CIX) was 0.205 (p <0.001), indicating that women from wealthy groups were disproportionately more prevalent to facility delivery. The decomposition analysis reveals that wealth status of women (57.40%), age at first birth (10.24%), husband's education (8.96%), husband's occupation
Frontiers in Public Health, 2022
Background: Pornography exposure, particularly among students, in Bangladesh, has increased in th... more Background: Pornography exposure, particularly among students, in Bangladesh, has increased in the twenty-first century. However, pornography exposure during the COVID-19 pandemic, when people were compelled to “stay at home” and relied extensively on the internet for all forms of activities, including academia, socializing, and communication, has remained unexplored. The present study aimed to assess the prevalence of pornography exposure among students during the third wave of the COVID-19 pandemic and to determine the associated predictors.
Methods: A web-based cross-sectional study was carried out among students with certain specifications, i.e., current students at high school/college/university with access to the internet and valid social media accounts. By administering a semi-structured e-questionnaire using Google Forms, a total of 646 valid responses were retained for this study. The data were analyzed in two phases by Pearson's Chi-square and multiple logistic regression model, using IBM SPSS Statistics, version 25. The results were expressed as an adjusted odds ratio (AOR) with a 95% confidence interval (95% CI).
Results: The findings suggest that 75.9% of students were exposed to pornography during the third wave of the COVID-19 pandemic and preferred to watch the amateur/professional genre of pornography. Pornography exposure was significantly associated with age and relationship status, as students aged 22–24 years (95% CI: 1.01–2.41; p = 0.045) and over 25 years (95% CI: 1.61–10.03; p = 0.003) were more likely to watch pornography, while married students and those in relationships (95% CI: 1.24–3.49; p = 0.006) also watched pornography during the pandemic. In contrast, students who were living alone (95% CI: 0.38–0.92; p = 0.021), were living in the Khulna division (95% CI: 0.16–0.52; p < 0.001) or had a negative attitude toward pornography (95% CI: 0.94–0.99; p = 0.002) were less likely to be exposed to pornography.
Conclusion: Pornography exposure was higher among students in Bangladesh during the COVID-19 pandemic, and religiosity and disapproving attitudes toward pornography negatively influenced the pornography exposure. For a better understanding of the complex dynamics of socio-demographic issues with pornography exposure among students, extensive research is required for policymakers to devise appropriate strategies and interventions to ensure healthy and safe sex life for the younger population.
BMJ Open, 2022
Objectives The prime objectives of the study were to measure the prevalence of facility delivery,... more Objectives The prime objectives of the study were to measure the prevalence of facility delivery, assess socioeconomic inequalities and determine potential associated factors in the use of facility delivery in Bangladesh. Design Cross-sectional. Setting The study involved investigation of nationally representative secondary data from the Bangladesh Demographic and Health Survey between 2007 and 2017-2018. Participants The participants of this study were 30 940 (weighted) Bangladeshi women between the ages of 15 and 49. Methods Decomposition analysis and multivariable logistic regression were both used to analyse data to achieve the study objectives. Results The prevalence of using facility delivery in Bangladesh has increased from 14.48% in 2007 to 49.26% in 2017-2018. The concentration index for facility delivery utilisation was 0.308 with respect to household wealth status (p<0.001), indicating that use of facility delivery was more concentrated among the rich group of people. Decomposition analysis also indicated that wealth quintiles (18.31%), mothers' education (8.78%), place of residence (7.75%), birth order (5.56%), partners' education (4.30%) and antenatal care (ANC) seeking (8.51%) were the major contributors to the prorich socioeconomic inequalities in the use of facility delivery. This study found that women from urban areas, were overweight, had any level of education, from wealthier families, had ANC, and whose partners had any level of education and involved in business were more likely to have facility births compared with their respective counterparts. Conclusions This study found a prorich inequality in the use of facility delivery in Bangladesh. The socioeconomic disparities in facility delivery must be addressed if facility delivery usage is to increase in Bangladesh.
Frontiers in Psychiatry, 2023
Background: Due to unemployment, the prolonged lockdown during the COVID-19 pandemic caused panic... more Background: Due to unemployment, the prolonged lockdown during the COVID-19 pandemic caused panic and deepened poverty, especially among lower-class and marginal people. The related financial crises led to harmful practices such as the early marriage of adolescent girls, which deteriorated these girl's mental state. Aims: This study attempted to assess the prevalence of mental health problems among early married girls and determine the associated predictors of the growing mental health burden. Methods: This cross-sectional survey was conducted during the third wave of the COVID-19 pandemic in Dumuria Upazila in the Khulna district of Bangladesh. Data were collected purposively from 304 girls who were married off during the COVID-19 pandemic, this was carried out between 22 July and 31 August 2022 by administering a semi-structured interview schedule, with mental health measured by the depression, anxiety, and stress scale 21 (DASS 21). The data were analyzed using IBM SPSS Statistics (version 25), and multiple linear regression was executed in order to predict mental health problems among early married girls. Results: The findings show that the overall prevalence of depression, anxiety, and stress among early married girls during the COVID-19 pandemic in Bangladesh was 60.9% (95% CI: 0.554-0.663), 74.7% (95% CI: 0.698-0.796), and 23.7% (95% CI: 0.189-0.285). The prevalence was relatively higher among girls from the Sanatan (Hindu) religion and younger girls than among Muslim and older girls, respectively. The multiple linear regressions indicate that age, age at marriage, duration of the marriage, spousal occupation, intimate partner violence (IPV), and subjective happiness were the critical predictors of mental health problems among early married girls.
Dr. Sulaiman Al Habib Medical Journal (2023) 5:10–22, 2023
Background Bangladesh is one of the most densely populated countries in the world. This large pop... more Background Bangladesh is one of the most densely populated countries in the world. This large population predominantly affects the socioeconomic development of the people living in this country. Therefore, it is essential to identify the determinants of household size in the country and suggest implications for future interventions in similar contexts. Objectives The primary purpose of the present study was to explore the distribution of household size and its determinants based on the nationally representative Bangladesh Demographic and Health Survey (BDHS) data. Material and Methods The data were extracted from BDHS 2017-2018, a national survey. Individual responses from the adult women of each household were considered in this nationwide survey. We applied univariate and bivariate analyses (chi-squared test) to explore the distribution of household size and different selected determinants. The multinomial logistic regression was utilized to identify the association between household size and the selected independent determinants in our study. Results Findings of our multinomial logistic regression analysis showed that sex of the household head, division, decision about health, respondent's age, residence, respondent's education, husband's education, wealth index, religion, husband's occupation, and respondent's working status were significantly associated with the household size (P ≤ 0.05). We observed that household size tended to be more prominent in rural areas, in the Sylhet division, in families where the head of the household was a male, and in families where others except the respondents and their husbands made health-related decisions. Besides, large household size was also common among respondents aged 25 years or less, respondents and their husbands with higher education, respondents from the rich and middle class, respondents who were Muslim, respondents whose husbands were businessmen and jobholders, and respondents who were workers. Conclusions The findings of our study suggest that household size in Bangladesh is associated with different socioeconomic factors. We recommend promoting awareness programs on family planning promotion and early marriage prevention, especially in rural areas, to prevent the rapid growth of the population. Expansion of education for both men and women and female involvement in income-generating activities should be encouraged to effectively control the household size in Bangladesh.
Agrotechnology, 2017
Adoption of an environment friendly agricultural technique, namely Integrated Pest Management (IP... more Adoption of an environment friendly agricultural technique, namely Integrated Pest Management (IPM) depends on various socioeconomic and demographic factors. This study attempts to determine the factors that influence farmers' decision to receive IPM. For analysis purpose several socioeconomic and demographic information were collect from 617 farmers of five division (Dhaka, Chittagong, Rangpur, Khulna, Barisal), Bangladesh by prepared a structured query. To ensure randomness, simple random sampling technique was used for data collection. Farmers' ten background characteristics were analyzed in both bivariate and multivariate setup. In bivariate setup, association between selected factors and adoption status of IPM were investigated by performing a chi-square test. To get the adjusted effect, a binary logistic regression model was estimated in multivariate setup. The results of the model provide evidence that farmers' age, education level, farming experience, training on IPM and membership status of IPM club are the highly significant (P<0.05) factors for IPM adoption. Farm ownership status and Barisal division also found significant (P<0.10) factors for IPM adoption in Bangladesh.
Uploads
Papers by Md. Akhtarul Islam
all the fields to deal with the pandemic situation. In the field of computer science, major contributions
include the development of methods for the diagnosis, detection, and prediction of COVID-19 cases.
Since the emergence of information technology, data science and machine learning have become
the most widely used techniques to detect, diagnose, and predict the positive cases of COVID-19.
This paper presents the prediction of confirmed cases of COVID-19 and its mortality rate and then
a COVID-19 warning system is proposed based on the machine learning time series model. We
have used the date and country-wise confirmed, detected, recovered, and death cases features for
training of the model based on the COVID-19 dataset. Finally, we compared the performance of time
series models on the current study dataset, and we observed that PROPHET and Auto-Regressive
(AR) models predicted the COVID-19 positive cases with a low error rate. Moreover, death cases
are positively correlated with the confirmed detected cases, mainly based on different regions’
populations. The proposed forecasting system, driven by machine learning approaches, will help the
health departments of underdeveloped countries to monitor the deaths and confirm detected cases of
COVID-19. It will also help make futuristic decisions on testing and developing more health facilities,
mostly to avoid spreading diseases.
Methods: A web-based cross-sectional study was carried out among students with certain specifications, i.e., current students at high school/college/university with access to the internet and valid social media accounts. By administering a semi-structured e-questionnaire using Google Forms, a total of 646 valid responses were retained for this study. The data were analyzed in two phases by Pearson's Chi-square and multiple logistic regression model, using IBM SPSS Statistics, version 25. The results were expressed as an adjusted odds ratio (AOR) with a 95% confidence interval (95% CI).
Results: The findings suggest that 75.9% of students were exposed to pornography during the third wave of the COVID-19 pandemic and preferred to watch the amateur/professional genre of pornography. Pornography exposure was significantly associated with age and relationship status, as students aged 22–24 years (95% CI: 1.01–2.41; p = 0.045) and over 25 years (95% CI: 1.61–10.03; p = 0.003) were more likely to watch pornography, while married students and those in relationships (95% CI: 1.24–3.49; p = 0.006) also watched pornography during the pandemic. In contrast, students who were living alone (95% CI: 0.38–0.92; p = 0.021), were living in the Khulna division (95% CI: 0.16–0.52; p < 0.001) or had a negative attitude toward pornography (95% CI: 0.94–0.99; p = 0.002) were less likely to be exposed to pornography.
Conclusion: Pornography exposure was higher among students in Bangladesh during the COVID-19 pandemic, and religiosity and disapproving attitudes toward pornography negatively influenced the pornography exposure. For a better understanding of the complex dynamics of socio-demographic issues with pornography exposure among students, extensive research is required for policymakers to devise appropriate strategies and interventions to ensure healthy and safe sex life for the younger population.
all the fields to deal with the pandemic situation. In the field of computer science, major contributions
include the development of methods for the diagnosis, detection, and prediction of COVID-19 cases.
Since the emergence of information technology, data science and machine learning have become
the most widely used techniques to detect, diagnose, and predict the positive cases of COVID-19.
This paper presents the prediction of confirmed cases of COVID-19 and its mortality rate and then
a COVID-19 warning system is proposed based on the machine learning time series model. We
have used the date and country-wise confirmed, detected, recovered, and death cases features for
training of the model based on the COVID-19 dataset. Finally, we compared the performance of time
series models on the current study dataset, and we observed that PROPHET and Auto-Regressive
(AR) models predicted the COVID-19 positive cases with a low error rate. Moreover, death cases
are positively correlated with the confirmed detected cases, mainly based on different regions’
populations. The proposed forecasting system, driven by machine learning approaches, will help the
health departments of underdeveloped countries to monitor the deaths and confirm detected cases of
COVID-19. It will also help make futuristic decisions on testing and developing more health facilities,
mostly to avoid spreading diseases.
Methods: A web-based cross-sectional study was carried out among students with certain specifications, i.e., current students at high school/college/university with access to the internet and valid social media accounts. By administering a semi-structured e-questionnaire using Google Forms, a total of 646 valid responses were retained for this study. The data were analyzed in two phases by Pearson's Chi-square and multiple logistic regression model, using IBM SPSS Statistics, version 25. The results were expressed as an adjusted odds ratio (AOR) with a 95% confidence interval (95% CI).
Results: The findings suggest that 75.9% of students were exposed to pornography during the third wave of the COVID-19 pandemic and preferred to watch the amateur/professional genre of pornography. Pornography exposure was significantly associated with age and relationship status, as students aged 22–24 years (95% CI: 1.01–2.41; p = 0.045) and over 25 years (95% CI: 1.61–10.03; p = 0.003) were more likely to watch pornography, while married students and those in relationships (95% CI: 1.24–3.49; p = 0.006) also watched pornography during the pandemic. In contrast, students who were living alone (95% CI: 0.38–0.92; p = 0.021), were living in the Khulna division (95% CI: 0.16–0.52; p < 0.001) or had a negative attitude toward pornography (95% CI: 0.94–0.99; p = 0.002) were less likely to be exposed to pornography.
Conclusion: Pornography exposure was higher among students in Bangladesh during the COVID-19 pandemic, and religiosity and disapproving attitudes toward pornography negatively influenced the pornography exposure. For a better understanding of the complex dynamics of socio-demographic issues with pornography exposure among students, extensive research is required for policymakers to devise appropriate strategies and interventions to ensure healthy and safe sex life for the younger population.