Mohammad Arif

Mohammad Arif

Auto-generated profile, based on publicly available information

Mohammad Arif

CHINTA Research Bangladesh, Dhaka, Bangladesh

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 October 2025 in Journal of Health, Population and Nutrition
Verified
Journal Article
Open access
PDF file
MHMd Emran Hasan
Md Emran Hasan
MAMohammad Arif
Mohammad Arif
SHS. M. Rakibul Hasan
S. M. Rakibul Hasan
Moses MuwanguziMoses Muwanguzi
Moses Muwanguzi
JAJoan Abaatyo
Joan Abaatyo
MMMohammed Mamun
Mohammed Mamun
Mental health challenges are a growing global public health concern, with university students at elevated risk due to academic and social pressures. Although several studies have exmanined mental health among Bangladeshi students, few have integrated conventional statistical analyses with advanced machine learning (ML) approaches. This study aimed to assess the prevalence and factors associated with depression, anxiety, and stress among Bangladeshi university students, and to evaluate the predictive performance of multiple ML models for those outcomes. A cross-sectional survey was conducted in February 2024 among 1697 students residing in halls at two public universities in Bangladesh: Jahangirnagar University and Patuakhali Science and Technology University. Data on sociodemographic, health, and behavioral factors were collected via structured questionnaires. Mental health outcomes were measured using the validated Bangla version of the Depression, Anxiety, and Stress Scale-21 (DASS-21). Statistical analyses included chi-square tests and binary logistic regression, while seven ML models including, K-Nearest Neighbors (KNN), Random Forest (RF), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Logistic Regression (LR), and Support Vector Machine (SVM) were employed to predict mental health outcomes. The prevalence of depression, anxiety, and stress was 56.9%, 69.5%, and 32.2%, respectively. Significant associated factors for depression included unfriendly family relationships, enrollment in commerce, and cigarette smoking. Female gender, unfriendly family relationships, academic year, and cigarette smoking were significant factors for stress. No significant factors were identified for anxiety. Among ML models, SVM achieved the highest accuracy for depression prediction (accuracy = 0.5693; precision = 0.7560; log loss = 0.6847), LR for anxiety (accuracy = 0.6948; precision = 0.7881), and CatBoost for stress (accuracy = 0.6706; precision = 0.6454; F1-score = 0.5777; log loss = 0.6284). Feature importance analyses highlighted faculty of study and relation with family as the top predictors. ROC-AUC values indicated moderate discriminatory performance (all ≥ 0.5). Integrating machine learning with conventional analyses enhances the identification and prediction of factors associated with depression, anxiety, and stress among university students. These findings support the implementation of campus-based mental health screening, accessible counseling, and peer support programs, and highlight the value of data-driven approaches for developing targeted university mental health policies.

25 April 2024 in BMC Psychiatry
Verified
Journal Article
Open access
PDF file
MMMohammed Mamun
Mohammed Mamun
MHMd Emran Hasan
Md Emran Hasan
NMNahida Bintee Mostofa
Nahida Bintee Mostofa
MAMarzia Akther
Marzia Akther
TMTahnin Mashruba
Tahnin Mashruba
MMMohammed Mamun
Mohammed Mamun
Background: The surge in digital media consumption, coupled with the ensuing consequences of digital addiction, has witnessed a rapid increase, particularly after the initiation of the COVID-19 pandemic. Despite some studies exploring specific technological addictions, such as internet or social media addiction, in Bangladesh, there is a noticeable gap in research focusing on digital addiction in a broader context. Thus, this study aims to investigate digital addiction among students taking the university entrance test, examining its prevalence, contributing factors, and geographical distribution using GIS techniques. Methods: Data from a cross-sectional survey were collected from a total of 2,157 students who were taking the university entrance test at Jahangirnagar University, Bangladesh. A convenience sampling method was applied for data collection using a structured questionnaire. Statistical analyses were performed with SPSS 25 Version and AMOS 23 Version, whereas ArcGIS 10.8 Version was used for the geographical distribution of digital addiction. Results: The prevalence of digital addiction was 33.1% (mean score: 16.05 ± 5.58). Those students who are attempting the test for a second time were more likely to be addicted (42.7% vs. 39.1%), but the difference was not statistically significant. Besides, the potential factors predicted for digital addiction were student status, satisfaction with previous mock tests, average monthly expenditure during the admission test preparation, and depression. No significant difference was found between digital addiction and districts. However, digital addiction was higher in the districts of Manikganj, Rajbari, Shariatpur, and Chittagong Hill Tract areas, including Rangamati, and Bandarban. Conclusions: The study emphasizes the pressing need for collaborative efforts involving educational policymakers, institutions, and parents to address the growing digital addiction among university-bound students. The recommendations focus on promoting alternative activities, enhancing digital literacy, and imposing restrictions on digital device use, which are crucial steps toward fostering a healthier digital environment and balanced relationship with technology for students.

1 October 2025 in Nature and Science of Sleep
Verified
Journal Article
Open access
PDF file
PDPronab Das
Pronab Das
MAMohammad Arif
Mohammad Arif
MHMd Emran Hasan
Md Emran Hasan
MAMoneerah Mohammad Almerab
Moneerah Mohammad Almerab
AHAbdullah Al Habib
Abdullah Al Habib
David GozalDavid Gozal
David Gozal
Background: Insomnia significantly impairs both mental and physical health, and its bidirectional relationship with chronic diseases exacerbates outcomes for both conditions. While insomnia risk factors are well-studied in general populations, little is known about its prevalence and determinants among chronic disease patients in Bangladesh. Using machine learning (ML) alongside traditional analyses may improve prediction and early identification of insomnia risk in this high-vulnerability group. Methods: This cross-sectional study recruited 1,222 adult chronic disease patients from healthcare facilities in Dhaka and Chattogram between May and November 2024. Insomnia was assessed using the Insomnia Severity Index (ISI-7). Multivariable logistic regression identified significant risk and protective factors. Six ML classifiers, K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost), were trained and tested (with Synthetic Minority Over-sampling Technique for class imbalance), and model performance was evaluated using accuracy, precision, F1 score, log loss, and the area under the receiver operating characteristic curve (AUC-ROC). Feature importance was determined via SHapley Additive exPlanations (SHAP) and gain values. Results: Insomnia affected 41.3% of patients. Risk factors included female gender, joint family, urban residence, smokeless tobacco and substance use, prolonged daytime napping, late disease onset, presence of other chronic diseases, and unmet mental healthcare needs. Protective factors were physical activity, 7– 9 hours of nighttime sleep, met mental healthcare needs, and notably, presence of urinary disease. Among ML models, CatBoost outperformed others (accuracy 71.67%, AUC 77.27%, F1 score 71.23%), followed closely by RF and SVM. Feature importance analysis consistently identified mental healthcare need fulfillment and nighttime sleep duration as the strongest predictors of insomnia. Conclusion: Insomnia was common among Bangladeshi chronic disease patients and linked to sociodemographic, behavioral, clinical, and mental health factors. CatBoost and other ML models showed strong predictive ability, supporting their use in early screening. Prospective studies are needed to validate these findings and guide targeted interventions.

10 November 2025 in Brain and Behavior
Verified
Journal Article
Open access
MMMohammed Mamun
Mohammed Mamun
MMMohammed Mamun
Mohammed Mamun
MAMohammad Arif
Mohammad Arif
PDPronab Das
Pronab Das
MAMoneerah Mohammad Almerab
Moneerah Mohammad Almerab
David GozalDavid Gozal
David Gozal
Background: Insomnia is highly prevalent among individuals with chronic diseases and often exacerbates disease progression while adversely impacting mental health and quality of life. However, validated tools to assess insomnia in this vulnerable population remain limited in emerging economies. This study aimed to evaluate the psychometric properties of the Bangla version of the Insomnia Severity Index (ISI) among Bangladeshi adults with chronic diseases using confirmatory factor analysis (CFA), Rasch modeling, and network analysis. Methods: A face‐to‐face survey was conducted among adults with clinically diagnosed chronic illnesses. CFA was used to test one‐, two‐, and three‐factor structures and gender‐based measurement invariance. Rasch analysis examined item fit, reliability, and response category functioning. Network analysis estimated symptom interrelations, centrality, bridge metrics, and gender‐based network invariance. Results: The two‐factor model (Night Symptoms, Daytime Impact) provided the most favorable balance between statistical fit and theoretical coherence. Although the three‐factor model yielded marginally better indices, its reliance on a single‐indicator factor and high inter‐factor correlations limited its interpretability. All items showed strong factor loadings and internal consistency. Measurement invariance was supported across gender. Rasch modeling confirmed item fit, category functioning, and reliability, though some items exhibited moderate gender‐based DIF. Network analysis identified ISI_1 (difficulty falling asleep) and ISI_6 (noticeability of sleep problems) as central symptoms, while ISI_4 (satisfaction with sleep pattern) emerged as a key bridge symptom. Predictability was high, and network structure was invariant across gender. Conclusion: The ISI‐Bangla demonstrates strong psychometric validity in a chronic disease population, supporting its use for clinical and research purposes in Bangladesh. Testing the alternative factor structures confirmed the robustness of the two‐factor specification. The integration of CFA, Rasch, and network analysis provides a comprehensive validation framework.

29 March 2026 in Psychiatric Quarterly
Verified
Journal Article
Closed access
MMMohammed Mamun
Mohammed Mamun
MAMohammad Arif
Mohammad Arif
PDPronab Das
Pronab Das
MHMd Emran Hasan
Md Emran Hasan
MAMoneerah Mohammad Almerab
Moneerah Mohammad Almerab
MMMohammed Mamun
Mohammed Mamun