Exploring Sleep Duration and Insomnia Among Prospective University Students: A Study with Geographical Data and Machine Learning Techniques

• DOI: 10.2147/nss.s481786
• Publication Date: 2024-08-20T02:15:18Z
• Authors: Firoj Al-Mamun; Mohammed Mamun; Md Emran Hasan; Moneerah Mohammad...; David Gozal
• Keywords: Psychiatry; Neurophysiology and neuropsychology; insomnia; QP351-495; RC435-571; abnormal sleep duration; mental health.; sleep disturbances; 03 medical and health sciences; 0302 clinical medicine; university entrance exams; Original Research

Background: Sleep disruptions among prospective university students are increasingly recognized for their potential ramifications on academic achievement and psychological well-being.But, information regarding sleep issues preparing entrance exams is unknown.Thus, this study aimed to investigate the prevalence factors associated with duration insomnia test-takers in Bangladesh, utilizing both traditional statistical analyses advanced geographic system machine learning techniques enhanced predictive capability.Methods: A cross-sectional was conducted June 2023 1496 at Jahangirnagar University, Dhaka.Structured questionnaires collected data demographics, information, mental health assessments.Statistical analyses, including chi-square tests logistic regression, were performed using SPSS, while models applied Python Google Colab.Results: Approximately 62.9% of participants reported abnormal (<7 hours/night or >9 hours/night), 25.5% experiencing insomnia.Females those dissatisfied mock more likely report duration, repeat test-takers, unsatisfactory test results, anxiety symptoms had a higher risk insomnia.Machine identified satisfaction previous as most significant predictor disturbances, secondary school certificate GPA least influence.The CatBoost model achieved maximum accuracy rates 61.27% 73.46%, respectively, predicting insomnia, low log loss values indicating robust performance.Geographic analysis revealed regional variations some southern districts northern eastern districts.Conclusion: disturbances prevalent various gender, test-taking status, satisfaction, anxiety.Targeted interventions, education support, hold promise ameliorating overall well-being students, potentially enhancing performance.