RESUMO
Background and Aims: Mental health problem is a rising public health concern. People of all ages, specially Bangladeshi university students, are more affected by this burden. Thus, the objective of the study was to use tree-based machine learning (ML) models to identify major risk factors and predict anxiety, depression, and insomnia in university students. Methods: A social media-based cross-sectional survey was employed for data collection. We used Generalized Anxiety Disorder (GAD-7), Patient Health Questionnaire (PHQ-9) and Insomnia Severity Index (ISI-7) scale for measuring students' anxiety, depression and insomnia problems. The tree-based supervised decision tree (DT), random forest (RF) and robust eXtreme Gradient Boosting (XGBoost) ML algorithms were used to build the prediction models and their predictive performance was evaluated using confusion matrix and receiver operating characteristic (ROC) curves. Results: Of the 1250 students surveyed, 64.7% were male and 35.3% were female. The students' ages ranged from 18 to 26 years old, with an average age of 22.24 years (SD = 1.30). Majority of the students (72.6%) were from rural areas and social media addicted (56.6%). Almost 83.3% of the students had moderate to severe anxiety, 84.7% had moderate to severe depression and 76.5% had moderate to severe insomnia problems. Students' social media addiction, age, academic performance, smoking status, monthly family income and morningness-eveningness are the main risk factors of anxiety, depression and insomnia. The highest predictive performance was observed from the XGBoost model for anxiety, depression and insomnia. Conclusion: The study findings offer valuable insights for stakeholders, families and policymakers enabling a more profound comprehension of the pressing mental health disorders. This understanding can guide the formulation of improved policy strategies, initiatives for mental health promotion, and the development of effective counseling services within university campus. Additionally, our proposed model might play a critical role in diagnosing and predicting mental health problems among Bangladeshi university students and similar settings.
RESUMO
BACKGROUND: Bangladesh is a densely populated country with a substandard healthcare system and a mediocre economic framework. Due to the enormous number of people who have been unaware until now, the development of COVID-19's second-wave infection has become a severe threat. The present investigation aimed to characterize the clinical and socio-demographic characteristics of COVID-19 in Bangladesh. METHODS: A cross-sectional analysis was carried out from all the other COVID-19 patients and confirmed by RT-PCR undergoing a specialized COVID-19 hospital. From March 1 to April 15, 2021, a total of 1326 samples were collected. Samples were only obtained from non-critical COVID-19 patients as critically ill patients required emergency intensive care medications. Then, from April 17 to May 03, 2021, SARS-CoV-2 infection and clinical assessment was performed based on interim guidelines from the WHO. The diagnosis was conducted through RT-PCR. Later, identifying the symptomatic and asymptomatic patient based on checking the Clinical Observation Form (COF). The patients filled the COF form. Finally, statistical analyses were done using the SPSS 20 statistical program. RESULTS: In this investigation, a total of 326 patients were diagnosed as COVID-19 positive. Among them, approximately 19.02% (n = 62) were asymptomatic, and 80.98% (n = 264) were symptomatic. Here, the finding shows that the occurrence of this infection was varied depending on age, sex, residence, occupation, smoking habit, comorbidities, etc. However, Males (60.12%) were more affected than females (39.88%), and, surprisingly, this pandemic infected both urban and rural residents almost equally (urban = 50.92%; rural = 49.08%). Approximately 19% of the asymptomatic and 62% of symptomatic cases had at least one comorbid disorder. Interestingly, an unexpected result was exhibited in the case of smokers, where non-smokers were more affected than smokers. The study indicates community transmission of COVID 19, where people were highly infected at their occupations (35.58%), at houses (23.93%) and by traveling (12.88%). Noteworthy, according to this report, a large number (19.33%) of individuals did not know exactly how they were contaminated with SARS-CoV-2. Patients were most commonly treated by an antibiotic 95.09%, followed in second by corticosteroid 46.01%. Anti-viral drugs, remdesivir, and oxygenation are also needed for other patients. Among those, who were being treated, approximately 69.33% were isolated at home, 27.91% were being treated at dedicated COVID-19 hospitals. Finally, 96.63% were discharged without complications, and 0.03% has died. CONCLUSION: This investigation concludes that males became more infected than females. Interestingly, both urban and rural people became nearly equally infected. It noticed community transmission of SARS-CoV-2, where people were highly infected at their workplaces. A higher rate of silent transmission indicates that more caution is needed to identify asymptomatic patients. Most of the infected people were isolated at home whereas nearly one-fourth were treated at hospitals. Clinically, antibiotics were the most widely used treatment. However, the majority of the patients were discharged without complications. The current investigation would be helpful to understand the clinical manifestations and socio-demographic situations during the second wave of the COVID-19 pandemic in Bangladesh.