An Investigation into the Relationship among Psychiatric, Demographic and Socio-Economic Variables with Bayesian...

Area of Science:

• Psychology
• Data Science
• Public Health

Background:

• Mental health challenges among university students are a growing concern.
• Understanding the interplay of demographic, socioeconomic, and psychiatric factors is crucial for targeted interventions.
• Existing research often examines these factors in isolation, necessitating integrated analytical approaches.

Purpose of the Study:

• To investigate factors influencing depression, hopelessness, and self-esteem in university students.
• To model the relationships among psychiatric, demographic, and socioeconomic variables using Bayesian networks.
• To identify key predictors of mental health outcomes in a student population.

Main Methods:

• Utilized Bayesian network modeling with the b n l e a r n package in R.
• Analyzed data from 823 university students, encompassing 21 psychiatric, demographic, and socioeconomic variables.
• Employed two discretization approaches for continuous variables to construct two distinct Bayesian network models.

Main Results:

• Bayesian network analysis indicated gender influences depression levels, with female students reporting higher depression.
• Social activity was identified as a direct influencer of depression levels in the second model.
• Depression significantly impacted both hopelessness and self-esteem; increased depression correlated with higher hopelessness and lower self-esteem.

Conclusions:

• Bayesian networks provide a robust framework for understanding complex mental health interrelationships in students.
• Identified specific demographic (gender) and socioeconomic (social activity) factors associated with depression.
• Findings highlight the cascading negative effects of depression on hopelessness and self-esteem, underscoring the need for mental health support.