An Artificial Neural Network to Predict Depression Symptoms Through Emotional Divorce and Spiritual Beliefs in Married University Students.

Background and Objectives: Spirituality and spiritual beliefs are among the factors playing key roles in preventing psychological disorders. The present study aimed to investigate the relationship between depression symptoms with emotional divorce and spiritual beliefs using artificial neural networks (ANN) in married university students. Methods: The statistical population of this descriptive-correlational study included all married students at the Islamic Azad University of Ahvaz (Khuzestan Province, Iran) during the 2021–22 academic year. The convenience sampling technique was adopted to select 301 married students as the research sample. An ANN was employed and data collection was done using the Beck’s depression inventory, emotional divorce scale, and religious orientation scale. Data analysis was performed through the Pearson correlation coefficient, stepwise regression, and an ANN. Results: The results showed a significant positive relationship between emotional divorce and depression symptoms, whereas there was a significant negative relationship between intrinsic religious beliefs and depression symptoms (P<0.001). However, a significant positive relationship existed between extrinsic religious beliefs and depression symptoms (P<0.001). Furthermore, depression symptoms were associated with emotional divorce and intrinsic/extrinsic religious beliefs in married university students. The results of the ANN also showed that emotional divorce had the most relationship with the depression symptoms of married students. Conclusion: The ANN appropriately predicted depression symptoms through an emotional divorce and spiritual beliefs among married university students. The results indicated the necessity of paying more attention to marital relationships, emotional divorce improvement, and depression alleviation. [ABSTRACT FROM AUTHOR]

Copyright of Health, Spirituality & Medical Ethics Journal is the property of Qom University of Medical Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)