The association between attachment pattern and depression severity in Thai depressed patients

Machine learning models for predicting depression in Korean young employees

Background

The incidence of depression among employees has gradually risen. Previous studies have focused on predicting the risk of depression, but most studies were conducted using basic statistical methods. This study used machine learning algorithms to build models that detect and identify the important factors associated with depression in the workplace.

Methods

A total of 503 employees completed an online survey that included questionnaires on general characteristics, physical health, job-related factors, psychosocial protective, and risk factors in the workplace. The dataset contained 27 predictor variables and one dependent variable which referred to the status of employees (normal or at the risk of depression). The prediction accuracy of three machine learning models using sparse logistic regression, support vector machine, and random forest was compared with the accuracy, precision, sensitivity, specificity, and AUC. Additionally, the important factors identified via sparse logistic regression and random forest.

Results

All machine learning models demonstrated similar results, with the lowest accuracy obtained from sparse logistic regression and support vector machine (86.8%) and the highest accuracy from random forest (88.7%). The important factors identified in this study were gender, physical health, job, psychosocial protective factors, and psychosocial risk and protective factors in the workplace.

Discussion

The results of this study indicated the potential of machine learning models to accurately predict the risk of depression among employees. The identified factors that influence the risk of depression can contribute to the development of intelligent mental healthcare systems that can detect early signs of depressive symptoms in the workplace.

The Mediating Role of Precepts and Meditation on Attachment and Depressive Symptoms in Adolescents

Research shows that Buddhist precept adherence (i.e., abstaining from killing, stealing, sexual misconduct, lying, and intoxicant use) and meditation practice influence mental health outcomes. This study investigated how Buddhist precept adherence and meditation practice influenced the relationship between insecure attachment and depressive symptoms among Thai adolescents. A total of 453 Thai boarding-school students from 10th-12th grade were recruited from five boarding schools (two purposively selected Buddhist schools and three conveniently selected secular schools). They completed these tools: Experiences in Close Relationships Questionnaire-revised-18, Outcome-Inventory-21: Depression Subscale, Precept Practice Questionnaire, and Inner-Strength-Based Inventory: Meditation. A parallel mediation model analyzed the indirect effects of attachment anxiety and attachment avoidance on depression through precept adherence and meditation practice. The participants' demographics were 16.35 ± 0.96 years, 88% female, and 89.4% Buddhist. The mean scores for attachment anxiety were 2.7 ± 1.1; attachment avoidance, 2.78 ± 1.2; overall regular precept adherence, 20.1 ± 4.4; regular but not daily meditation, 2.94 ± 1.3; and low depressive symptoms, 3.75 ± 3.4. The standardized indirect effects for attachment anxiety (β = 0.042, 95% CI = 0.022, 0.070) and avoidance (β = 0.024, 95% CI = 0.009, 0.046) on depressive symptoms through meditation and precept adherence were significant. Meditation practice had a significantly higher indirect effect size than precept adherence.

Meditation and Five Precepts Mediate the Relationship between Attachment and Resilience

Secure attachment is fundamental to the development of resilience among adolescents. The present study investigated whether meditation and precept practices influence the relationship between attachment and resilience. This study recruited 453 10th−12th-grade boarding school students who completed the Experience of Close Relationship Questionnaire (revised), Resilience Inventory, Inner Strength-Based Inventory, and Precept Practice to assess attachment, resilience, meditation practice, and precepts adherence. The participants’ mean age was 16.35 ± 0.96 years; 87.9% were females, and 89.2% were Buddhists. A parallel mediation model within the structural equation framework was used for an analysis of the indirect effect of attachment on resilience through meditation and precept practices. The indirect effects of attachment anxiety and avoidance on resilience were β = −0.086, 95% CI = −0.125, −0.054, p < 0.001, and β = −0.050, 95% CI = −0.088, −0.021, p = 0.006, respectively. The indirect effect size resulting from meditation was significantly higher than that resulting from observance of the precepts. The parallel mediation model explained the 33% variance of the resilience scores, compared with 23% from the direct effect of attachment anxiety and avoidance only. This work provides evidence that meditation and precepts significantly affect the relationship between attachment and resilience.