Background: Depression is one of the most prevalent mental illnesses among college students worldwide. Using the family triad dataset, this study investigated machine learning (ML) models to predict the risk of depression in college students and identify important family and individual factors.Methods: This study predicted college students at risk of depression and identified significant family and individual factors in 171 family data (171 fathers, mothers, and college students). The prediction accuracy of three ML models, sparse logistic regression (SLR), support vector machine (SVM), and random forest (RF), was compared.Results: The three ML models showed excellent prediction capabilities. The RF model showed the best performance. It revealed five significant factors responsible for depression: self-perceived mental health of college students, neuroticism, fearful-avoidant attachment, family cohesion, and mother's depression. Additionally, the logistic regression model identified five factors responsible for depression: the severity of cancer in the father, the severity of respiratory diseases in the mother, the self-perceived mental health of college students, conscientiousness, and neuroticism.Discussion: These findings demonstrated the ability of ML models to accurately predict the risk of depression and identify family and individual factors related to depression among Korean college students. With recent developments and ML applications, our study can improve intelligent mental healthcare systems to detect early depressive symptoms and increase access to mental health services.

Objectives: This study used structural equation modeling to test the mediated model of late-life depression to understand the mechanisms that account for the direct and indirect effects of spiritual variables and purpose in life on depression within the context of Korean family caregiving relationships. Method: A secondary analysis study design used data from a study that tested a theory of family interdependence of 157 Korean elder-family caregiver dyads in Seoul, Korea. Results: Both caregivers’ and elders’ self-transcendence was positively related to their own sense of purpose in life. However, only elders’ spiritual perspective was related to purpose in life. Also, elders’ purpose in life was positively associated with caregivers’ purpose in life. Furthermore, there was a strong negative relationship between elders’ purpose in life and their depressive symptoms, but there was not a significant negative relationship between caregivers’ purpose in life and elders’ depressive symptoms. Last, elders’ purpose in life mediated the negative effects of elders’ self-transcendence and spiritual perspective and of caregivers’ self-transcendence and purpose in life on elders’ depression. Conclusion: The findings suggest that purpose in life for both the caregiver and elder played an important role in elders’ depression. Self-transcendence also was related to decreased depression in elders. It is suggested that more attention be given to caregiver and elder purpose in life in developing interventions to reduce or avoid elder depression in Korean elders.

The purpose of this secondary analysis study was to determine whether care recipients’ nighttime sleep patterns, medical comorbidity, observed nocturnal agitation behaviors, and caregivers’ perceptions of nocturnal agitation behaviors in care recipients with dementia are associated with caregiver burden. Sixty care recipient–caregiver dyads, comprising older adults with geriatrician-diagnosed dementia living at home with caregivers, participated. Caregivers’ perceptions of the frequency of care recipients’ nocturnal agitation behaviors were associated with caregiver burden; however, objective, real-time data on the frequency of nocturnal agitation behaviors were not associated with burden. Care recipients’ increased minutes of wakefulness before falling asleep and severe cognitive impairment with musculoskeletal/integument and neurological comorbidities were associated with higher caregiver burden. These results suggest that targeted interventions to reduce sleep onset latency, medical comorbidity, and caregivers’ perception of frequency of nocturnal behaviors may reduce caregiver burden. [Res Gerontol Nurs. 2014; 7(5):206–214.]

The nature of family relationships is a critical measure for healthcare professionals who work with families. In particular, non‐Western cultural groups display a higher level of collectivism that emphasizes relationships between family members. This paper reports the development and psychometric testing of a new scale, the Korean Family Relationship Assessment Scale (FRAS). Using DeVellis’ Guidelines in Scale Development, a pool of 40 items was created after a review of the literature, followed by an assessment for content validity by six experts. Both exploratory and confirmatory factor analyses were conducted with data from a sample of 217 Korean family triads (father, mother, and college‐aged offspring) (N = 651). The final evaluation yielded three factors with 15 items: family support, family conflict, and family togetherness. Since the FRAS demonstrated good internal consistency and validity, it would be able to facilitate research on the relationships between family support, conflict, togetherness, and health. Applying this new instrument in theory‐based research may contribute to knowledge about the role of the family in the health and well‐being of family members within a Korean context. For clinical practice, this culturally sensitive and valid instrument has the potential to measure changes in family relationships after family therapy or interventions.

Logan JG, et al. Korean Circ J. 2016 Nov;46(6):834-840. https://doi.org/10.4070/kcj.2016.46.6.834