Predicting 3-year persistent or recurrent major depressive episode using machine learning techniques

Fialho, Amanda Rodrigues; Montezano, Bruno Braga; Ballester, Pedro; Cardoso, Taiane de Azevedo; Mondin, Thaíse Campos; Moreira, Fernanda Pedrotti; Souza, Luciano Dias de Mattos; Silva, Ricardo Azevedo da; Jansen, Karen

doi:10.1016/j.psycom.2022.100055

Cited by 2 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 94 , 95 Similarly, a machine learning study found that suicidality was the top predictor of persistent and recurrent depression over three years. 96 In tandem with those studies, our findings suggest that SI and SP have prominent roles in linking depression and suicidality during the COVID-19 pandemic. Despite the importance of SI and SP, there are still insufficient diagnostic criteria for suicidal ideation and inadequate understanding of passive suicidal behavior.…”

Section: Discussionsupporting

confidence: 82%

The Inter-Relationships Between Depressive Symptoms and Suicidality Among Macau Residents After the “Relatively Static Management” COVID-19 Strategy: A Perspective of Network Analysis

Lam,

Cai,

Chen

et al. 2024

NDT

View full text Add to dashboard Cite

Background Suicidality is a global public health problem which has increased considerably during the coronavirus disease 2019 (COVID-19) pandemic. This study examined the inter-relationships between depressive symptoms and suicidality using network analysis among Macau residents after the “relatively static management” COVID-19 strategy. Methods An assessment of suicidal ideation (SI), suicide plan (SP), suicide attempt (SA) and depressive symptoms was conducted with the use of individual binary response items (yes/no) and Patient Health Questionnaire (PHQ-9). In the network analysis, central and bridge symptoms were identified in the network through “Expected Influence” and “Bridge Expected Influence”, and specific symptoms that were directly associated with suicidality were identified via the flow function. Network Comparison Tests (NCT) were conducted to examine the gender differences in network characteristics. Results The study sample included a total of 1008 Macau residents. The prevalence of depressive symptoms and suicidality were 62.50% (95% CI = 59.4–65.5%) and 8.9% (95% CI = 7.2–10.9%), respectively. A network analysis of the sample identified SI (“Suicidal ideation”) as the most central symptom, followed by SP (“Suicide plan”) and PHQ4 (“Fatigue”). SI (“Suicidal ideation”) and PHQ6 (“Guilt”) were bridge nodes connecting depressive symptoms and suicidality. A flow network revealed that the strongest connection was between S (“Suicidality”) and PHQ6 (“Guilt”), followed by S (“Suicidality”) and PHQ 7 (“Concentration”), and S (“Suicidality”) and PHQ3 (“Sleep”). Conclusion The findings indicated that reduction of specific depressive symptoms and suicidal thoughts may be relevant in decreasing suicidality among adults. Further, suicide assessment and prevention measures should address the central and bridge symptoms identified in this study.

show abstract

Section: Discussionsupporting

confidence: 82%

The Inter-Relationships Between Depressive Symptoms and Suicidality Among Macau Residents After the “Relatively Static Management” COVID-19 Strategy: A Perspective of Network Analysis

Lam,

Cai,

Chen

et al. 2024

NDT

View full text Add to dashboard Cite

show abstract

“…However, these experiences may represent a smaller subset of a broader set of factors that together explain individuals' psychosocial functioning during the pandemic. Indeed, prediction or clinical risk models often reveal that factors such as preexisting mental health problems, social or family history, and physical health conditions have greater utility in predicting anxiety and depressive symptoms when compared to exposure to stressors or traumatic events (e.g., Fialho et al, 2022). It may also be the case that exposure to similar events prior to the pandemic may explain some of the variability in predicting depression or anxiety during the pandemic (Kolacz et al, 2020).…”

Section: Discussionmentioning

confidence: 99%

The Epidemic–Pandemic Impacts Inventory (EPII): A multisample study examining pandemic-related experiences and their relation to mental health.

Janssen,

McGuire,

López-Castro

et al. 2023

Psychological Assessment

View full text Add to dashboard Cite

The Epidemic–Pandemic Impacts Inventory (EPII) was developed to assess pandemic-related adverse and positive experiences across several key domains, including work/employment, home life, isolation, and quarantine. Several studies have associated EPII-assessed pandemic-related experiences with a wide range of psychosocial factors, most commonly depressive and anxiety symptoms. The present study investigated the degree to which specific types of COVID-19 pandemic-related experiences may be associated with anxiety and depression risk, capitalizing on two large, independent samples with marked differences in sociodemographic characteristics. The present study utilized two adult samples: participants (N = 635) recruited online over a 4-week period in early 2020 (Sample 1) and participants (N = 908) recruited from the student body of a large Northeastern public university (Sample 2). We employed a cross-validated, least absolute shrinkage and selection operator (LASSO) regression approach, as well as a random forest (RF) machine learning algorithm, to investigate classification accuracy of anxiety/depression risk using the pandemic-related experiences from the EPII. The LASSO approach isolated eight items within each sample. Two items from the work/employment and emotional/physical health domains overlapped across samples. The RF approach identified similar items across samples. Both methods yielded acceptable cross-classification accuracy. Applying two analytic approaches on data from two large, sociodemographically unique samples, we identified a subset of sample-specific and nonspecific pandemic-related experiences from the EPII that are most predictive of concurrent depression/anxiety risk. Findings may help to focus on key experiences during future public health disasters that convey greater risk for depression and anxiety symptoms.

show abstract

Predicting 3-year persistent or recurrent major depressive episode using machine learning techniques

Cited by 2 publications

References 16 publications

The Inter-Relationships Between Depressive Symptoms and Suicidality Among Macau Residents After the “Relatively Static Management” COVID-19 Strategy: A Perspective of Network Analysis

The Inter-Relationships Between Depressive Symptoms and Suicidality Among Macau Residents After the “Relatively Static Management” COVID-19 Strategy: A Perspective of Network Analysis

The Epidemic–Pandemic Impacts Inventory (EPII): A multisample study examining pandemic-related experiences and their relation to mental health.

Contact Info

Product

Resources

About