A machine learning analysis of risk and protective factors of suicidal thoughts and behaviors in college students

Journal article

N. Kirlic, E. Akeman, Danielle C DeVille, Hung-wen Yeh, K. Cosgrove, Timothy McDermott, J. Touthang, A. Clausen, M. Paulus, R. Aupperle
Journal of American College Health, 2021

Semantic Scholar DOI PubMedCentral PubMed

Cite

APA Click to copy
Kirlic, N., Akeman, E., DeVille, D. C., Yeh, H.-wen, Cosgrove, K., McDermott, T., … Aupperle, R. (2021). A machine learning analysis of risk and protective factors of suicidal thoughts and behaviors in college students. Journal of American College Health.

Chicago/Turabian Click to copy
Kirlic, N., E. Akeman, Danielle C DeVille, Hung-wen Yeh, K. Cosgrove, Timothy McDermott, J. Touthang, A. Clausen, M. Paulus, and R. Aupperle. “A Machine Learning Analysis of Risk and Protective Factors of Suicidal Thoughts and Behaviors in College Students.” Journal of American College Health (2021).

MLA Click to copy
Kirlic, N., et al. “A Machine Learning Analysis of Risk and Protective Factors of Suicidal Thoughts and Behaviors in College Students.” Journal of American College Health, 2021.

BibTeX Click to copy

@article{n2021a,
  title = {A machine learning analysis of risk and protective factors of suicidal thoughts and behaviors in college students},
  year = {2021},
  journal = {Journal of American College Health},
  author = {Kirlic, N. and Akeman, E. and DeVille, Danielle C and Yeh, Hung-wen and Cosgrove, K. and McDermott, Timothy and Touthang, J. and Clausen, A. and Paulus, M. and Aupperle, R.}
}

Abstract

Abstract Objective To identify robust and reproducible factors associated with suicidal thoughts and behaviors (STBs) in college students. Methods 356 first-year university students completed a large battery of demographic and clinically-relevant self-report measures during the first semester of college and end-of-year (n = 228). Suicide Behaviors Questionnaire-Revised (SBQ-R) assessed STBs. A machine learning (ML) pipeline using stacking and nested cross-validation examined correlates of SBQ-R scores. Results 9.6% of students were identified at significant STBs risk by the SBQ-R. The ML algorithm explained 28.3% of variance (95%CI: 28–28.5%) in baseline SBQ-R scores, with depression severity, social isolation, meaning and purpose in life, and positive affect among the most important factors. There was a significant reduction in STBs at end-of-year with only 1.8% of students identified at significant risk. Conclusion Analyses replicated known factors associated with STBs during the first semester of college and identified novel, potentially modifiable factors including positive affect and social connectedness.