scholarly journals Predicting suicidal thoughts and behaviors among college students: a machine learning approach

Author(s):  
Melissa Macalli ◽  
Marie Navarro ◽  
Massimiliano Orri ◽  
Marie Tournier ◽  
Rodolphe Thiébaut ◽  
...  

Abstract Suicidal thoughts and behaviors are prevalent among college students. Yet little is known about screening tools to identify students at higher risk. We aimed to develop a risk algorithm to identify the main predictors of suicidal thoughts and behaviors among college students within one-year of baseline assessment. We used data collected in 2013–2019 from the French i-Share cohort, a longitudinal population-based study including 5066 volunteer students. To predict suicidal thoughts and behaviours at follow-up, we used random forests models with 70 potential predictors measured at baseline, including sociodemographic and familial characteristics, mental health and substance use. Model performance was measured using the area under the receiver operating curve (AUC), sensitivity, and positive predictive value. At follow-up, 17.4% of girls and 16.8% of boys reported suicidal thoughts and behaviors. The models achieved good predictive performance: AUC, 0.8; sensitivity, 79% for girls, 81% for boys; and positive predictive value, 40% for girls and 36% for boys. Among the 70 potential predictors, four showed the highest predictive power: 12-month suicidal thoughts, trait anxiety, depression symptoms, and self-esteem. We identified a parsimonious set of mental health indicators that accurately predicted one-year suicidal thoughts and behaviors in a community sample of college students.

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Melissa Macalli ◽  
Marie Navarro ◽  
Massimiliano Orri ◽  
Marie Tournier ◽  
Rodolphe Thiébaut ◽  
...  

AbstractSuicidal thoughts and behaviours are prevalent among college students. Yet little is known about screening tools to identify students at higher risk. We aimed to develop a risk algorithm to identify the main predictors of suicidal thoughts and behaviours among college students within one-year of baseline assessment. We used data collected in 2013–2019 from the French i-Share cohort, a longitudinal population-based study including 5066 volunteer students. To predict suicidal thoughts and behaviours at follow-up, we used random forests models with 70 potential predictors measured at baseline, including sociodemographic and familial characteristics, mental health and substance use. Model performance was measured using the area under the receiver operating curve (AUC), sensitivity, and positive predictive value. At follow-up, 17.4% of girls and 16.8% of boys reported suicidal thoughts and behaviours. The models achieved good predictive performance: AUC, 0.8; sensitivity, 79% for girls, 81% for boys; and positive predictive value, 40% for girls and 36% for boys. Among the 70 potential predictors, four showed the highest predictive power: 12-month suicidal thoughts, trait anxiety, depression symptoms, and self-esteem. We identified a parsimonious set of mental health indicators that accurately predicted one-year suicidal thoughts and behaviours in a community sample of college students.


2020 ◽  
Vol 288 ◽  
pp. 112988
Author(s):  
Paula Suárez-Pinilla ◽  
Marina Pérez-Herrera ◽  
Marta Suárez-Pinilla ◽  
Raquel Medina-Blanco ◽  
Enrique López-García ◽  
...  

2020 ◽  
Author(s):  
Namik Kirlic ◽  
Elisabeth Akeman ◽  
Danielle DeVille ◽  
Henry Yeh ◽  
Kelly T. Cosgrove ◽  
...  

Background: An estimated 1100 college students die by suicide each year. Our ability to predict who is at risk for suicide, as well as our knowledge of resilience factors protecting against it, remains limited. We used a machine learning (ML) framework in conjunction with a large battery of self-report and demographic measures to select features contributing most to observed variability in suicidal thoughts and behaviors (STBs) in college.Method: First-year university students completed demographic and clinically-relevant self-report measures at the beginning of the first semester of college (baseline; n=356), and at end-of-year (n=228). Suicide Behaviors Questionnaire-Revised (SBQ-R) assessed STBs. A ML pipeline with 55 and 57 variables using stacking and nested cross-validation to avoid overfitting was conducted to examine predictors of baseline and end-of-year STBs, respectively. Results: For baseline SBQ-R score, the identified ML algorithm explained 28.3% of variance (95%CI: 28-28.5%), with depression severity, meaning and purpose in life, and social isolation among the most important predictors. For end-of-year SBQ-R score, the identified algorithm explained 5.6% of variance [95%CI: 5.1-6.1%], with baseline SBQ-R score, emotional suppression, and positive emotional experiences among the most important predictors.Limitations: External validation of the model with another independent sample is needed for further demonstrating its replicability.Conclusions: ML analyses replicated known factors contributing to STBs, and identified novel, potentially modifiable risk and resilience factors. Intervention programing on college campuses aiming to reduce depressive symptomatology, promote positive affect and social connectedness, and foster a sense of meaning and purpose, may be effective in reducing STBs.


2019 ◽  
Author(s):  
Alyssa C Milton ◽  
Benjamin A Gill ◽  
Tracey A Davenport ◽  
Mitchell Dowling ◽  
Jane M Burns ◽  
...  

BACKGROUND The rapid uptake of information and communication technology (ICT) over the past decade—particularly the smartphone—has coincided with large increases in sexting. All previous Australian studies examining the prevalence of sexting activities in young people have relied on convenience or self-selected samples. Concurrently, there have been recent calls to undertake more in-depth research on the relationship between mental health problems, suicidal thoughts and behaviors, and sexting. How sexters (including those who receive, send, and two-way sext) and nonsexters apply ICT safety skills warrants further research. OBJECTIVE This study aimed to extend the Australian sexting literature by measuring (1) changes in the frequency of young people’s sexting activities from 2012 to 2014; (2) young people’s beliefs about sexting; (3) association of demographics, mental health and well-being items, and internet use with sexting; and (4) the relationship between sexting and ICT safety skills. METHODS Computer-assisted telephone interviewing using random digit dialing was used in two Young and Well National Surveys conducted in 2012 and 2014. The participants included representative and random samples of 1400 young people aged 16 to 25 years. RESULTS From 2012 to 2014, two-way sexting (2012: 521/1369, 38.06%; 2014: 591/1400, 42.21%; P=.03) and receiving sexts (2012: 375/1369, 27.39%; 2014: 433/1400, 30.93%; P<.001) increased significantly, not sexting (2012: 438/1369, 31.99%; 2014: 356/1400, 25.43%; P<.001) reduced significantly, whereas sending sexts (2012: n=35/1369, 2.56%; 2014: n=20/1400, 1.43%; P>.05) did not significantly change. In addition, two-way sexting and sending sexts were found to be associated with demographics (male, second language, and being in a relationship), mental health and well-being items (suicidal thoughts and behaviors and body image concerns), and ICT risks (cyberbullying others and late-night internet use). Receiving sexts was significantly associated with demographics (being male and not living with parents or guardians) and ICT risks (being cyberbullied and late-night internet use). Contrary to nonsexters, Pearson correlations demonstrated that all sexting groups (two-way, sending, and receiving) had a negative relationship with endorsing the ICT safety items relating to being careful when using the Web and not giving out personal details. CONCLUSIONS Our research demonstrates that most young Australians are sexting or exposed to sexting in some capacity. Sexting is associated with some negative health and well-being outcomes—specifically, sending sexts is linked to suicidal thoughts and behaviors, body image issues, and ICT safety risks, including cyberbullying and late-night internet use. Those who do sext are less likely to engage in many preventative ICT safety behaviors. How the community works in partnership with young people to address this needs to be a multifaceted approach, where sexting is positioned within a wider proactive conversation about gender, culture, psychosocial health, and respecting and caring for each other when on the Web.


2018 ◽  
Vol 57 (4) ◽  
pp. 263-273.e1 ◽  
Author(s):  
Philippe Mortier ◽  
Randy P. Auerbach ◽  
Jordi Alonso ◽  
Jason Bantjes ◽  
Corina Benjet ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document