Association of Online Risk Factors With Subsequent Youth Suicide-Related Behaviors in the US

Sumner, Steven A.; Ferguson, Brock; Bason, Brian; Dink, Jacob; Yard, Ellen E.; Hertz, Marci; Hilkert, Brandon; Holland, Kristin M.; Mercado-Crespo, Melissa C.; Tang, Shichao; Jones, Christopher M.

doi:10.1001/jamanetworkopen.2021.25860

Cited by 11 publications

(11 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, suicide attempt, described as the self-injurious behaviour is intended to cause death but leads to a non-fatal outcome, is reported to be 20 times more frequent than the suicide itself [ 1 ]. Suicidal deaths occur in all races, genders, and age groups, but disproportionally affects males and youth in almost all populations [ 2 ]. For instance, it was reported to be the fourth leading cause of death in youth in 2019 (WHO, 2021).…”

Section: Suicide Overviewmentioning

confidence: 99%

Role of pets and animal assisted therapy in suicide prevention

Shoib

Hussaini

Chandradasa

et al. 2022

Annals of Medicine &Amp; Surgery

View full text Add to dashboard Cite

Section: Suicide Overviewmentioning

confidence: 99%

Role of pets and animal assisted therapy in suicide prevention

Shoib

Hussaini

Chandradasa

et al. 2022

Annals of Medicine &Amp; Surgery

View full text Add to dashboard Cite

“…This contrasts with media, research, and other reports of increases in cyberbullying among children during the pandemic (e.g., Jain et al, 2020; Karmakar & Das, 2020). It also suggests that while we know the effectiveness of bullying prevention strategies employed during in-person learning contexts (Fraguas et al, 2021; Gaffney et al, 2019), there is a need to assess how novel- and/or evidence-based bullying and other violence prevention strategies have or can be applied to virtual learning contexts (Nikiforos et al, 2020; Sumner et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

Parents’ Self-reported Changes in Concern About Children’s Bullying—Fall ConsumerStyles and Estilos Surveys, United States, 2020

Mercado

Wang

Kollar

2022

J Interpers Violence

View full text Add to dashboard Cite

Bullying is a type of youth violence and an adverse childhood experience that can result in trauma and have immediate and long-term consequences for all involved. It can happen at school or elsewhere — including online entertainment and social and learning environments. Some children are at increased risk for bullying victimization, such as those targeted because of their racial/ethnic background or cultural identity. This study assessed U.S. parents and caregivers’ self-reported changes in concern about their children’s involvement in bullying during Fall 2020 compared to the prior year, which was marked by extraordinary historical circumstances (e.g., COVID-19 pandemic, heightened awareness of racial inequities, schools transitioning to virtual learning). Secondary analyses of data from the 2020 Fall ConsumerStyles and Estilos online panel surveys — designed to be representative of U.S. adults overall and U.S. Hispanic adults, respectively — were conducted. Differences by children’s type of school attendance (i.e., physically at school or not) and parents’ sociodemographic characteristics were explored. While findings suggest that U.S. parents’ concern for their children being bullied during Fall 2020 compared to the prior year did not change, significant differences were found by the children’s type of school attendance and the parents’ race/ethnicity — with increased concern among parents of children who physically attended school, non-Hispanic Black parents and Hispanic parents. Among parents who reported being less concerned during Fall 2020 about their children being bullied compared to the prior year, not being physically at school is noted as the main reason why. Parents who reported being more concerned frequently noted racism as the reason why. It is imperative to understand what parents think about bullying, to best inform efforts to support their key role in bullying prevention.

show abstract

“…The Add Health data included a wide net of social determinants and related features that are known suicide risk factors [11][12][13][14]26]. We considered 23 features.…”

Section: Datasets and Cohortsmentioning

confidence: 99%

Target-based fusion using social determinants of health to enhance suicide prediction with electronic health records

et al. 2023

View full text Add to dashboard Cite

Objective Preventing suicide in US youth is of paramount concern, with rates increasing over 50% between 2007 and 2018. Statistical modeling using electronic health records may help identify at-risk youth before a suicide attempt. While electronic health records contain diagnostic information, which are known risk factors, they generally lack or poorly document social determinants (e.g., social support), which are also known risk factors. If statistical models are built incorporating not only diagnostic records, but also social determinants measures, additional at-risk youth may be identified before a suicide attempt. Methods Suicide attempts were predicted in hospitalized patients, ages 10–24, from the State of Connecticut’s Hospital Inpatient Discharge Database (HIDD; N = 38943). Predictors included demographic information, diagnosis codes, and using a data fusion framework, social determinants features transferred or fused from an external source of survey data, The National Longitudinal Study of Adolescent to Adult Health (Add Health). Social determinant information for each HIDD patient was generated by averaging values from their most similar Add Health individuals (e.g., top 10), based upon matching shared features between datasets (e.g., Pearson’s r). Attempts were then modelled using an elastic net logistic regression with both HIDD features and fused Add Health features. Results The model including fused social determinants outperformed the conventional model (AUC = 0.83 v. 0.82). Sensitivity and positive predictive values at 90 and 95% specificity were almost 10% higher when including fused features (e.g., sensitivity at 90% specificity = 0.48 v. 0.44). Among social determinants variables, the perception that their mother cares and being non-religious appeared particularly important to performance improvement. Discussion This proof-of-concept study showed that incorporating social determinants measures from an external survey database could improve prediction of youth suicide risk from clinical data using a data fusion framework. While social determinant data directly from patients might be ideal, estimating these characteristics via data fusion avoids the task of data collection, which is generally time-consuming, expensive, and suffers from non-compliance.

show abstract

Association of Online Risk Factors With Subsequent Youth Suicide-Related Behaviors in the US

Cited by 11 publications

References 46 publications

Role of pets and animal assisted therapy in suicide prevention

Role of pets and animal assisted therapy in suicide prevention

Parents’ Self-reported Changes in Concern About Children’s Bullying—Fall ConsumerStyles and Estilos Surveys, United States, 2020

Target-based fusion using social determinants of health to enhance suicide prediction with electronic health records

Contact Info

Product

Resources

About