Logo image
Machine Learning Prediction of First Suicide Attempts in Early Adolescence Among Child Ideators
Journal article   Open access   Peer reviewed

Machine Learning Prediction of First Suicide Attempts in Early Adolescence Among Child Ideators

Josh Nguyen, Dominic B. Dwyer, Scott D. Tagliaferri, Simon Hartmann, Scott R. Clark, Isabelle Scott, Johanna T.W. Wigman, Ashleigh Lin, Andrew Thompson, Caroline X. Gao, …
Journal of the American Academy of Child and Adolescent Psychiatry
06/08/2026
PMID: 42562219

Abstract

ABCD children longitudinal suicide Machine Learning
Identifying those at highest risk of making a first suicide attempt during adolescence is crucial to inform early suicide prevention. Our study aimed to predict the first ideation-to-attempt transition during adolescence among children with suicidal ideation at baseline using 187 sociodemographic, clinical, neurocognitive, functional and structural brain predictors. Data was obtained from the multisite, longitudinal Adolescent Brain Cognitive Development (ABCD) study, conducted in 21 US sites among 11,864 children aged 9-10 years at baseline with 4 follow-up waves measured between 2018-2022. The primary outcome was suicide attempt reported at any of the follow-up waves amongst children with suicidal ideation at baseline. Machine learning models were trained using 70% of the sample from 14 sites, and validated in participants from 7 holdout sites. The final sample included 660 children with suicidal ideation at baseline (no previous suicide attempt; mean[SD] age: 9.91[0.63] years; 42% female at baseline), of whom 83 children had a first suicide attempt within 4 year follow-up. The final model, which excluded the brain imaging feature as its inclusion did not improve performance, generalized well to the external holdout sites (AUC-ROC[95% CI]=0.75[0.68, 0.83], sensitivity = 0.65 [0.61, 0.75], specificity = 0.69 [0.50, 0.80], PPV = 0.23 [0.15, 0.34], NPV = 0.94 [0.88, 0.97]), p <.001) with good expected calibration error of 0.03. The model was unbiased across race and sex subgroups. The top contributing features included female sex, presence of self-harm, access to means, generalized anxiety disorder, social anxiety, impulsivity, severity of suicidal ideation, parental income and clinical treatment history. Our model using clinically accessible features predicts the first-onset suicide attempt in children. Most predictors (e.g., suicidal ideation severity, impulsivity, anxiety symptoms) are modifiable, highlighting the potential intervention targets. Findings provide longitudinal evidence for key risk factors for the ideation-attempt transition in current suicide theories.
pdf
PIIS08908567260156501,009.57 kBDownloadView
Open Access CC BY V4.0
url
https://doi.org/10.1016/j.jaac.2026.07.1245View
Published (Version of record) Open

Metrics

1 Record Views

Details

Logo image

Usage Policy