Applying machine learning to investigate future life-oriented predictors of adolescents' near-term suicidal ideation.
4 affiliations
- 1Yale Child Study Center, Yale School of Medicine, New Haven, CT 06511, USA.
- 2Department of Counseling and Clinical Psychology, Teachers College, Columbia University, NY, NY 10027, USA.
- 3Department of Psychology, Yale University, New Haven, CT 06511, USA.
- 4Yale Center for Brain and Mind Health, Yale School of Medicine, New Haven, CT 06511, USA.
Abstract
Background
Adolescents contemplating suicide consider both the discontinuation and continuation of their lives. Yet prior research has mainly focused on what suicidal youth want to escape from (i.e., distress-oriented predictors) rather than what may keep them living into the future. This study applies machine learning (ML) to examine how adolescents' momentary Future Life-Oriented (FLO) processes predict their near-term changes in suicidal ideation (SI).Methods
Adolescents (N = 121; 15-17 years) completed a 14-day, 5x/day smartphone-based ecological momentary assessment protocol, reporting on a range of FLO predictors (e.g., vividness, importance, emotional valence of future life events), distress-oriented predictors (e.g., prior SI, stressors, affect), and SI. ML algorithms were trained on time-series data to predict future SI based on FLO and distress-oriented predictors. To identify optimal temporal prediction windows, we implemented a sliding-window approach and compared models across multiple temporal frames.Results
Models including FLO variables significantly improved prediction of subsequent SI (AUC = 0.880) relative to models using prior SI (AUC = 0.783) alone or prior SI with stress/affect (AUC = 0.781). The best-performing model (Random Forest; AUC = 0.956) achieved optimal prediction using seven prior observations to forecast SI two timepoints ahead (avg. 11h). SHAP analyses identified prior SI and two FLO variables (desire to live, future thought uncontrollability) as the most influential predictors of SI.Conclusions
Adolescents' momentary FLO processes meaningfully enhance near-term prediction of SI, highlighting a potentially promising collection of modifiable targets for suicide prevention.
Related
- Predictors of suicide attempt in adolescents with a history of self-harm: a machine learning study combining psychosocial and actigraphy measures
- Psychophysiological Trajectories of Trauma Recovery: A Process-Oriented Randomized Comparison of Internal Family Systems (IFS) and Emotion-Focused Training for Self-Compassion and Self-Protection (EFT-SCP) in Traumatized Adolescents
- Differentiating nonfluent/agrammatic and logopenic primary progressive aphasia in Catalan-Spanish bilinguals by applying multilingual multimodal machine learning to connected speech
- The effectiveness of the Youth-Oriented Mental Health Education Program (Y-MIND) school-based psychoeducational program in improving mental health literacy and reducing psychological distress among adolescents in Klaten, Indonesia: A quasi-experimental study
- Examining individual and school-level predictors of positive attitudes towards condom use among adolescents in Tanzania: An exploratory analysis using hierarchical linear modeling
BibTeX
@article{lee2026applying,
title = {{Applying machine learning to investigate future life-oriented predictors of adolescents' near-term suicidal ideation.}},
author = {Da-Eun Lee and Olivia Lawrence and Ki Eun Shin and Shirley B Wang and Christine B Cha},
journal = {Journal of affective disorders reports},
year = {2026},
month = jun,
doi = {10.1016/j.jadr.2026.101105},
url = {https://europepmc.org/article/MED/43011987},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Applying machine learning to investigate future life-oriented predictors of adolescents' near-term suicidal ideation.
AU - Da-Eun Lee
AU - Olivia Lawrence
AU - Ki Eun Shin
AU - Shirley B Wang
AU - Christine B Cha
PY - 2026
DA - 2026/06/15
JO - Journal of affective disorders reports
DO - 10.1016/j.jadr.2026.101105
UR - https://europepmc.org/article/MED/43011987
AB - Background Adolescents contemplating suicide consider both the discontinuation and continuation of their lives. Yet prior research has mainly focused on what suicidal youth want to escape from (i.e., distress-oriented predictors) rather than what may keep them living into the future. This study applies machine learning (ML) to examine how adolescents' momentary Future Life-Oriented (FLO) processes predict their near-term changes in suicidal ideation (SI).Methods Adolescents (N = 121; 15-17 years) completed a 14-day, 5x/day smartphone-based ecological momentary assessment protocol, reporting on a range of FLO predictors (e.g., vividness, importance, emotional valence of future life events), distress-oriented predictors (e.g., prior SI, stressors, affect), and SI. ML algorithms were trained on time-series data to predict future SI based on FLO and distress-oriented predictors. To identify optimal temporal prediction windows, we implemented a sliding-window approach and compared models across multiple temporal frames.Results Models including FLO variables significantly improved prediction of subsequent SI (AUC = 0.880) relative to models using prior SI (AUC = 0.783) alone or prior SI with stress/affect (AUC = 0.781). The best-performing model (Random Forest; AUC = 0.956) achieved optimal prediction using seven prior observations to forecast SI two timepoints ahead (avg. 11h). SHAP analyses identified prior SI and two FLO variables (desire to live, future thought uncontrollability) as the most influential predictors of SI.Conclusions Adolescents' momentary FLO processes meaningfully enhance near-term prediction of SI, highlighting a potentially promising collection of modifiable targets for suicide prevention.
SN - 2666-9153
ER -