Silent struggles: a machine learning approach for predicting suicidal ideation based on crisis symptoms and childhood trauma in Saudi adolescents

Adolescent suicide is a significant public health concern, with rising rates globally and increasing psychological distress among youth. Despite its significance, limited research in Saudi Arabia has explored the combined impact of acute emotional crises and childhood trauma on suicidal ideation, particularly using machine learning approach. This study aimed to identify key psychological and trauma-related predictors of suicidal ideation among Saudi adolescents. It specifically examined the role of Suicidal Crisis Syndrome symptoms and childhood maltreatment experiences using both correlational and machine learning approaches. A cross-sectional study was conducted among 583 Saudi adolescents aged 13–18 years, using convenience sampling. Participants completed a battery of validated self-report instruments: the Suicide Crisis Inventory, the Childhood Trauma Questionnaire–Short Form, and the Okasha Suicidality Scale. Descriptive statistics, bivariate correlations, and variable importance analysis via machine learning, in particular a random forest classifier, were used to identify the strongest predictors of suicidal ideation. Emotional pain, entrapment, and panic dissociation were the most significant predictors of suicidal ideation. Childhood trauma variables—particularly emotional abuse, sexual abuse, and emotional neglect—also showed strong positive correlations with suicidal ideation. Adolescents from divorced families and those in high school reported significantly higher suicidal ideation scores. The random forest model confirmed emotional pain and entrapment as top predictors. Suicidal ideation among Saudi adolescents is strongly influenced by both acute emotional crisis symptoms and histories of childhood trauma. These findings highlight the need for early screening of suicidal crisis markers and trauma-informed mental health interventions in school and clinical settings. Culturally sensitive strategies that integrate emotional, developmental, and family-based factors are essential for effective suicide prevention among adolescents.

Authors

Institutions

Publication Details

Journal
BMC Psychology
Published
2025-12-10
DOI
https://doi.org/10.1186/s40359-025-03830-6
Primary Topic
Suicide and Self-Harm Studies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Silent struggles: a machine learning approach for predicting suicidal ideation based on crisis symptoms and childhood trauma in Saudi adolescents

Radeah Mohammed Hamididin, Mogeda El Sayed El Keshky
BMC Psychology
Suicide and Self-Harm Studies
article

Silent struggles: a machine learning approach for predicting suicidal ideation based on crisis symptoms and childhood trauma in Saudi adolescents

Radeah Mohammed Hamididin, Mogeda El Sayed El Keshky
article en

Abstract

Adolescent suicide is a significant public health concern, with rising rates globally and increasing psychological distress among youth. Despite its significance, limited research in Saudi Arabia has explored the combined impact of acute emotional crises and childhood trauma on suicidal ideation, particularly using machine learning approach. This study aimed to identify key psychological and trauma-related predictors of suicidal ideation among Saudi adolescents. It specifically examined the role of Suicidal Crisis Syndrome symptoms and childhood maltreatment experiences using both correlational and machine learning approaches. A cross-sectional study was conducted among 583 Saudi adolescents aged 13–18 years, using convenience sampling. Participants completed a battery of validated self-report instruments: the Suicide Crisis Inventory, the Childhood Trauma Questionnaire–Short Form, and the Okasha Suicidality Scale. Descriptive statistics, bivariate correlations, and variable importance analysis via machine learning, in particular a random forest classifier, were used to identify the strongest predictors of suicidal ideation. Emotional pain, entrapment, and panic dissociation were the most significant predictors of suicidal ideation. Childhood trauma variables—particularly emotional abuse, sexual abuse, and emotional neglect—also showed strong positive correlations with suicidal ideation. Adolescents from divorced families and those in high school reported significantly higher suicidal ideation scores. The random forest model confirmed emotional pain and entrapment as top predictors. Suicidal ideation among Saudi adolescents is strongly influenced by both acute emotional crisis symptoms and histories of childhood trauma. These findings highlight the need for early screening of suicidal crisis markers and trauma-informed mental health interventions in school and clinical settings. Culturally sensitive strategies that integrate emotional, developmental, and family-based factors are essential for effective suicide prevention among adolescents.

BMC PsychologyVol. 14(1)
King Abdulaziz University (SA), Assiut University (EG)
Openalex Percentile: Top 49%
Suicide and Self-Harm Studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.