The prediction and impact of self-criticism on non-suicidal self-injury in adolescents

A study based on machine learning

Bibliographic Data

ID21282243
AuthorsXiaoning Huo (Gansu University of Traditional Chinese Medicine), Xuan Liu (0000-0001-5599-2607, First Hospital of Lanzhou University), Yiying Wang (0009-0009-6313-0340, First Hospital of Lanzhou University), Linhan Yang (First Hospital of Lanzhou University), Yuting Huang (0000-0002-1968-6247, First Hospital of Lanzhou University), Yannan Wang (0000-0001-7248-4954, First Hospital of Lanzhou University), Hongming Zheng (0000-0002-2207-1163, Gansu University of Traditional Chinese Medicine), Haozhong Zheng, Xuan Zhao (0000-0002-0893-8920), Xyn Zhao (Gansu Provincial Hospital, corresponding author)
Year2026
Volume265
Pages106655
Publication date2026-05-01
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueActa Psychologica (JOURNAL)
Journal identifiersISSN: 0001-6918 • E-ISSN: 1873-6297
PublisherElsevier BV (PUBLISHER)
DOI10.1016/j.actpsy.2026.106655
PMID41930525
OpenAlexW7147597421
LanguageEN
References cited48

This study uniquely combines machine learning with structural equation modeling to investigate how self-criticism affects non-suicidal self-injury (NSSI) behaviors in adolescents. Using a Support Vector Machine (SVM) for binary classification (distinguishing NSSI presence/absence) and XGBRegressor for regression (predicting NSSI severity), with self-criticism, emotional regulation difficulties, and public self-consciousness as key predictors, the study accurately classified and forecasted NSSI behaviors. The K-fold cross-validation confirmed the robustness of these predictors. The SVM classifier achieved an accuracy of 85.3% (AUC = 0.89, 95% CI [0.87, 0.91]), while the regression model explained 50.9% of variance ( R 2 = 0.509). Structural equation modeling revealed that self-criticism directly influences NSSI ( β = 0.32, p < .001) and indirectly affects it through both emotional regulation difficulties ( β = 0.18, 95% CI [0.14, 0.22]) and public self-consciousness ( β = −0.11, 95% CI [−0.15, −0.07]), with a significant serial mediation pathway (self-criticism → emotional regulation difficulties → public self-consciousness → NSSI). These findings demonstrate that self-criticism, difficulty in emotional regulation, and public self-consciousness can predict NSSI risk/severity and differentiate between groups with and without NSSI behaviors in our sample. Additionally, adolescents' public self-consciousness can directly and negatively predict non-suicidal self-injurious behaviour, revealing its protective role in the pattern of NSSI behaviour and providing support for the assumptions in the benefit and hindrance models of NSSI

Binary classification · Classifier (UML) · Mediation · Regression analysis · Robustness (evolution) · Structural equation modeling · Support vector machine · Variance (accounting) · Digital Mental Health Interventions · Personality Disorders and Psychopathology · Suicide and Self-Harm Studies

Tools

Open DOIOpen Access