.png){kind=icon}
.png){kind=icon}
Return
Predicting Adolescent Executive Function in China: Interpersonal Distress and Childhood Neglect as the Largest Relative Contributors in a Machine Learning Study
.png){kind=icon}
PRE
AI
X
T
T
Z
X
X
DOI：10.1007/s10896-026-01141-x.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Executive function (EF) undergoes rapid maturation during adolescence and is highly sensitive to early-life adversity and ongoing psychosocial stressors. While adverse childhood experiences (ACEs) have been linked to EF, the specific contribution of childhood neglect and interpersonal factors remains unclear. The study investigated the factors associated with adolescent executive function, as well as the predictive effect of childhood neglect experience and interpersonal factors on adolescent EF by using a machine learning algorithm. Using cluster random sampling, 761 s-grade high school students completed an online survey, including the Executive Function Self-rating Scale, the Childhood Psychological Abuse and Neglect Scale, the Interpersonal Reaction Index Scale, and the Interpersonal Relationship Integrative Diagnostic Scale. The sample included 761 adolescents of age 16.67 ± 0.63 years and a mean EF score of 32.72 ± 8.06. A predictive model for adolescent executive function was established by five machine learning algorithms, with Ridge regression demonstrating the best performance (R² =0.380, MAE = 5.037, MSE = 40.059), outperforming others. Standardized coefficients from the ridge model indicated that interpersonal distress (β = 3.896) showed the largest relative contribution, followed by childhood neglect (β = 1.760), empathy (β = 0.920), and gender (β = 0.508). Within the examined predictor set, interpersonal distress and childhood neglect showed the largest relative contributions to adolescent EF in the final model, followed by empathy and gender. These findings underscore the importance of proximal psychosocial experiences in understanding individual differences in EF during adolescence.
Keywords:
Executive Function
Childhood Neglect
Interpersonal Distress
Adolescents
Machine Learning
Journal
IF:
2.2
Papers:
373
Citations:
4.4K
Organization
Cited Papers