Skip to main content
CSWE Annual Conference 2025 Main banner

E-Poster

Student Presentations

Machine Learning Analysis of Sex Differences in Adolescent Suicide Risk

This study uses machine learning (XGBoost) and Ecological Systems Theory to analyze sex differences in adolescent suicide risk. Using 2021 YRBS data, it assesses digital and physical influences. Cyberbullying impacted females more, while physical activity was a stronger protective factor for males. Findings highlight the need for sex-specific prevention strategies.

Learning Objectives:

At the end of this session, attendees should be able to:
  1. Upon completion, the participant will be able to describe sex differences in adolescent suicide risk and explain the impact of digital (e.g., cyberbullying, screen time) and physical (e.g., physical activity) factors.
  2. Upon completion, the participant will be able to explain how machine learning (XGBoost) is used to analyze suicide risk factors and interpret key findings.
  3. Upon completion, the participant will be able to discuss the implications of digital and physical factors for suicide prevention and consider potential intervention strategies.