Machine Learning Uncovers Key Factors in Adolescent Self-Injury | Study Highlights the Role of Situational Anxiety and Emotional States

In this episode of SciBud, join Rowan as we explore a groundbreaking study that employs advanced machine learning techniques to better understand non-suicidal self-injury (NSSI) among adolescents. Drawing on data from nearly 3,000 high school students in eastern China, researchers utilized six machine learning algorithms, discovering that the CatBoost model excelled at identifying key risk and protective factors associated with NSSI behaviors. They identified 23 crucial features organized into significant areas like anxiety, depression, and bullying, offering insights that align with existing psychological theories. While the study advances our understanding of adolescent self-harm, it also raises important questions about data transparency and accessibility. Tune in to learn how the intersection of AI and psychology could lead to innovative strategies for prevention and support in this critical area of mental health! Link to episode page with article citation: www.scibud.media/podcast/season/2025/episode/152