Development and validation of a machine learning–based risk prediction model for non-suicidal self-injury in adolescents - Takeaways - MDSpire

Development and validation of a machine learning–based risk prediction model for non-suicidal self-injury in adolescents

  • By

  • Yujun Zhao

  • Qian Wang

  • Wei Liu

  • May 13, 2026

  • 0 min

Share

  • 1

    A predictive model for non-suicidal self-injury (NSSI) in adolescents was developed using machine learning techniques.

  • 2

    The study included 588 adolescents, assessing various predictors like demographics, psychological status, and peer support.

  • 3

    The support vector machine (SVM) model outperformed others, achieving AUC values above 0.75 and F1 scores over 0.7.

  • 4

    Key predictors of NSSI identified were suicide-related ideation, school bullying, and depressive symptoms.

  • 5

    Findings aim to enhance early identification of adolescents at risk for NSSI and inform targeted intervention strategies.

Original Source(s)

Development and validation of a machine learning–based risk prediction model for non-suicidal self-injury in adolescents

  • by Yujun Zhao, Qian Wang, Wei Liu

  • May 13, 2026

Related Content

Top 10 States With Rising Demand for Physicians

These 10 states report physician shortages, projected physician supply gaps, or physician-to-population ratios below national benchmarks.

Auricular acupuncture for insomnia in female patients with non-metastatic breast cancer: study protocol for a multicenter, randomized, controlled clinical trial

Medical Oddities: Something Viral is Lurking in the Dust

Everyday things like yawns, tea, dust, and kimchi suddenly look medically important.