Clinical Scorecard: Development of a Machine Learning Nomogram to Assess Non-Suicidal Self-Injury Risk in Depressed Adolescents: A Multicenter Analysis

At a Glance

Key Highlights

• Nomogram developed to estimate NSSI risk in adolescents with depression.
• Eight key variables identified: depression score, sleep medication use, difficulty identifying feelings, age, perceived family support, female gender, hallucination, and externally oriented thinking.
• Model performance assessed with AUC values of 0.754 and 0.748 in training and validation cohorts, respectively.
• Integration of machine learning enhances risk assessment accuracy.
• NSSI is a strong predictor of subsequent suicide-related behaviors.

Guideline-Based Recommendations

Diagnosis

• Assess for NSSI in adolescents presenting with depression.

Management

• Utilize the developed nomogram for individualized risk assessment.

Monitoring & Follow-up

• Regularly evaluate psychosocial factors and risk indicators.

Risks

• Monitor for long-term suicide risk associated with NSSI.

Patient & Prescribing Data

Adolescents with depression

Psychosocial assessment and individualized clinical management are critical.

Clinical Best Practices

• Incorporate machine learning tools in clinical settings for risk assessment.
• Utilize a biopsychosocial framework for comprehensive evaluation of NSSI risk.

Related Resources & Content

• Development of a Machine Learning Nomogram to Assess Non-Suicidal Self-Injury Risk in Depressed Adolescents