To develop and validate a clinically applicable nomogram for estimating the probability of non-suicidal self-injury (NSSI) in adolescents with depression.
Approach:
Data Collection: Data were obtained from a nationwide multicenter cohort of 2,343 adolescents with depression from 14 hospitals in China.
Variable Selection: Variables associated with NSSI were selected using Random Forest integrated with SHAP values and logistic regression.
Model Assessment: Model performance was evaluated using AUC, the Hosmer–Lemeshow test, calibration curves, and decision curve analysis (DCA).
Key Findings:
Eight variables were identified as significant predictors of NSSI risk: depression score, sleep medication use, difficulty identifying feelings, age, perceived family support, female gender, hallucination, and externally oriented thinking.
The nomogram demonstrated good performance with AUC values of 0.754 (95% CI: 0.726-0.781) in the training cohort and 0.748 (95% CI: 0.707-0.789) in the validation cohort.
Interpretation:
The nomogram integrates eight clinical and psychosocial variables to estimate NSSI risk among adolescents with depression.
Limitations:
The study is limited to a specific population in China, which may affect generalizability.
The reliance on self-reported data may introduce bias.
Conclusion:
A nomogram was developed and validated to estimate NSSI risk, which may assist clinicians in assessing and managing adolescents with depression.
