| Objective To establish a diagnostic prediction model for non-suicidal self-injury (NSSI) in adolescents with depressive disorder, in order to provide ideas for early identification of NSSI in adolescents with depressive disorder. Methods The clinical data of 366 hospitalized patients with depression disorder in the Pediatric Department of Shenzhen Kangning Hospital from January 1, 2021 to December 31, 2021 were retrospectively collected. According to the Diagnostic and Statistical Manual of Mental Disorders, fifth edition (DSM-5) diagnostic criteria, the patients were divided into two groups: the group with NSSI (n=289) and the group without NSSI (n=77). 366 patients were randomly divided into training set and validation set in 7:3 ratio. The independent variables screened by Logistic regression (P<0.05) were used to establish a predictive model for NSSI in adolescents with depressive disorder. Finally, the area under receiver Operating characteristic (ROC) curve (AUC) was used to evaluate the discrimination between the training set and validation set models. Calibration curves were used to evaluate the calibration degree of the training set and verification set models. The Goodness of fit test (HL) was used to evaluate the accuracy of the calibration degree of the model.Decision curve analysis (DCA) was used to evaluate the clinical benefit of the prediction model. Results Finally, gender (β=1.734, OR=5.561, 95% CI: 2.678~11.964), grade (β=0.864, OR=2.737, 95% CI: 1.174~4.795), history of suicide attempts (β=0.932, OR=2.539, 95% CI: 1.253~5.144), only child (β=0.745, OR=2.106, 95% CI: 1.029~4.311), depression severity (β=0.056, OR=1.058, 95% CI: 1.025~1.092) and four independent risk factors related to NSSI behavior in adolescents with depressive disorder (P<0.05). ROC curve training set AUC was 0.808 (95% CI: 0.746~0.870). Validation set AUC was 0.722 (95% CI: 0.581~0.864). HL test evaluated the prediction results of calibration chart showed a good fit (P=0.561). Conclusion Gender, education level, suicide attempt history, only child, and depression severity are independent risk factors for NSSI behavior in adolescents with depressive disorder. The constructed diagnostic clinical prediction model for NSSI behavior in adolescents with depressive disorder has good sensitivity and specificity. |