Influencing Factors, Construction and Verification of a Nomogram Model for Adolescent Depression With Nonsuicidal Self-Injury Behaviour.
Adolescent depression with nonsuicidal self-injury (NSSI) is a serious public health issue. NSSI involves intentional self-harm without suicidal intent and is common amongst depressed teens, leading to considerable psychological and physical risks. Early detection and intervention are essential to reduce these risks. To explore the influencing factors of adolescent depression with NSSI behaviour and construct a nomogram prediction model and verify its clinical application value.
From January 2023 to April 2025, 136 cases of adolescent depression admitted to our hospital were selected. Patients were randomly divided into training (n = 95) and verification (n = 41) sets in a 7:3 ratio. Multivariate logistic regression was used to analyse the risk factors of NSSI behaviour in the training set, and a nomogram prediction model was constructed. Receiver operating characteristic (ROC) and calibration curves were drawn to evaluate the prediction efficiency of the nomogram model, and verification was conducted on the basis of the verification set. Decision curve analysis was applied to assess the clinical application value of the nomogram model for the prediction of NSSI behaviour.
The training and verification sets included 38 (40.00%) and 15 (36.59%) of cases of NSSI behaviour, respectively. No statistically significant differences in the incidence and clinical characteristics of NSSI behaviour were found between the training and verification sets (p > 0.05). Multivariate logistic regression analysis on the training set indicated that tense parental relationship, long depression duration, co-occurring physical diseases, high depression severity, high anxiety levels, childhood trauma, Electroencephalogram (EEG) frontal α power, functional Magnetic Resonance Imaging (fMRI) dorsolateral prefrontal cortex activation and negative life events were factors associated with NSSI behaviour (p < 0.05). The nomogram model showed good calibration and fit between prediction and reality on the training and verification sets with C-index values of 0.936 and 0.923, respectively. average absolute errors between predicted and actual values of 0.092 and 0.105, respectively. and Hosmer-Lemeshow test p values of 0.452 and 0.523, respectively. ROC curves indicated that the areas under the curve of the nomogram model for predicting the NSSI behaviour of patients with adolescent depression in the training and verification sets were 0.941 (95% CI: 0.887-0.995) and 0.928 (95% CI: 0.834-1.000), respectively, with the sensitivity of 0.929 and 0.846, respectively, and specificity of 1.000 and 0.667, respectively.
The nomogram prediction model based on risk factors for depression with NSSI behaviour is beneficial for the early prediction of such behaviour in adolescents with depression, guiding appropriate clinical decisions and minimising the risk of NSSI behaviour, thereby safeguarding adolescent mental health.
From January 2023 to April 2025, 136 cases of adolescent depression admitted to our hospital were selected. Patients were randomly divided into training (n = 95) and verification (n = 41) sets in a 7:3 ratio. Multivariate logistic regression was used to analyse the risk factors of NSSI behaviour in the training set, and a nomogram prediction model was constructed. Receiver operating characteristic (ROC) and calibration curves were drawn to evaluate the prediction efficiency of the nomogram model, and verification was conducted on the basis of the verification set. Decision curve analysis was applied to assess the clinical application value of the nomogram model for the prediction of NSSI behaviour.
The training and verification sets included 38 (40.00%) and 15 (36.59%) of cases of NSSI behaviour, respectively. No statistically significant differences in the incidence and clinical characteristics of NSSI behaviour were found between the training and verification sets (p > 0.05). Multivariate logistic regression analysis on the training set indicated that tense parental relationship, long depression duration, co-occurring physical diseases, high depression severity, high anxiety levels, childhood trauma, Electroencephalogram (EEG) frontal α power, functional Magnetic Resonance Imaging (fMRI) dorsolateral prefrontal cortex activation and negative life events were factors associated with NSSI behaviour (p < 0.05). The nomogram model showed good calibration and fit between prediction and reality on the training and verification sets with C-index values of 0.936 and 0.923, respectively. average absolute errors between predicted and actual values of 0.092 and 0.105, respectively. and Hosmer-Lemeshow test p values of 0.452 and 0.523, respectively. ROC curves indicated that the areas under the curve of the nomogram model for predicting the NSSI behaviour of patients with adolescent depression in the training and verification sets were 0.941 (95% CI: 0.887-0.995) and 0.928 (95% CI: 0.834-1.000), respectively, with the sensitivity of 0.929 and 0.846, respectively, and specificity of 1.000 and 0.667, respectively.
The nomogram prediction model based on risk factors for depression with NSSI behaviour is beneficial for the early prediction of such behaviour in adolescents with depression, guiding appropriate clinical decisions and minimising the risk of NSSI behaviour, thereby safeguarding adolescent mental health.