Related Experiment Video
Updated: Jan 9, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Construction of a Nomogram Prediction Model for Individualized Prediction of the Risk of Non Suicidal Self Injury in
Qingyan Zhao1, Lingbin Zeng2, Shaolun Hu3
1School of Nursing of Shaoyang University, Shaoyang, Hunan, 422000, People's Republic of China.
Objective:
To develop a nomogram model for individualized prediction of non-suicidal self-injury (NSSI) risk in adolescent depression patients.
Methods:
Clinical data from 270 adolescent depression patients (August 2022-January 2025) were randomly divided into modeling and validation groups. The modeling group was split into NSSI and non-NSSI subgroups based on NSSI occurrence. Logistic regression identified risk factors. R software was used to construct the nomogram, while ROC and DCA evaluated its discrimination and clinical utility.
Results:
A total of 189 patients from our hospital were retrospectively selected, among whom 72 patients (38.10%) were identified as having engaged in NSSI behavior within the past year. Disease duration, depression level, childhood abuse, family dysfunction, school bullying, sleep disorder, and Barratt Impulsiveness were significant risk factors (P<0.05). AUCs were 0.899 (modeling) and 0.954 (validation). H-L tests showed good fit: χ²=7.243 (P=0.721) and χ²=7.010 (P=0.711). The DCA curve indicated high clinical value when probability ranged from 0.05 to 0.97.
Conclusion:
Disease course, severity of depression, childhood abuse, dysfunctional family environment during childhood, experiences of school bullying, sleep disorders, and Barratt Impulsiveness Scale scores were identified as influencing factors for NSSI in adolescents with depression. Based on these factors, a nomogram model was constructed, which showed good predictive consistency and high clinical applicability. This model can assist clinicians in identifying high-risk individuals for early prevention. Although the model may help guide interventions to reduce the incidence of NSSI, further validation through rigorously designed implementation studies is still required.
