Development and validation of a nomogram to predict suicidal behavior in female patients with mood disorder

Introduction This study aims to explore the risk factors associated with suicidal behavior and establish predictive models in female patients mood disorders, specifically using a nomogram of least absolute shrinkage selection operator (LASSO) regression. Methods A cross-sectional survey was conducted among 396 individuals diagnosed disorders (F30-F39) according International Classification Diseases Related Health Problems 10th Revision (ICD-10). The utilized Chi-Squared Test, t -test, Wilcoxon Rank-Sum Test assess differences demographic information clinical characteristics between two groups. Logistic LASSO Regression Analyses were identify behavior. constructed develop prediction model. accuracy model evaluated Receiver Operating Characteristic (ROC) curve. Result regression analysis showed that psychotic symptoms at first-episode ( β = 0.27), social dysfunction 1.82), somatic disease 1.03) increased Conversely, BMI −0.03), age onset −0.02), polarity −1.21), number hospitalizations −0.18) decreased area under ROC curve (AUC) predicting SB 0.778 (95%CI: 0.730–0.827, p < 0.001). Conclusion based on can predict Chinese disorders.