Construction and Efficacy Validation of Nomogram Model for Risk Prediction of Depression in Patients with Ulcerative Colitis

WU Hongyan; XU Xiaojing; WANG Liangliang

doi:10.3969/j.issn.1004-437X.2025.15.014

Abstract：Objective To construct a nomogram model for risk prediction of depression in patients with ulcerative colitis,and verify the effectiveness of this model.Methods A total of 291 patients with ulcerative colitis admitted to Staff Hospital of Henan Province from February 2020 to May 2023 were selected as the study subjects,and the patients were divided into modeling set(194 cases)and validation set(97 cases)according to the ratio of 2∶1.Ulcerative colitis patients were divided into concurrent and non-concurrent groups based on whether they had concurrent depression.The risk factors for depression in patients with ulcerative colitis were screened through logistic regression analysis,and the risk prediction nomogram model was constructed,and the feasibility of the model was evaluated in the validation set.Results There was no statistically significant difference in the comparison of clinical data between the modeling set and the validation set(P＞0.05).The logistic regression analysis results of the modeling set showed that education level at or below junior high school,poor economic status,disease course＞5 years,poor treatment compliance and disease activity period were risk factors for depression in patients with ulcerative colitis(P＜0.05).Based on the above 5 risk factors,the nomogram model had been established for predicting the risk of depression in patients with ulcerative colitis.The calibration curve showed good consistency between the calibration curve and the ideal curve of the risk prediction nomogram model,and the consistency index of the modeling set and validation set were 0.822 and 0.810,respectively.The receiver operating characteristic showed that the area under the curve for predicting the risk of depression in the modeling sets and validation set of the model were 0.827 and 0.815,respectively.The decision curve showed that patients with ulcerative colitis had higher net benefit in predicting depression based on this model.Conclusion The predictive efficacy and applicability of the risk prediction model for depression in patients with ulcerative colitis are good based on the educational level,economic status,disease course,treatment compliance and disease activity period,and it can be used to screen for the risk of depression in such patients.