关键词: Wilson病, 中脑, 列线图, 预测模型

Abstract: Objective To investigate the influencing factors of brain lesions in Wilson's disease(WD) and to construct a predictive model for brain lesions in WD to facilitate early identification and intervention. Methods A retrospective analysis was conducted on the clinical and laboratory data of 198 patients with neurological WD who were treated at the Neurology Institute affiliated with Anhui University of Chinese Medicine from April 2019 to April 2023.All patients underwent cranial magnetic resonance imaging(MRI) and exhibited varying degrees of MRI changes in the brain.LASSO regression and multivariate Logistic regression analysis were used to identify factors influencing the occurrence of brain pathology and to construct a nomogram prediction model.The effectiveness of the predictive model was verified using the receiver operating characteristic(ROC) curve, calibration curve, and decision curve analysis(DCA).The model was internally validated using 1000 bootstrap resamples and 10-fold cross-validation. Results The age of WD patients, and MRI findings of pontine and thalamic lesions were identified as independent risk factors for brain pathology.The nomogram demonstrated good discrimination, calibration, and clinical utility.After 1000 bootstrap resamples and 10-fold cross-validation, the model maintained robust predictive performance. Conclusion The nomogram prediction model developed in this study has good predictive and discriminative capabilities, which can assist clinicians in predicting the occurrence of brainstem lesions in WD patients and has potential clinical translational application value.

Key words: Wilson's Disease, Mesencephalon, Nomogram, Predictive Model