Construction and validation of a risk prediction model for foot muscle tone disorders in patients with Parkinson's disease
Sun Pingge
Yin Xiran
Fang Hua
Li Kunbin
Abstract：Objective To explore the influencing factors of foot muscle tone disorders in patients with Parkinson's disease(PD)and to construct and validate a risk prediction model.Methods Clinical data of 124 PD patients were analyzed retrospectively,who were divided into the occurrence group and the non-occurrence group based on the presence or absence of foot muscle tone disorders.Multivariate logistic regression analysis was used to identify the influencing factors of foot muscle tone disorder in PD patients,and a nomogram risk prediction model for foot muscle tone disorder in PD patients was developed.The discrimination and calibration of the nomogram model were evaluated using the receiver operating characteristic(ROC)curve and calibration curve.Results There were 23 patients(18.55%)in the occurrence group and 101 patients(81.45%)in the non-occurrence group.Statistically significant differences were observed between the two groups in terms of the mini-mental state examination(MMSE)score,activities of daily living(ADL)score,C-reactive protein(CRP)level,interleukin-6(IL-6)level,unified Parkinson's Disease rating scale(UPDRS)Ⅰ and Ⅲ scores,PD disease duration,age of PD onset,gender,and PD stage(all P<0.05).Multivariate logistic regression analysis revealed that female gender,disease duration≥5 years,age of onset<60 years,advanced PD stage,high UPDRS Ⅰ score,and elevated IL-6 level were independent risk factors for foot dystonia in PD patients(all P<0.05).Internal validation showed that the C-index of the nomogram model for predicting foot muscle tone disorders in PD patients was 0.810.The ROC curve of the nomogram indicated that the area under the curve(AUC)for predicting foot muscle tone disorders in PD patients was 0.919(95%CI:0.806～0.977),with a sensitivity of 89.47%and a specificity of 87.10%,demonstrating good predictive performance.The calibration curve of the nomogram model for predicting foot muscle tone disorders in PD patients was close to the ideal curve,indicating high accuracy of the prediction results.Conclusions The nomogram model constructed based on gender,disease duration,age of onset,PD stage,UPDRS Ⅰ score,and serum inflammatory factor levels can effectively predict the risk of foot muscle tone disorders in PD patients,demonstrating good clinical application value and providing a basis for early clinical intervention.
Keywords：Parkinson diseasedystonic disordersfootnomogramsrisk prediction model
Publication Date：2025-07-20
Online Publishing Date：2025-08-21(First online date of this platform, not the publication date of the document)
Pages：5( 387-391 )