Individualized diagnosis of Parkinson’s disease based on multivariate magnetic resonance imaging radiomics and clinical indexes

Objective To explore MRI-based radiomics models, integrating clinical characteristics, for differential diagnosis of Parkinson’s disease (PD) to evaluate their diagnostic performance. Methods A total of 256 participants [153 PD, 103 healthy controls (HCs)] from the First Affiliated Hospital of Wenzhou Medical Hospital, were enrolled as the training set, and 120 subjects (74 PD, 46 HCs) from the PPMI dataset served as the test set. Radiomics features were extracted from structural MRI (T1WI and T2-FLair). Support Vector Machine (SVM) classifiers were developed using MRI radiomics data from both monomodal and multimodal radiomics models. The clinical-radiomics model was constructed by integrating clinical variables, including UPDRS, Hoehn-Yahr stage, age, sex, and MMSE scores. Receiver operating characteristic (ROC) curves were generated to evaluate the performance of the models. Decision curve analysis (DCA) was performed to access the clinical usefulness of the models. Results In the training set, the T2-FLair and T1WI radiomics model achieved an AUC of 0.896 (95% CI, 0.812–0.900) and 0.899 (95% CI, 0.818–0.908), respectively. The double-sequence radiomics model demonstrated superior diagnostic performance, with an AUC of 0.965 (95% CI, 0.885–0.978) in the training set and an AUC of 0.852 (95% CI, 0.748–0.910) in the test set. The integrated clinical-radiomics model showed enhanced diagnostic accuracy, with AUC = 0.983 (95% CI, 0.897–0.996) in the training set and AUC = 0.837 (95% CI, 0.786–0.902) in the test set. Rad-scores derived from the radiomics model were significantly correlated with diagnostic outcomes (P < 0.001). DCA confirmed the substantial clinical usefulness of the clinical-radiomics integrated model. Conclusion The integrated clinical-radiomics model offered superior diagnostic performance compared to models based relying solely on imaging or clinical data, underscoring its potential as a non-invasive and effective tool in routine clinical practice for the early diagnosis of PD.