Machine learning approach effectively discriminates between Parkinson’s disease and progressive supranuclear palsy: Multi-level indices of rs-fMRI

• Published in: Brain research bulletin Vol. 229; p. 111476
• Main Authors: Cheng, Weiling, Liang, Xiao, Zeng, Wei, Guo, Jiali, Yin, Zhibiao, Dai, Jiankun, Hong, Daojun, Zhou, Fuqing, Li, Fangjun, Fang, Xin
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.09.2025; Elsevier
• Subjects: Aged; Brain - diagnostic imaging; Brain - physiopathology; Female; Humans; Machine Learning; Magnetic Resonance Imaging - methods; Male; Middle Aged; Parkinson Disease - diagnosis; Parkinson Disease - diagnostic imaging; Parkinson Disease - physiopathology; Parkinson’s disease; Progressive supranuclear palsy; Prospective Studies; Rs-fMRI; Support Vector Machine; Supranuclear Palsy, Progressive - diagnosis; Supranuclear Palsy, Progressive - diagnostic imaging; Supranuclear Palsy, Progressive - physiopathology; Progressive supranuclear palsy; Parkinson’s disease; Rs-fMRI
• DOI: 10.1016/j.brainresbull.2025.111476
• ISSN: 0361-9230; 1873-2747

Parkinson’s disease (PD) and progressive supranuclear palsy (PSP) present similar clinical symptoms, but their treatment options and clinical prognosis differ significantly. Therefore, we aimed to discriminate between PD and PSP based on multi-level indices of resting-state functional magnetic resonance imaging (rs-fMRI) via the machine learning approach. A total of 58 PD and 52 PSP patients were prospectively enrolled in this study. Participants were randomly allocated to a training set and a validation set in a 7:3 ratio. Various rs-fMRI indices were extracted, followed by a comprehensive feature screening for each index. We constructed fifteen distinct combinations of indices and selected four machine learning algorithms for model development. Subsequently, different validation templates were employed to assess the classification results and investigate the relationship between the most significant features and clinical assessment scales. The classification performance of logistic regression (LR) and support vector machine (SVM) models, based on multiple index combinations, was significantly superior to that of other machine learning models and combinations when utilizing automatic anatomical labeling (AAL) templates. This has been verified across different templates. The utilization of multiple rs-fMRI indices significantly enhances the performance of machine learning models and can effectively achieve the automatic identification of PD and PSP at the individual level. •Machine learning with rs-fMRI indices effectively differentiates PD from PSP.•Multi-level rs-fMRI features enhance classification accuracy in individual diagnosis.•LR and SVM models outperform others, achieving AUC > 0.9 in validation.•Key discriminative features involve DMN, SMN, and cerebellum networks.