Combined brain topological metrics with machine learning to distinguish essential tremor and tremor-dominant Parkinson’s disease

• Published in: Neurological sciences 2024-09, Vol.45 (9), p.4323-4334
• Main Authors: Xiao, Pan, Li, Qin, Gui, Honge, Xu, Bintao, Zhao, Xiaole, Wang, Hongyu, Tao, Li, Chen, Huiyue, Wang, Hansheng, Lv, Fajin, Luo, Tianyou, Cheng, Oumei, Luo, Jin, Man, Yun, Xiao, Zheng, Fang, Weidong
• Format: Article
• Language: English
• Subjects: Aged; Algorithms; Brain - diagnostic imaging; Cerebellum; Classification; Correlation analysis; Diagnosis, Differential; Essential Tremor - diagnosis; Essential Tremor - diagnostic imaging; Female; Humans; Learning algorithms; Machine Learning; Magnetic Resonance Imaging - methods; Male; Medicine; Medicine & Public Health; Middle Aged; Movement disorders; Neurodegenerative diseases; Neurology; Neuroradiology; Neurosurgery; Original Article; Parkinson Disease - diagnosis; Parkinson Disease - diagnostic imaging; Parkinson Disease - physiopathology; Parkinson's disease; Pathogenesis; Psychiatry; Sensorimotor system; Support Vector Machine; Tremor; Tremor (Muscular contraction)
• ISSN: 1590-1874; 1590-3478; 1590-3478
• DOI: 10.1007/s10072-024-07472-1

Background Essential tremor (ET) and Parkinson’s disease (PD) are the two most prevalent movement disorders, sharing several overlapping tremor clinical features. Although growing evidence pointed out that changes in similar brain network nodes are associated with these two diseases, the brain network topological properties are still not very clear. Objective The combination of graph theory analysis with machine learning (ML) algorithms provides a promising way to reveal the topological pathogenesis in ET and tremor-dominant PD (tPD). Methods Topological metrics were extracted from Resting-state functional images of 86 ET patients, 86 tPD patients, and 86 age- and sex-matched healthy controls (HCs). Three steps were conducted to feature dimensionality reduction and four frequently used classifiers were adopted to discriminate ET, tPD, and HCs. Results A support vector machine classifier achieved the best classification performance of four classifiers for discriminating ET, tPD, and HCs with 89.0% mean accuracy (mACC) and was used for binary classification. Particularly, the binary classification performances among ET vs. tPD, ET vs. HCs, and tPD vs. HCs were with 94.2% mACC, 86.0% mACC, and 86.3% mACC, respectively. The most power discriminative features were mainly located in the default, frontal-parietal, cingulo-opercular, sensorimotor, and cerebellum networks. Correlation analysis results showed that 2 topological features negatively and 1 positively correlated with clinical characteristics. Conclusions These results demonstrated that combining topological metrics with ML algorithms could not only achieve high classification accuracy for discrimination ET, tPD, and HCs but also help to reveal the potential brain topological network pathogenesis in ET and tPD.