Parkinson’s disease (PD) is a neurological movement illness that is prevalent, progressive, and currently incurable. The diagnosis of Parkinson’s disease is difficult, especially in the differential diagnosis of parkinsonism and in the early discovery of the disease. Machine learning techniques have been progressively applied to the diagnosis of PD, with promising findings. Machine learning techniques have been increasingly applied to the diagnosis of PD, with promising results. On magnetic resonance imaging (MRI), resting-state functional MRI (rs-fMRI), diffusion tensor imaging (DTI), and single photon emission computed tomography (SPECT) images, machine learning-based imaging applications have made it possible to automatically differentiate parkinsonism and detect PD at an early stage. In diagnosing PD-associated dopaminergic degeneration, machine learning-based SPECT image analysis apps outperformed conventional semi-quantitative analysis, performed as well as experts, and increased radiologists’ PD diagnostic accuracy. Multimodal data (such as multimodal imaging and clinical data) may help with early identification of Parkinson’s disease. Further refining and comprehensive validation of machine learning-based computer-aided diagnostic apps are required to incorporate them into clinical systems and make them accurate and reliable for the diagnosis of Parkinson’s disease. Machine learning techniques are expected to improve differential diagnosis of parkinsonism and early PD detection, potentially lowering PD diagnosis error rates, allowing early neuroprotective treatment to slow neurodegeneration progression and prevent clinical symptoms from arising in patients with early-stage PD, and allowing proper treatment to effectively relieve patients from their symptoms.
Author (S) Details
Department of Neurology, School of Medicine, Washington University in St. Louis, St. Louis, MO 63110, USA.
View Book :- https://stm.bookpi.org/NFMMR-V9/article/view/3453