Inflammatory responses, including glial cell activation and peripheral immune cell infiltration, are involved in the pathogenesis of Parkinson’s disease (PD). These inflammatory responses appear to be closely related to the release of extracellular vesicles, such as exosomes. However, the relationships among different forms of glial cell activation, synuclein dysregulation, mitochondrial dysfunction, and exosomes are complicated. This review discusses the multiple roles played by exosomes in PD-associated inflammation and concludes that exosomes can transport toxic α-synuclein oligomers to immature neurons and into the extracellular environment, inducing the oligomerization of α-synuclein in normal neurons. Misfolded α-synuclein causes microglia and astrocytes to activate and secrete exosomes. Glial cell-derived exosomes participate in communications between glial cells and neurons, triggering anti-stress and anti-inflammatory responses, in addition to axon growth. The production and release of mitochondrial vesicles and exosomes establish a new mechanism for linking mitochondrial dysfunction to systemic inflammation associated with PD. Given the relevance of exosomes as mediators of neuron-glia communication in neuroinflammation and neuropathogenesis, new targeted treatment strategies are currently being developed that use these types of extracellular vesicles as drug carriers. Exosome-mediated inflammation may be a promising target for intervention in PD patients.

This study aimed to identify potential markers that can predict Parkinson’s disease with mild cognitive impairment (PDMCI). We retrospectively collected general demographic data, clinically relevant scales, plasma samples, and neuroimaging data (T1-weighted magnetic resonance imaging (MRI) data as well as resting-state functional MRI [Rs-fMRI] data) from 173 individuals. Subsequently, based on the aforementioned multimodal indices, a support vector machine was employed to investigate the machine learning (ML) classification of PD patients with normal cognition (PDNC) and PDMCI. The performance of 29 classifiers was assessed based on various combinations of indicators. Results demonstrated that the optimal classifier in the validation set was composed by clinical + Rs-fMRI+ neurofilament light chain, exhibiting a mean Accuracy of 0.762, a mean area under curve of 0.840, a mean sensitivity of 0.745, along with a mean specificity of 0.783. The ML algorithm based on multimodal data demonstrated enhanced discriminative ability between PDNC and PDMCI patients.