Fig. 1: Framework for proteomics and metabolomics analyses, model construction, model evaluation, and model validation. | npj Parkinson's Disease

Fig. 1: Framework for proteomics and metabolomics analyses, model construction, model evaluation, and model validation.

From: Machine learning model base on metabolomics and proteomics to predict cognitive impairment in Parkinson’s disease

Fig. 1

Proteomics and metabolomics analyses were performed on a discover cohort. A machine learning model was used to identify candidate protein and metabolite biomarkers of Parkinson’s disease with cognitive impairment (PDCI), which were validated in an independent cohort. The predictive ability of the proteins in combination with neuroimaging was also analyzed. The figure were performed with Adobe Illustrator 2019. C, control healthy subjects; DC degree centrality, fMRI functional Magnetic resonance imaging, GMV Gray matter volume, PD Parkinson’s disease, PDD Parkinson’s disease patients with dementia, PDMCI Parkinson’s disease patients with mild cognitive impairment, PDNC Parkinson’s disease patients with normal cognition.

Back to article page