11 September 2023 in International Journal of Biological Macromolecules
25 September 2023 in Molecular Cell
8 May 2023 in Journal of Translational Medicine
Background: Cognitive dysfunction is the most common non-motor symptom in Parkinson’s disease (PD), and timely detection of a slight cognitive decline is crucial for early treatment and prevention of dementia. This study aimed to build a machine learning model based on intra- and/or intervoxel metrics extracted from diffusion tensor imaging (DTI) to automatically classify PD patients without dementia into mild cognitive impairment (PD-MCI) and normal cognition (PD-NC) groups. Methods: We enrolled PD patients without dementia (52 PD-NC and 68 PD-MCI subtypes) who were assigned to the training and test datasets in an 8:2 ratio. Four intravoxel metrics, including fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD), and two novel intervoxel metrics, local diffusion homogeneity (LDH) using Spearman’s rank correlation coefficient (LDHs) and Kendall’s coefficient concordance (LDHk), were extracted from the DTI data. Decision tree, random forest, and eXtreme gradient boosting (XGBoost) models based on individual and combined indices were built for classification, and model performance was assessed and compared via the area under the receiver operating characteristic curve (AUC). Finally, feature importance was evaluated using SHapley Additive exPlanation (SHAP) values. Results: The XGBoost model based on a combination of the intra- and intervoxel indices achieved the best classification performance, with an accuracy of 91.67%, sensitivity of 92.86%, and AUC of 0.94 in the test dataset. SHAP analysis showed that the LDH of the brainstem and MD of the right cingulum (hippocampus) were important features. Conclusions: More comprehensive information on white matter changes can be obtained by combining intra- and intervoxel DTI indices, improving classification accuracy. Furthermore, machine learning methods based on DTI indices can be used as alternatives for the automatic identification of PD-MCI at the individual level.
20 January 2023 in Human Brain Mapping
Differentiating the parkinsonian variant of multiple system atrophy (MSA‐P) from idiopathic Parkinson's disease (IPD) is challenging, especially in the early stages. This study aimed to investigate differences and similarities in the brain functional connectomes of IPD and MSA‐P patients and use machine learning methods to explore the diagnostic utility of these features. Resting‐state fMRI data were acquired from 88 healthy controls, 76 MSA‐P patients, and 53 IPD patients using a 3.0 T scanner. The whole‐brain functional connectome was constructed by thresholding the Pearson correlation matrices of 116 regions, and topological properties were evaluated through graph theory approaches. Connectome measurements were used as features in machine learning models (random forest [RF]/logistic regression [LR]/support vector machine) to distinguish IPD and MSA‐P patients. Regarding graph metrics, early IPD and MSA‐P patients shared network topological properties. Both patient groups showed functional connectivity disruptions within the cerebellum‐basal ganglia‐cortical network, but these disconnections were mainly in the cortico‐thalamo‐cerebellar circuits in MSA‐P patients and the basal ganglia‐thalamo‐cortical circuits in IPD patients. Among the connectome parameters, t tests combined with the RF method identified 15 features, from which the LR classifier achieved the best diagnostic performance on the validation set (accuracy = 92.31%, sensitivity = 90.91%, specificity = 93.33%, area under the receiver operating characteristic curve = 0.89). MSA‐P and IPD patients show similar whole‐brain network topological alterations. MSA‐P primarily affects cerebellar nodes, and IPD primarily affects basal ganglia nodes; both conditions disrupt the cerebellum‐basal ganglia‐cortical network. Moreover, functional connectome parameters showed outstanding value in the differential diagnosis of early MSA‐P and IPD.
3 October 2024 in Construction and Building Materials