MuscNet, a Weighted Voting Model of Multi-Source Connectivity Networks to Predict Mild Cognitive Impairment Using Resting-State Functional MRI

Abstract

The neurological disorder mild cognitive impairment (MCI) demonstrates minor impacts on the patient's daily activities and may be ignored as the status of normal aging. But some of the MCI patients may further develop into severe statuses like Alzheimer's disease (AD). The brain functional connectivity network (BFCN) was usually constructed from the resting-state functional magnetic resonance imaging (rs-fMRI) data. This technology has been widely used to detect the neurodegenerative dementia and to reveal the intrinsic mechanism of neural activities. The BFCN edge was usually determined by the pairwise correlation between the brain regions. This study proposed a weighted voting model of multi-source connectivity networks (MuscNet) by integrating multiple BFCNs of different correlation coefficients. Our model was further improved by removing redundant features. The experimental data demonstrated that different BFCNs contributed complementary information to each other and MuscNet outperformed the existing models on detecting MCI patients. The previous study suggested the existence of multiple solutions with similarly good performance for a machine learning problem. The proposed model MuscNet utilized a weighted voting strategy to slightly outperform the existing studies, suggesting an effective way to fuse multiple base models. The reason may need further theoretical investigations about why different base models contribute to each other for the MCI prediction.

Keywords: Alzheimer’s disease; Mild cognitive impairment; MuscNet; brain functional connectivity network; multi-source connectivity network; resting-state functional MRI; weighted voting model.

FIGURE 1.

Multi-source dynamic BFCN structure. For each correlation coefficient, we can follow the above structure to construct the corresponding BFCN and to further integrate the pairwise estimators.

FIGURE 2.

Classification performance of BFCNs based on different parameters. (a) The static BFNCs using different correlation coefficient metrics. (b) The dynamic BFCNs using different window_size and window_step for different correlation coefficient metrics. The horizontal axis was in the format of window_{size_}window_step and the vertical axis was the classification accuracy. Features with Ttest Pvalue < 0.05 was chosen to calculate the classification performances for both sub-figures.

FIGURE 3.

MuscNet classification accuracies based on dynamic BFCNs of one CC or a CC duet. The parameter “110_1” in the top left corner represented the two parameters window_size = 110 and window_step = 1. As correlation heatmap, this comparison heatmap was also diagonally symmetrical. The diagonal represented a dynamic BFCN based on single correlation coefficient (CC), and the grids represented the integrated dynamic BFCNs of a CC duet. The heatmap background color was lighter if the value was larger. Features with Ttest Pvalue < 0.05 were chosen to calculate the classification performances.

FIGURE 4.

Classification accuracy of MuscNet with different feature selection methods (p-value = 0.05). The notation “PCC&MIC” represented the MuscNet model integrating the PCC- and MIC-based dynamic BFCNs. The horizontal axis was the parameter duet window_{size_}window_step. The vertical axis was the classification accuracy calculated using the features with the filter Pvalue < 0.05, where the filter algorithm could be (a) Wtest, (b) Ttest and (c) KStest.

FIGURE 5.

Best performance comparison among Wtest, Ttest and KStest (Pvalue < 0.05). The horizontal axis was the three classification performance metrics, Acc, Sn and Sp. The horizontal axis was the three classification performance metrics of different filter algorithms, respectively. The vertical axis was the corresponding values of each metric.

FIGURE 6.

The classification accuracy heatmap. This heatmap showed the comparison between dynamic BFCNs based on one CC and integrated CC duets. Features with the KStest (Pvalue < 0.2) were selected for training the model. And the two parameters window_size = 110, window_step = 10 were set for the sliding windows. The heatmap background color was lighter if the value was larger.

FIGURE 7.

Classification accuracies of MuscNet models with different Pvalue thresholds. The horizontal axis was the filter Pvalue thresholds and the vertical axis was the classification accuracies. The evaluation was carried out for (a) Wtest, (b) Ttest and (c) KStest.

FIGURE 8.

Comparison between top-10 features most frequently selected by MIC and KCC models. Column in red represents the top-10 features selected by one model, column in blue represents this feature also belongs to the top-10 features selected by the other model, and column in green represents this feature doesn’t belong to the top-10 features selected by the other model. The vertical axis of each figure was the selected frequency of one feature.