Abstract
Studies on developing effective neuromarkers based on magnetoencephalographic (MEG) signals have been drawing increasing attention in the neuroscience community. This study explores the idea of using source-based magnitude-squared spectral coherence as a spatial indicator for effective regions of interest (ROIs) localization, subsequently discriminating the participants with mild cognitive impairment (MCI) from a group of age-matched healthy control (HC) elderly participants. We found that the cortical regions could be divided into two distinctive groups based on their coherence indices. Compared to HC, some ROIs showed increased connectivity (hyper-connected ROIs) for MCI participants, whereas the remaining ROIs demonstrated reduced connectivity (hypo-connected ROIs). Based on these findings, a series of wavelet-based source-level neuromarkers for MCI detection are proposed and explored, with respect to the two distinctive ROI groups. It was found that the neuromarkers extracted from the hyper-connected ROIs performed significantly better for MCI detection than those from the hypo-connected ROIs. The neuromarkers were classified using support vector machine (SVM) and k-NN classifiers and evaluated through Monte Carlo cross-validation. An average recognition rate of 93.83% was obtained using source-reconstructed signals from the hyper-connected ROI group. To better conform to clinical practice settings, a leave-one-out cross-validation (LOOCV) approach was also employed to ensure that the data for testing was from a participant that the classifier has never seen. Using LOOCV, we found the best average classification accuracy was reduced to 83.80% using the same set of neuromarkers obtained from the ROI group with functional hyper-connections. This performance surpassed the results reported using wavelet-based features by approximately 15%. Overall, our work suggests that (1) certain ROIs are particularly effective for MCI detection, especially when multi-resolution wavelet biomarkers are employed for such diagnosis; (2) there exists a significant performance difference in system evaluation between research-based experimental design and clinically accepted evaluation standards.
Highlights
With the recent surge in the development of machine learning (ML) techniques, the success of machine learning in speech and image recognition [1,2], ML-aided clinical diagnosis has received increasing attention in the healthcare research community [3]
Based on the above analysis, we propose two hypotheses: (1) regions of interest (ROIs) showing hypoconnectivity may be reflecting the underlying anatomical changes due to progression towards Alzheimer’s disease (AD); (2) hyper-connectivity of ROIs may be induced by some compensatory mechanism limited to adjacent areas in mild cognitive impairment (MCI) groups
A series of tests were conducted to quantitatively explore the impact of region selection for MCI detection based on the two typical groups of ROIs explored in Section 2: one group represented COH-based hyperconnected functional connectivity (FC) and the other hypoconnected FCs
Summary
With the recent surge in the development of machine learning (ML) techniques, the success of machine learning in speech and image recognition [1,2], ML-aided clinical diagnosis has received increasing attention in the healthcare research community [3]. The major signal processing phases, such as signal pre-processing, neuromarker (feature) extraction, and feature classification/recognition, should be carefully engineered while developing an ML-aided diagnosis system Of all these important steps, the development of effective neuromarkers is possibly one of the most important tasks for a MEG-based MCI detection system, from the ML point of view and from the clinical perspective. Nakamura et al [6] investigated the prodromal stages of AD using source-space MEG signals reconstructed through the linearly constrained minimum variance (LCMV) beamforming technique It involved using MEG data obtained from 28 individuals with MCI and 38 cognitively normal individuals for feature extraction. Among the wavelet-based feature extraction approaches, this was considered a superior recognition performance compared to using MEG for MCI detection.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
