{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:02:21Z","timestamp":1764842541663,"version":"build-2065373602"},"reference-count":51,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2021,9,16]],"date-time":"2021-09-16T00:00:00Z","timestamp":1631750400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s21186210","type":"journal-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T03:47:35Z","timestamp":1632282455000},"page":"6210","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers"],"prefix":"10.3390","volume":"21","author":[{"given":"Su","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Computer Science, Swansea University, Swansea SA1 8EN, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4014-4255","authenticated-orcid":false,"given":"Jose Miguel Sanchez","family":"Bornot","sequence":"additional","affiliation":[{"name":"Intelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems, Ulster University, Londonderry BT48 7JL, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1007-900X","authenticated-orcid":false,"given":"Ricardo Bru\u00f1a","family":"Fernandez","sequence":"additional","affiliation":[{"name":"Centre for Biomedical Technology, Technical University of Madrid, 28223 Madrid, Spain"}]},{"given":"Farzin","family":"Deravi","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Kent, Canterbury CT2 7NZ, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8627-3429","authenticated-orcid":false,"given":"Sanaul","family":"Hoque","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Kent, Canterbury CT2 7NZ, UK"}]},{"given":"KongFatt","family":"Wong-Lin","sequence":"additional","affiliation":[{"name":"Intelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems, Ulster University, Londonderry BT48 7JL, UK"}]},{"given":"Girijesh","family":"Prasad","sequence":"additional","affiliation":[{"name":"Intelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems, Ulster University, Londonderry BT48 7JL, UK"}]}],"member":"1968","published-online":{"date-parts":[[2021,9,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/LSP.2017.2672753","article-title":"Universum Autoencoder-Based Domain Adaptation for Speech Emotion Recognition","volume":"24","author":"Deng","year":"2017","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ciresan, D., Meier, U., and Schmidhuber, J. (2012, January 16\u201321). Multi-column deep neural networks for image classification. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"ref_3","first-page":"1","article-title":"Functional Connectivity as a Neurophysiological Biomarker of Alzheimer\u2019s Disease","volume":"3","author":"Medvedeva","year":"2018","journal-title":"J. Alzheimer\u2019s Park. Dement."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Gross, C.G. (1999). Brain, Vision, Memory: Tales in the History of Neuroscience, MIT Press.","DOI":"10.7551\/mitpress\/1662.001.0001"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1109\/TBME.2019.2898871","article-title":"M\/EEG-based Bio-markers to predict the Mild Cognitive Impairment and Alzheimer\u2019s disease: A Review from the Machine Learning Perspective","volume":"66","author":"Yang","year":"2019","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1093\/brain\/awy044","article-title":"Electromagnetic sig-natures of the preclinical and prodromal stages of Alzheimer\u2019s disease","volume":"141","author":"Nakamura","year":"2018","journal-title":"Brain"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fnagi.2018.00400","article-title":"Amnestic mild cognitive impairment is associated with frequency-specific brain network alterations in temporal poles","volume":"10","author":"Jacini","year":"2018","journal-title":"Front. Aging Neurosci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fnins.2018.00306","article-title":"How to build a functional con-nectomic biomarker for mild cognitive impairment from source reconstructed MEG Resting-state activity: The combination of ROI representation and connectivity estimator matters","volume":"12","author":"Dimitriadis","year":"2018","journal-title":"Front. Neurosci."},{"key":"ref_9","unstructured":"(2020, June 18). Elekta Neuromag Vector View 306 Channel Meg|Mindset. Available online: https:\/\/www.mindsetconsultinggroup.com\/index.php\/what-we-do\/medical-imaging\/elekta-neuromag-vector-view-306-channel-meg."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"026010","DOI":"10.1088\/1741-2560\/11\/2\/026010","article-title":"Analysis of neural dynamics in mild cognitive impairment and Alzheimer\u2019s disease using wavelet turbulence","volume":"11","author":"Poza","year":"2014","journal-title":"J. Neural Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/1753-4631-3-2","article-title":"Everything you wanted to ask about EEG but were afraid to get the right answer","volume":"3","author":"Klonowski","year":"2009","journal-title":"Nonlinear Biomed. Phys."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-018-0613-y","article-title":"Combining EEG signal processing with supervised methods for Alzheimer\u2019s patients classification","volume":"18","author":"Fiscon","year":"2018","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"133","DOI":"10.3233\/JAD-151034","article-title":"Searching for Primary Predictors of Conversion from Mild Cognitive Impairment to Alz-heimer\u2019s Disease: A Multivariate Follow-Up Study","volume":"52","author":"Turrero","year":"2016","journal-title":"J. Alzheimer\u2019s Dis."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1759","DOI":"10.1088\/0031-9155\/51\/7\/008","article-title":"Spatiotemporal signal space separation method for rejecting nearby interference in MEG measurements","volume":"51","author":"Taulu","year":"2006","journal-title":"Phys. Med. Biol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.bspc.2014.01.009","article-title":"A survey of methods used for source localization using EEG signals","volume":"11","author":"Jatoi","year":"2014","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.neuroimage.2017.04.038","article-title":"The impact of MEG source reconstruction method on source-space connectivity estimation: A comparison between mini-mum-norm solution and beamforming","volume":"156","author":"Kujala","year":"2017","journal-title":"Neuroimage"},{"key":"ref_17","unstructured":"Vicente, J.M.F., \u00c1lvarez-S\u00e1nchez, J.R., De la Paz L\u00f3pez, F., Moreo, J.T., and Adeli, H. (2017). Natural and Artificial Computation for Biomedicine and Neuroscience: International Work-Conference on the Interplay Between Natural and Artificial Computation, Springer."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1002\/acn3.129","article-title":"Power spectra for screening parkinsonian patients for mild cognitive impairment","volume":"1","author":"Bousleiman","year":"2014","journal-title":"Ann. Clin. Transl. Neurol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1007\/s10548-018-0640-0","article-title":"Robust EEG\/MEG Based Functional Connectivity with the Envelope of the Imaginary Coherence: Sensor Space Analysis","volume":"31","author":"Bornot","year":"2018","journal-title":"Brain Topogr."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/j.bspc.2018.10.019","article-title":"A broadband method of quantifying phase synchronization for discriminating seizure EEG signals","volume":"52","author":"Wang","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Bendat, J.S., and Piersol, A.G. (2011). Random Data: Analysis and Measurement Procedures, John Wiley & Sons.","DOI":"10.1002\/9781118032428"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2292","DOI":"10.1016\/j.clinph.2004.04.029","article-title":"Identifying true brain interaction from EEG data using the imaginary part of coherency","volume":"115","author":"Nolte","year":"2004","journal-title":"Clin. Neurophysiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fnana.2015.00152","article-title":"The Structural Connectivity Pattern of the Default Mode Network and Its Association with Memory and Anxiety","volume":"9","author":"Tao","year":"2015","journal-title":"Front. Neuroanat."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3936","DOI":"10.1093\/brain\/awz320","article-title":"Hypersynchronization in mild cognitive impairment: The \u2018X\u2019 model","volume":"142","author":"Pusil","year":"2019","journal-title":"Brain"},{"key":"ref_25","first-page":"1","article-title":"The relationship between physical activity, apolipo-protein E \u03b54 carriage, and brain health","volume":"12","author":"Brown","year":"2020","journal-title":"Alzheimers. Res. Ther."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.7554\/eLife.36011","article-title":"Oscillatory hyperactivity and hyperconnectivity in young APOE-\u03b54 carriers and hypoconnectivity in alzheimer\u2019s disease","volume":"8","author":"Koelewijn","year":"2019","journal-title":"eLife"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"572","DOI":"10.3389\/fnins.2018.00572","article-title":"The Role of Magnetoencephalography in the Early Stages of Alzheimer\u2019s Disease","volume":"12","author":"Serrano","year":"2018","journal-title":"Front. Neurosci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"183","DOI":"10.3233\/JAD-2010-100177","article-title":"Functional Connectivity in Mild Cognitive Impairment During a Memory Task: Implications for the Disconnection Hypothesis","volume":"22","author":"Bajo","year":"2010","journal-title":"J. Alzheimer\u2019s Dis."},{"key":"ref_29","unstructured":"Rice, J.A. (2003). Mathematical Statistics and Data Analysis, China Machine Press."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1037\/0033-2909.111.2.352","article-title":"A more realistic look at the robustness and Type II error properties of the t test to departures from population normality","volume":"111","author":"Sawilowsky","year":"1992","journal-title":"Psychol. Bull."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1080\/01621459.1974.10480196","article-title":"EDF Statistics for Goodness of Fit and Some Comparisons","volume":"69","author":"Ramani","year":"1974","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Stephens, M.A. (2017). Tests Based on EDF Statistics. Goodness-of-Fit Techniques, CRC Press.","DOI":"10.1201\/9780203753064-4"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"941","DOI":"10.2307\/2153268","article-title":"Ten Lectures on Wavelets","volume":"61","author":"Daubechies","year":"1993","journal-title":"Math. Comput."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yang, S., and Deravi, F. (2013, January 9\u201311). Wavelet-Based EEG Preprocessing for Biometric Applications. Proceedings of the 2013 Fourth International Conference on Emerging Security Technologies, Washington, DC, USA.","DOI":"10.1109\/EST.2013.14"},{"key":"ref_35","unstructured":"Duda, R.O., Hart, P.E., and Stork, D.G. (2001). Pattern Classification, Wiley."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"ref_37","unstructured":"Fugal, D. (2009). Conceptual Wavelets in Digital Signal Processing: An In-Depth, Practical Approach for the Non-Mathematician, Space & Signals Technical Pub."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s10044-016-0569-4","article-title":"Task sensitivity in EEG biometric recognition","volume":"21","author":"Yang","year":"2018","journal-title":"Pattern Anal. Appl."},{"key":"ref_39","unstructured":"(2021, August 11). Differences and Approximate Derivatives\u2014MATLAB Diff\u2014MathWorks United Kingdom. Available online: https:\/\/uk.mathworks.com\/help\/matlab\/ref\/diff.html."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1109\/TBME.1973.324218","article-title":"A Nonstationary Analysis of the Electroencephalogram","volume":"20","author":"Kawabata","year":"1973","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"49604","DOI":"10.1109\/ACCESS.2019.2910752","article-title":"Improved Time-Frequency Features and Electrode Placement for EEG-Based Biometric Person Recognition","volume":"7","author":"Yang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.eswa.2019.04.022","article-title":"A practical computerized decision support system for predicting the severity of Alzheimer\u2019s disease of an individual","volume":"130","author":"Bucholc","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1111\/j.1751-5823.2010.00122_6.x","article-title":"Nonparametric Statistics for Non-Statisticians: A Step-by-Step Approach by Gregory W. Corder, Dale I. Foreman","volume":"78","author":"Richardson","year":"2010","journal-title":"Int. Stat. Rev."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Miller, R.G. (1981). Nonparametric Techniques. Simultaneous Statistical Inference, Springer.","DOI":"10.1007\/978-1-4613-8122-8"},{"key":"ref_45","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand. J. Stat."},{"key":"ref_46","unstructured":"(2021, August 16). Brain Anatomy, Anatomy of the Human Brain. Available online: https:\/\/mayfieldclinic.com\/pe-anatbrain.htm."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1037\/neu0000110","article-title":"Hyperconnectivity is a Fundamental Response to Neurological Disruption Introduction: Disconnecting the Brain","volume":"29","author":"Hillary","year":"2015","journal-title":"Neuropsychology"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"9774","DOI":"10.1038\/s41598-018-27997-8","article-title":"A hybrid computational approach for efficient Alzheimer\u2019s disease classification based on heterogeneous data","volume":"8","author":"Ding","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_49","first-page":"1","article-title":"Corrigendum: Multi-Kernel Learning with Dartel Improves Combined MRI-PET Classification of Alzheimer\u2019s Disease in AIBL Data: Group and Individual Analyses","volume":"11","author":"Youssofzadeh","year":"2017","journal-title":"Front. Hum. Neurosci."},{"key":"ref_50","unstructured":"Tadel, F., Bock, E., Niso, G., Mosher, J.C., Cousineau, M., Pantazis, D., Leahy, R.M., and Baillet, S. (2020, June 06). Brainstorm. Available online: https:\/\/neuroimage.usc.edu\/brainstorm\/CiteBrainstorm."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1016\/j.neuroimage.2006.01.021","article-title":"An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest","volume":"31","author":"Desikan","year":"2006","journal-title":"NeuroImage"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/18\/6210\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:00:51Z","timestamp":1760166051000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/18\/6210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,16]]},"references-count":51,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["s21186210"],"URL":"https:\/\/doi.org\/10.3390\/s21186210","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2021,9,16]]}}}