Share this content in WeChat
Clinical Article
MVPA method study for distinguishing the cognitive level of healthy elderly people based on resting-state fMRI
WANG Fangyi  TANG Jieqing  LIU Qian  YU Chengxin  LI Bo  DING Fan 

Cite this article as: WANG F Y, TANG J Q, LIU Q, et al. MVPA method study for distinguishing the cognitive level of healthy elderly people based on resting-state fMRI[J]. Chin J Magn Reson Imaging, 2023, 14(6): 18-25. DOI:10.12015/issn.1674-8034.2023.06.003.

[Abstract] Objective To construct brain network based on resting-state functional magnetic resonance imaging (fMRI) data and establish multivariate pattern analysis (MVPA) to effectively distinguish the cognitive level of healthy elderly people.Materials and Methods Using a publicly available dataset of 55 healthy elderly individuals with excellent cognitive abilities (cognitive excellent group) and 43 individuals with poor cognitive abilities (cognitive poor group), based on the resting-state fMRI data of all participants, an MVPA method was established to distinguish the cognitive level of healthy elderly people. Among them, Gaussian Copula mutual information (GCMI) was used for brain network construction and feature selection, and support vector machine (SVM) was used to complete classification. Then the existing MVPA method was used to distinguish the cognitive level of healthy elderly people as a comparison. Finally, the differences of consistency functional connection between the groups were analyzed through independent-samples t-test.Results The MVPA method established in this article effectively distinguishes the cognitive level of healthy elderly people, with a classification accuracy of 77.22%, the sensitivity, specificity and AUC were 81.82%, 72.09% and 0.77 respectively. In addition, the consistency functional connection strength of the cognitive poor group was significantly reduced compared to the cognitive excellent group, and the differences between groups were generally statistically significant (P<0.05).Conclusions Using GCMI, which is sensitive to nonlinear, to construct brain networks and filter features, combined with SVM can effectively distinguish cognitive level of healthy elderly people. Through the analysis of consistency functional connection, we found that the weakening of its strength may lead to the reduction of cognitive level. The consistency functional connection differences with statistically significant has important value in assisting clinical diagnosis.
[Keywords] functional magnetic resonance imaging;healthy elderly people;cognitive level;classification;multivariate pattern analysis;brain network;Gaussian Copula mutual information

WANG Fangyi1, 2   TANG Jieqing1, 2   LIU Qian1, 2   YU Chengxin3   LI Bo3   DING Fan1, 2*  

1 Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University, Yichang 443002, China

2 College of Computer and Information Technology, China Three Gorges University, Yichang 443002, China

3 Department of Radiology, the First College of Clinical Medical Science of China Three Gorges University and Yichang Central People's Hospital, Yichang 443003, China

Corresponding author: Ding F, E-mail:

Conflicts of interest   None.

ACKNOWLEDGMENTS Science and Technology Research Plan of Hubei Provincial Department of Education (No. Z2019096); Industry-University-Research Innovation Fund of Universities in China (No. 2019ITA03043).
Received  2022-12-23
Accepted  2023-06-07
DOI: 10.12015/issn.1674-8034.2023.06.003
Cite this article as: WANG F Y, TANG J Q, LIU Q, et al. MVPA method study for distinguishing the cognitive level of healthy elderly people based on resting-state fMRI[J]. Chin J Magn Reson Imaging, 2023, 14(6): 18-25. DOI:10.12015/issn.1674-8034.2023.06.003.

WU Q, CHEN Y Y, ZHAO X, et al. A review of cognition related macro-microstructural changes based on MRI[J]. Chin J Biomed Eng, 2019, 38(1): 94-101. DOI: 10.3969/j.issn.0258-8021.2019.01.012
ANDERSON N D. State of the science on mild cognitive impairment (MCI)[J]. CNS Spectr, 2019, 24(1): 78-87. DOI: 10.1017/S1092852918001347.
ZHANG F Y, GE M L, GUO Z T, et al. Study of multiscale entropy model to evaluate the cognitive behavior of healthy elderly people based on resting state functional magnetic resonance imaging[J/OL]. Acta Phys Sin, 2020, 69(10): 108703 [2022-12-22]. DOI: 10.7498/aps.69.20200050.
MARQUES P C, SOARES J M, MAGALHÃES R J, et al. Macro- and micro-structural white matter differences correlate with cognitive performance in healthy aging[J]. Brain Imaging Behav, 2016, 10(1): 168-181. DOI: 10.1007/s11682-015-9378-4.
YANG F, ZHANG F Y, BELKACEM A N, et al. Optimized multiscale entropy model based on resting-state fMRI for appraising cognitive performance in healthy elderly[J/OL]. Comput Math Methods Med, 2022, 2022: 2484081 [2022-12-22]. DOI: 10.1155/2022/2484081.
VAN BALKOM T D, VAN DEN HEUVEL O A, BERENDSE H W, et al. The effects of cognitive training on brain network activity and connectivity in aging and neurodegenerative diseases: a systematic review[J]. Neuropsychol Rev, 2020, 30(2): 267-286. DOI: 10.1007/s11065-020-09440-w.
DONG C, LIU T, WEN W, et al. Altered functional connectivity strength in informant-reported subjective cognitive decline: a resting-state functional magnetic resonance imaging study[J]. Alzheimers Dement (Amst), 2018, 10: 688-697. DOI: 10.1016/j.dadm.2018.08.011.
LIN Q, ROSENBERG M D, YOO K, et al. Resting-state functional connectivity predicts cognitive impairment related to alzheimer's disease[J/OL]. Front Aging Neurosci, 2018, 10: 94 [2022-12-22]. DOI: 10.3389/fnagi.2018.00094.
LI Q G, DONG C, LIU T, et al. Longitudinal changes in whole-brain functional connectivity strength patterns and the relationship with the global cognitive decline in older adults[J/OL]. Front Aging Neurosci, 2020, 12: 71 [2022-12-22]. DOI: 10.3389/fnagi.2020.00071.
WANG Q, XIA J G, TIAN W Z. Advances in research on resting brain network functional magnetic resonance imaging for PD with cognitive impairmente[J]. Chin J Magn Reson Imaging, 2020, 11(11): 1044-1047. DOI: 10.12015/issn.1674-8034.2020.11.020
MCNORGAN C, SMITH G J, EDWARDS E S. Integrating functional connectivity and MVPA through a multiple constraint network analysis[J/OL]. NeuroImage, 2020, 208: 116412 [2022-12-22]. DOI: 10.1016/j.neuroimage.2019.116412.
OSTWALD D, BAGSHAW A P. Information theoretic approaches to functional neuroimaging[J]. Magn Reson Imaging, 2011, 29(10): 1417-1428. DOI: 10.1016/j.mri.2011.07.013.
INCE R A, GIORDANO B L, KAYSER C, et al. A statistical framework for neuroimaging data analysis based on mutual information estimated via a Gaussian copula[J]. Hum Brain Mapp, 2017, 38(3): 1541-1573. DOI: 10.1002/hbm.23471.
CHANG C C, LIN C J. LIBSVM: a library for support vector machines[J]. ACM Trans Intell Syst Technol, 2(3): 1-27. DOI: 10.1145/1961189.1961199.
SANTOS N C, COSTA P S, CUNHA P, et al. Mood is a key determinant of cognitive performance in community-dwelling older adults: a cross-sectional analysis[J]. Age (Dordr), 2013, 35(5): 1983-1993. DOI: 10.1007/s11357-012-9482-y.
SANTOS N C, COSTA P S, CUNHA P, et al. Clinical, physical and lifestyle variables and relationship with cognition and mood in aging: a cross-sectional analysis of distinct educational groups[J/OL]. Front Aging Neurosci, 2014, 6: 21 [2022-12-22]. DOI: 10.3389/fnagi.2014.00021.
COSTA P S, SANTOS N C, CUNHA P, et al. The use of Bayesian latent class cluster models to classify patterns of cognitive performance in healthy ageing[J/OL]. PLoS One, 2013, 8(8): e71940 [2022-12-22]. DOI: 10.1371/journal.pone.0071940.
CABRAL J, VIDAURRE D, MARQUES P, et al. Cognitive performance in healthy older adults relates to spontaneous switching between states of functional connectivity during rest[J/OL]. Sci Rep, 2017, 7(1): 5135 [2022-12-22]. DOI: 10.1038/s41598-017-05425-7.
MARQUES P, MOREIRA P, MAGALHÃES R, et al. The functional connectome of cognitive reserve[J]. Hum Brain Mapp, 2016, 37(9): 3310-3322. DOI: 10.1002/hbm.23242.
JENKINSON M, BECKMANN C F, BEHRENS T E, et al. Fsl[J]. Neuroimage, 2012, 62(2): 782-790. DOI: 10.1016/j.neuroimage.2011.09.015.
TZOURIO-MAZOYER N, LANDEAU B, PAPATHANASSIOU D, et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain[J]. Neuroimage, 2002, 15(1): 273-289. DOI: 10.1006/nimg.2001.0978.
ZHANG X Y, Chen H Y, Tao L, et al. Combined multivariate pattern analysis with frequency-dependent intrinsic brain activity to identify essential tremor[J]. Neuroscience Letters, 2022, 776: 136566 [2022-12-22]. DOI: 10.1016/j.neulet.2022.136566.
ALORF A, KHAN M U G. Multi-label classification of Alzheimer's disease stages from resting-state fMRI-based correlation connectivity data and deep learning[J/OL]. Comput Biol Med, 2022, 151(Pt A): 106240 [2022-12-22]. DOI: 10.1016/j.compbiomed.2022.106240.
AXEL WISMÜLLER, M D, VOSOUGHI M ALI. Classification of schizophrenia from functional MRI using large-scale extended Granger causality[C]//SPIE Medical Imaging. Proc SPIE 11597, Medical Imaging 2021: Computer-Aided Diagnosis, Online Only. 2021, 11597: 337-350. DOI: 10.1117/12.2582039.
SUN L, WANG T X, DING W P, et al. Feature selection using Fisher score and multilabel neighborhood rough sets for multilabel classification[J]. Inf Sci Int J, 2021, 578(C): 887-912. DOI: 10.1016/j.ins.2021.08.032.
WANG J, LU S Y, WANG S H, et al. A review on extreme learning machine[J]. Multimedia Tools and Applications, 2021, 81(29): 41611-41660. DOI: 10.1007/s11042-021-11007-7.
TAHMASSEBI A, GANDOMI A H, SCHULTE M H J, et al. Optimized naive-Bayes and decision tree approaches for fMRI smoking cessation classification[J/OL]. Complexity, 2018, 2018: 1-24 [2022-12-22]. DOI: 10.1155/2018/2740817.
KAMARAJAN C, ARDEKANI B A, PANDEY A K, et al. Random forest classification of alcohol use disorder using fMRI functional connectivity, neuropsychological functioning, and impulsivity measures[J/OL]. Brain Sci, 2020, 10(2): 115 [2022-12-22]. DOI: 10.3390/brainsci10020115.
FAWCETT T. An introduction to ROC analysis[J]. Pattern Recognit Lett, 2006, 27(8): 861-874. DOI: 10.1016/j.patrec.2005.10.010.
OJALA M, GARRIGA G C. Permutation tests for studying classifier performance[C]//2009 Ninth IEEE International Conference on Data Mining. December 6-9, 2009, Miami Beach, FL, USA. IEEE, 2009: 908-913. DOI: 10.1109/ICDM.2009.108.
DOSENBACH N U, NARDOS B, COHEN A L, et al. Prediction of individual brain maturity using fMRI[J]. Science, 2010, 329(5997): 1358-1361. DOI: 10.1126/science.1194144.
KRZYWINSKI M, SCHEIN J, BIROL I, et al. Circos: an information aesthetic for comparative genomics[J]. Genome Res, 2009, 19(9): 1639-1645. DOI: 10.1101/gr.092759.109.
SHI K, PANG X M, WANG Y L, et al. Altered interhemispheric functional homotopy and connectivity in temporal lobe epilepsy based on fMRI and multivariate pattern analysis[J]. Neuroradiology, 2021, 63(11): 1873-1882. DOI: 10.1007/s00234-021-02706-x.
PISTONO A, SENOUSSI M, GUERRIER L, et al. Language network connectivity increases in early alzheimer's disease[J]. J Alzheimers Dis, 2021, 82(1): 447-460. DOI: 10.3233/JAD-201584.
SU Q, ZHAO R, WANG S W, et al. Identification and therapeutic outcome prediction of cervical spondylotic myelopathy based on the functional connectivity from resting-state functional MRI data: a preliminary machine learning study[J/OL]. Front Neurol, 2021, 12: 711880 [2022-12-22]. DOI: 10.3389/fneur.2021.711880.
GUO Z T, GE M L, ZHANG F Y, et al. The specific index model of resting-state fMRI functional connectivity in the application to the evaluation of cognitive score of healthy elderly[J]. Chin J Biomed Eng, 2020, 39(6): 676-684. DOI: 10.3969/j.issn.0258-8021.2020.06.004.
MENON V, GALLARDO G, PINSK M A, et al. Microstructural organization of human insula is linked to its macrofunctional circuitry and predicts cognitive control[J/OL]. Elife, 2020, 9: e53470 [2022-12-22]. DOI: 10.7554/eLife.53470.

PREV Interhemispheric structural connectivity abnormalities in Alzheimer,s disease and mild cognitive impairment: A DTI-based study
NEXT Bibliometric analysis in neuroimaging of epilepsy research

Tel & Fax: +8610-67113815    E-mail: