# Beyond Frequency Bands: Complementary-Ensemble-Empirical-Mode-Decomposition-Enhanced Microstate Sequence Non-Randomness Analysis for Aiding Diagnosis and Cognitive Prediction of Dementia

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

^{2}= 0.940). The CEEMD-enhanced MSNRI method not only aids in the exploration of large-scale neural changes in populations with dementia but also offers a robust tool for characterizing the dynamics of EEG microstate transitions and their impact on cognitive function.

## 1. Introduction

## 2. Materials and Methods

#### 2.1. Dataset

#### 2.2. Preprocessing

#### 2.3. EEG Microstate Analysis

^{−6}. The original toolkit documentation includes a complete set of sample code for microstate analysis.

#### 2.4. CEEMD-Enhanced Microstate Sequence Non-Randomness Analysis

#### 2.5. Microstate Sequence Lempel–Ziv Complexity

#### 2.6. Statistical Analysis

#### 2.7. Predictive Models for the MMSE Score

## 3. Results

#### 3.1. Microstate Maps Analysis

#### 3.2. EEG Microstate Sequence Analysis

#### 3.3. CEEMD-Enhanced Non-Randomness Analysis of Microstate Dynamic Patterns

#### 3.4. Microstate Sequence Non-Randomness Has Predictive Power for MMSE Scores

^{2}= 0.388, rMSE of 4.784, and MAE of 3.511), the proposed method in this paper achieved superior predictive performance (R

^{2}= 0.702, rMSE of 3.340, and MAE of 2.555).

^{2}= 0.940, rMSE of 1.077, and MAE of 0.807) compared to the baseline method (R

^{2}= 0.297, rMSE of 3.680, and MAE of 2.877).

## 4. Discussion

^{2}= 0.297, rMSE of 3.680, and MAE of 2.877), the method integrating CEEMD-enhanced MSNRI and MSLZC shows a significant improvement in the accuracy of predicting MMSE scores (Figure 12b, R

^{2}= 0.940, rMSE of 1.077, and MAE of 0.807). As shown in Table 6, this prediction performance exceeds the results of previous studies of MMSE prediction using microstate or other EEG characterization methods [20,37,38,39,40,41], while also confirming the potential of resting-state EEG biomarkers as substitutes or supplements for MMSE.

## 5. Conclusions

## Supplementary Materials

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Nichols, E.; Steinmetz, J.D.; Vollset, S.E.; Fukutaki, K.; Chalek, J.; Abd-Allah, F.; Abdoli, A.; Abualhasan, A.; Abu-Gharbieh, E.; Akram, T.T.; et al. Estimation of the Global Prevalence of Dementia in 2019 and Forecasted Prevalence in 2050: An Analysis for the Global Burden of Disease Study 2019. Lancet Public Health
**2022**, 7, e105–e125. [Google Scholar] [CrossRef] - Miltiadous, A.; Tzimourta, K.D.; Afrantou, T.; Ioannidis, P.; Grigoriadis, N.; Tsalikakis, D.G.; Angelidis, P.; Tsipouras, M.G.; Glavas, E.; Giannakeas, N.; et al. A Dataset of Scalp EEG Recordings of Alzheimer’s Disease, Frontotemporal Dementia and Healthy Subjects from Routine EEG. Data
**2023**, 8, 95. [Google Scholar] [CrossRef] - Miltiadous, A.; Tzimourta, K.D.; Giannakeas, N.; Tsipouras, M.G.; Afrantou, T.; Ioannidis, P.; Tzallas, A.T. Alzheimer’s Disease and Frontotemporal Dementia: A Robust Classification Method of Eeg Signals and a Comparison of Validation Methods. Diagnostics
**2021**, 11, 1437. [Google Scholar] [CrossRef] - Zheng, X.; Wang, B.; Liu, H.; Wu, W.; Sun, J.; Fang, W.; Jiang, R.; Hu, Y.; Jin, C.; Wei, X.; et al. Diagnosis of Alzheimer’s Disease via Resting-State EEG: Integration of Spectrum, Complexity, and Synchronization Signal Features. Front. Aging Neurosci.
**2023**, 15, 1288295. [Google Scholar] [CrossRef] - Cassani, R.; Estarellas, M.; San-Martin, R.; Fraga, F.J.; Falk, T.H. Systematic Review on Resting-State EEG for Alzheimer’s Disease Diagnosis and Progression Assessment. Dis. Markers
**2018**, 2018, 5174815. [Google Scholar] [CrossRef] - Wang, R.; Wang, J.; Yu, H.; Wei, X.; Yang, C.; Deng, B. Power Spectral Density and Coherence Analysis of Alzheimer’s EEG. Cogn. Neurodyn.
**2015**, 9, 291–304. [Google Scholar] [CrossRef] - Şeker, M.; Özbek, Y.; Yener, G.; Özerdem, M.S. Complexity of EEG Dynamics for Early Diagnosis of Alzheimer’s Disease Using Permutation Entropy Neuromarker. Comput. Methods Programs Biomed.
**2021**, 206, 106116. [Google Scholar] [CrossRef] - Briels, C.T.; Briels, C.T.; Schoonhoven, D.N.; Schoonhoven, D.N.; Stam, C.J.; De Waal, H.; Scheltens, P.; Gouw, A.A. Reproducibility of EEG Functional Connectivity in Alzheimer’s Disease. Alzheimer’s Res. Ther.
**2020**, 12, 68. [Google Scholar] [CrossRef] - Lassi, M.; Fabbiani, C.; Mazzeo, S.; Burali, R.; Vergani, A.A.; Giacomucci, G.; Moschini, V.; Morinelli, C.; Emiliani, F.; Scarpino, M.; et al. Degradation of EEG Microstates Patterns in Subjective Cognitive Decline and Mild Cognitive Impairment: Early Biomarkers along the Alzheimer’s Disease Continuum? NeuroImage Clin.
**2023**, 38, 103407. [Google Scholar] [CrossRef] [PubMed] - Smailovic, U.; Koenig, T.; Laukka, E.J.; Kalpouzos, G.; Andersson, T.; Winblad, B.; Jelic, V. EEG Time Signature in Alzheimer’s Disease: Functional Brain Networks Falling Apart. NeuroImage Clin.
**2019**, 24, 102046. [Google Scholar] [CrossRef] [PubMed] - Lei, L.; Liu, Z.; Zhang, Y.; Guo, M.; Liu, P.; Hu, X.; Yang, C.; Zhang, A.; Sun, N.; Wang, Y.; et al. EEG Microstates as Markers of Major Depressive Disorder and Predictors of Response to SSRIs Therapy. Prog. Neuro-Psychopharmacol. Biol. Psychiatry
**2022**, 116, 110514. [Google Scholar] [CrossRef] - Kim, K.; Duc, N.T.; Choi, M.; Lee, B. EEG Microstate Features According to Performance on a Mental Arithmetic Task. Sci. Rep.
**2021**, 11, 343. [Google Scholar] [CrossRef] - Wiemers, M.C.; Laufs, H.; von Wegner, F. Frequency Analysis of EEG Microstate Sequences in Wakefulness and NREM Sleep. Brain Topogr.
**2023**, 37, 312–328. [Google Scholar] [CrossRef] - Van De Ville, D.; Britz, J.; Michel, C.M. EEG Microstate Sequences in Healthy Humans at Rest Reveal Scale-Free Dynamics. Proc. Natl. Acad. Sci. USA
**2010**, 107, 18179–18184. [Google Scholar] [CrossRef] - Tait, L.; Tamagnini, F.; Stothart, G.; Barvas, E.; Monaldini, C.; Frusciante, R.; Volpini, M.; Guttmann, S.; Coulthard, E.; Brown, J.T.; et al. EEG Microstate Complexity for Aiding Early Diagnosis of Alzheimer’s Disease. Sci. Rep.
**2020**, 10, 17627. [Google Scholar] [CrossRef] - von Wegner, F.; Wiemers, M.; Hermann, G.; Tödt, I.; Tagliazucchi, E.; Laufs, H. Complexity Measures for EEG Microstate Sequences: Concepts and Algorithms. Brain Topogr.
**2024**, 37, 296–311. [Google Scholar] [CrossRef] - Yang, A.C.C.; Goldberger, A.L.; Peng, C.K. Genomic Classification Using an Information-Based Similarity Index: Application to the SARS Coronavirus. J. Comput. Biol.
**2005**, 12, 1103–1116. [Google Scholar] [CrossRef] - Férat, V.; Seeber, M.; Michel, C.M.; Ros, T. Beyond Broadband: Towards a Spectral Decomposition of EEG Microstates. bioRxiv
**2020**. [Google Scholar] [CrossRef] - Houmani, N.; Vialatte, F.; Gallego-Jutglà, E.; Dreyfus, G.; Nguyen-Michel, V.H.; Mariani, J.; Kinugawa, K. Diagnosis of Alzheimer’s Disease with Electroencephalography in a Differential Framework. PLoS ONE
**2018**, 13, e0193607. [Google Scholar] [CrossRef] [PubMed] - Jiao, B.; Li, R.; Zhou, H.; Qing, K.; Liu, H.; Pan, H.; Lei, Y.; Fu, W.; Wang, X.; Xiao, X.; et al. Neural Biomarker Diagnosis and Prediction to Mild Cognitive Impairment and Alzheimer’s Disease Using EEG Technology. Alzheimer’s Res. Ther.
**2023**, 15, 32. [Google Scholar] [CrossRef] [PubMed] - Vicchietti, M.L.; Ramos, F.M.; Betting, L.E.; Campanharo, A.S.L.O. Computational Methods of EEG Signals Analysis for Alzheimer’s Disease Classification. Sci. Rep.
**2023**, 13, 8184. [Google Scholar] [CrossRef] - Yeh, J.R.; Shieh, J.S.; Huang, N.E. Complementary Ensemble Empirical Mode Decomposition: A Novel Noise Enhanced Data Analysis Method. Adv. Adapt. Data Anal.
**2010**, 2, 135–156. [Google Scholar] [CrossRef] - Bell, C.C. DSM-IV: Diagnostic and Statistical Manual of Mental Disorders. JAMA J. Am. Med. Assoc.
**1994**, 272, 828–829. [Google Scholar] [CrossRef] - McKhann, G.; Drachman, D.; Folstein, M.; Katzman, R.; Price, D.; Stadlan, E.M. Clinical Diagnosis of Alzheimer’s Disease: Report of the NINCDS-ADRDA Work Group⋆ under the Auspices of Department of Health and Human Services Task Force on Alzheimer’s Disease. Neurology
**1984**, 34, 939. [Google Scholar] [CrossRef] [PubMed] - Oostenveld, R.; Fries, P.; Maris, E.; Schoffelen, J.M. FieldTrip: Open Source Software for Advanced Analysis of MEG, EEG, and Invasive Electrophysiological Data. Comput. Intell. Neurosci.
**2011**, 2011, 156869. [Google Scholar] [CrossRef] - Vigário, R.N. Extraction of Ocular Artefacts from EEG Using Independent Component Analysis. Electroencephalogr. Clin. Neurophysiol.
**1997**, 103, 395–404. [Google Scholar] [CrossRef] - Poulsen, A.T.; Pedroni, A.; Langer, N.; Hansen, L.K. Microstate EEGlab Toolbox: An Introductory Guide. bioRxiv
**2018**. [Google Scholar] [CrossRef] - Michel, C.M.; Koenig, T. EEG Microstates as a Tool for Studying the Temporal Dynamics of Whole-Brain Neuronal Networks: A Review. Neuroimage
**2018**, 180, 577–593. [Google Scholar] [CrossRef] [PubMed] - Khanna, A.; Pascual-Leone, A.; Michel, C.M.; Farzan, F. Microstates in Resting-State EEG: Current Status and Future Directions. Neurosci. Biobehav. Rev.
**2015**, 49, 105–113. [Google Scholar] [CrossRef] [PubMed] - Britz, J.; Van De Ville, D.; Michel, C.M. BOLD Correlates of EEG Topography Reveal Rapid Resting-State Network Dynamics. Neuroimage
**2010**, 52, 1162–1170. [Google Scholar] [CrossRef] - Musaeus, C.S.; Nielsen, M.S.; Høgh, P. Microstates as Disease and Progression Markers in Patients with Mild Cognitive Impairment. Front. Neurosci.
**2019**, 13, 563. [Google Scholar] [CrossRef] - Yang, A.C.C.; Hseu, S.S.; Yien, H.W.; Goldberger, A.L.; Peng, C.K. Linguistic Analysis of the Human Heartbeat Using Frequency and Rank Order Statistics. Phys. Rev. Lett.
**2003**, 90, 108103. [Google Scholar] [CrossRef] - Gaubert, S.; Raimondo, F.; Houot, M.; Corsi, M.C.; Naccache, L.; Sitt, J.D.; Hermann, B.; Oudiette, D.; Gagliardi, G.; Habert, M.O.; et al. EEG Evidence of Compensatory Mechanisms in Preclinical Alzheimer’s Disease. Brain
**2019**, 142, 2096–2112. [Google Scholar] [CrossRef] - Zhang, Y.; Zhang, Z.; Luo, L.; Tong, H.; Chen, F.; Hou, S.T. 40 Hz Light Flicker Alters Human Brain Electroencephalography Microstates and Complexity Implicated in Brain Diseases. Front. Neurosci.
**2021**, 15, 777183. [Google Scholar] [CrossRef] - Zhao, Z.; Niu, Y.; Zhao, X.; Zhu, Y.; Shao, Z.; Wu, X.; Wang, C.; Gao, X.; Wang, C.; Xu, Y.; et al. EEG Microstate in First-Episode Drug-Naive Adolescents with Depression. J. Neural Eng.
**2022**, 19, 056016. [Google Scholar] [CrossRef] - Liu, S.; Guo, J.; Meng, J.; Wang, Z.; Yao, Y.; Yang, J.; Qi, H.; Ming, D. Abnormal EEG Complexity and Functional Connectivity of Brain in Patients with Acute Thalamic Ischemic Stroke. Comput. Math. Methods Med.
**2016**, 2016, 2582478. [Google Scholar] [CrossRef] - Wei, R.; Ganglberger, W.; Sun, H.; Hadar, P.N.; Gollub, R.L.; Pieper, S.; Billot, B.; Au, R.; Iglesias, J.E.; Cash, S.S.; et al. Linking Brain Structure, Cognition, and Sleep: Insights from Clinical Data. Sleep
**2024**, 47, zsad294. [Google Scholar] [CrossRef] - Doan, D.N.T.; Ku, B.; Choi, J.; Oh, M.; Kim, K.; Cha, W.; Kim, J.U. Predicting Dementia with Prefrontal Electroencephalography and Event-Related Potential. Front. Aging Neurosci.
**2021**, 13, 659817. [Google Scholar] [CrossRef] - Jesus, B.; Cassani, R.; McGeown, W.J.; Cecchi, M.; Fadem, K.C.; Falk, T.H. Multimodal Prediction of Alzheimer’s Disease Severity Level Based on Resting-State EEG and Structural MRI. Front. Hum. Neurosci.
**2021**, 15, 700627. [Google Scholar] [CrossRef] - Zorick, T.; Landers, J.; Leuchter, A.; Mandelkern, M.A. EEG Multifractal Analysis Correlates with Cognitive Testing Scores and Clinical Staging in Mild Cognitive Impairment. J. Clin. Neurosci.
**2020**, 76, 195–200. [Google Scholar] [CrossRef] - Si, Y.; He, R.; Jiang, L.; Yao, D.; Zhang, H.; Xu, P.; Ma, X.; Yu, L.; Li, F. Differentiating between Alzheimer’s Disease and Frontotemporal Dementia Based on the Resting-State Multilayer EEG Network. IEEE Trans. Neural Syst. Rehabil. Eng.
**2023**, 31, 4521–4527. [Google Scholar] [CrossRef] [PubMed]

**Figure 2.**Schematic flow of CEEMD-enhanced microstate sequences non-randomness index analysis. Step 1: decompose broadband EEG signals into a sequence of Intrinsic Mode Functions (IMFs) using CEEMD. Step 2: perform the microstate analysis on different IMFs and reconstruct the microstate sequence based on the microstate topographic template at each IMF (Red and blue indicate positive and negative values, respectively). Step 3: construct microstate transition sequences from microstate sequences. Step 4: calculate the microstate sequence non-randomness index according to the proposed methodology.

**Figure 4.**Microstate template topographies for the four classes. (

**Top**) Globally clustered maps for all cohorts for maps A–D from left to right. (

**Second**) As above, but for the HC group. (

**Third**) For the FTD group. (

**Bottom**) For the AD group. Red and blue indicate positive and negative values, respectively. The polarity is ignored during microstate analysis.

**Figure 5.**Spatial correlation between microstate template maps of the same class across groups. The allocation of microstate maps assigned to the same grade (

**a**–

**d**) was compared across all subject groups (All, HC, FTD, AD). Each element of every matrix displays the spatial correlation coefficient between two maps (numeric values within the squares, represented by colors on a color bar).

**Figure 6.**Classical dynamic characteristics of microstates. (

**a**–

**d**) Duration of microstates in the HC, FTD and AD groups; (

**e**–

**h**) occurrence of microstates in the HC, FTD and AD groups. In all panels, the significance of the corresponding statistical test is represented as follows: * p < 0.05, ** p < 0.01, *** p < 0.001.

**Figure 7.**Microstate sequence dynamic statistics are significantly altered in disease condition (both FTD and AD). (

**a**) Microstate sequence NRI, (

**b**) microstate sequence LZC, (

**c**) EEG time series NRI, (

**d**) EEG time series LZC. Stars denote effect size of Mann–Whitney U test: * p < 0.05, ** p < 0.01, *** p < 0.001. Points in the boxplots show values for each participant. (MSNRI with parameter m = 8).

**Figure 8.**Microstate template topographies for each IMF after CEEMD decomposition. Red and blue indicate positive and negative values, respectively.

**Figure 9.**Spatial correlation between microstate topographies across IMFs. Spatial correlation of microstate template topographies (

**a**) between the broadband EEG and IMF 2, (

**b**) between the broadband EEG and IMF 3, (

**c**) between the broadband EEG and IMF 4, (

**d**) between the broadband EEG and IMF 5. Numeric values within the squares, represented by colors on a color bar.

**Figure 10.**Microstate sequence dynamic statistics are significantly altered in disease condition (both FTD and AD) in all IMFs after CEEMD decomposition. (

**a**) The CEEMD-enhanced MSNRI among the HC, FTD, and AD groups (MSNRI with parameter m = 8). (

**b**) The CEEMD-enhanced MSLZC among the HC, FTD, and AD groups. Stars denote effect size of Mann–Whitney U test: * p < 0.05, ** p < 0.01, *** p < 0.001.

**Figure 11.**The results of the multivariate linear regression model predicting MMSE scores using resting-state EEG indices for all participants, with target MMSE scores on the x-axis and predicted MMSE scores on the y-axis. (

**a**) Scatter plot and fitted line of the baseline model’s predicted values and true values based on microstate temporal metrics. (

**b**) Scatter plot and fitted line of the prediction model’s predicted values and true values based on the microstate sequence dynamic metrics proposed in this paper. Black circles represent the HC group, blue circles represent the FTD group, and red circles represent the AD group. The solid red line represents the scatter fit curve, and the shaded area indicates the 95% confidence interval.

**Figure 12.**The prediction results of the multivariate linear regression model, which predicts MMSE scores based on resting-state EEG indices, for the cognitive impairment group (FTD and AD). (

**a**) Scatter plot and fitted line of the baseline model’s predicted values and true values based on microstate temporal metrics. (

**b**) Scatter plot and fitted line of the prediction model’s predicted values and true values based on the microstate sequence dynamic metrics proposed in this paper. Blue circles represent the FTD group, and red circles represent the AD group. The solid red line represents the scatter fit curve, and the shaded area indicates the 95% confidence interval.

Subject | Population | Sex (Male/Female) | Age | MMSE | Duration of Disease (Months) |
---|---|---|---|---|---|

HC | 29 | 11/18 | 67.9 (5.4) | 30 | -- |

FTD | 23 | 14/9 | 63.6 (8.2) | 22.17 (8.22) | 23 (9.35) |

AD | 36 | 13/23 | 66.4 (7.9) | 17.75 (4.5) | 25 (9.88) |

Groups | Map-A | Map-B | Map-C | Map-D | Average Pre-Comparison |
---|---|---|---|---|---|

HC vs. FTD | 0.922 | 0.938 | 0.913 | 0.887 | 0.915 |

HC vs. AD | 0.914 | 0.947 | 0.944 | 0.924 | 0.932 |

FTD vs. AD | 0.993 | 0.985 | 0.983 | 0.952 | 0.978 |

Average per map | 0.943 | 0.957 | 0.947 | 0.921 |

**Table 3.**The detailed results of MS-NRI and MS-LZC for the HC, FTD, and AD groups across different IMFs.

Features | HC | FTD | AD | p1 | p2 | p3 |
---|---|---|---|---|---|---|

EEG MSNRI | 6.976 ± 1.623 | 5.809 ± 1.121 | 5.485 ± 1.614 | 0.008 | 0.152 | <0.001 |

IMF2 MSNRI | 6.545 ± 1.684 | 5.572 ± 1.109 | 5.288 ± 1.441 | 0.039 | 0.216 | 0.0014 |

IMF3 MSNRI | 6.726 ± 1.559 | 5.596 ± 1.138 | 5.273 ± 1.531 | 0.009 | 0.152 | <0.001 |

IMF4 MSNRI | 7.103 ± 1.648 | 5.952 ± 1.329 | 5.689 ± 1.774 | 0.012 | 0.283 | 0.001 |

IMF5 MSNRI | 7.606 ± 1.717 | 6.310 ± 1.447 | 6.027 ± 1.833 | 0.009 | 0.338 | 0.001 |

EEG MSLZC | 0.394 ± 0.011 | 0.403 ± 0.008 | 0.405 ± 0.010 | 0.016 | 0.267 | 0.0014 |

IMF2 MSLZC | 0.396 ± 0.013 | 0.405 ± 0.009 | 0.407 ± 0.009 | 0.041 | 0.2871 | 0.0016 |

IMF3 MSLZC | 0.397 ± 0.011 | 0.404 ± 0.007 | 0.407 ± 0.010 | 0.034 | 0.115 | 0.0016 |

IMF4 MSLZC | 0.390 ± 0.016 | 0.401 ± 0.012 | 0.404 ± 0.012 | 0.025 | 0.309 | 0.0022 |

IMF5 MSLZC | 0.391 ± 0.014 | 0.397 ± 0.015 | 0.402 ± 0.015 | 0.136 | 0.247 | 0.0099 |

**Table 4.**Evaluation metrics for the multivariate linear regression model predicting MMSE scores using resting-state EEG indices for all participants.

Methods | Participants | Features | Model | R^{2} | MSE | RMSE | MAE |
---|---|---|---|---|---|---|---|

Microstate dynamics | HC, FTD, AD | MSNRI, MSLZC, Duration, Occurrence, Coverage | Multiple linear regression | 0.388 | 22.888 | 4.784 | 3.511 |

CEEMD-enhanced microstate dynamics | HC, FTD, AD | CEEMD-enhanced (MSNRI, MSLZC, Duration, Occurrence, Coverage) | Multiple linear regression | 0.702 | 11.158 | 3.340 | 2.555 |

**Table 5.**Evaluation metrics for the multivariate linear regression model predicting MMSE scores based on resting-state EEG indices for the cognitive impairment group.

Methods | Participants | Features | Model | R^{2} | MSE | RMSE | MAE |
---|---|---|---|---|---|---|---|

Microstate dynamics | FTD, AD | MSNRI, MSLZC, Duration, Occurrence, Coverage | Multiple linear regression | 0.297 | 13.543 | 3.680 | 2.877 |

CEEMD-enhanced microstate dynamics | FTD, AD | CEEMD-enhanced (MSNRI, MSLZC, Duration, Occurrence, Coverage) | Multiple linear regression | 0.940 | 1.160 | 1.077 | 0.807 |

Authors | Subjects | Methods | Model | Validation | R^{2} | r | RMSE |
---|---|---|---|---|---|---|---|

Wei et al. (2024) [37] | 160 (MCI, dementia) | Time/spectral-domain features | LASSO | LOSO CV | 0.230 | -- | 2.680 |

Jiao et al. (2023) [20] | 330 (AD) | Time/spectral/microstate features | Random forest regression | 10-fold CV | 0.820 | -- | -- |

Doan et al. (2021) [38] | 122 (HC, dementia) | Spectral-domain features | Linear regression | 5-fold CV | -- | 0.680 | -- |

Jesus et al. (2021) [39] | 89 (AD) | Spectral/coherence | Random forest regression | 5-fold CV | -- | 0.348 | 1.682 |

Zorick et al. (2020) [40] | 20 (elderly) | Multifractal detrended fluctuation analysis | Classification and Regression Trees | LOSO CV | -- | 0.650 | -- |

Si et al. (2023) [41] | 88 (HC, FTD, AD) | Functional connection | Multiple linear regression | LOSO CV | -- | 0.274 | -- |

Our study | 88 (HC, FTD, AD) | CEEMD- enhanced microstate dynamics | Multiple linear regression | LOSO CV | 0.702 | -- | 3.340 |

59 (FTD, AD) | 0.940 | -- | 1.077 |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Wan, W.; Gu, Z.; Peng, C.-K.; Cui, X.
Beyond Frequency Bands: Complementary-Ensemble-Empirical-Mode-Decomposition-Enhanced Microstate Sequence Non-Randomness Analysis for Aiding Diagnosis and Cognitive Prediction of Dementia. *Brain Sci.* **2024**, *14*, 487.
https://doi.org/10.3390/brainsci14050487

**AMA Style**

Wan W, Gu Z, Peng C-K, Cui X.
Beyond Frequency Bands: Complementary-Ensemble-Empirical-Mode-Decomposition-Enhanced Microstate Sequence Non-Randomness Analysis for Aiding Diagnosis and Cognitive Prediction of Dementia. *Brain Sciences*. 2024; 14(5):487.
https://doi.org/10.3390/brainsci14050487

**Chicago/Turabian Style**

Wan, Wang, Zhongze Gu, Chung-Kang Peng, and Xingran Cui.
2024. "Beyond Frequency Bands: Complementary-Ensemble-Empirical-Mode-Decomposition-Enhanced Microstate Sequence Non-Randomness Analysis for Aiding Diagnosis and Cognitive Prediction of Dementia" *Brain Sciences* 14, no. 5: 487.
https://doi.org/10.3390/brainsci14050487