1
|
Kachare P, Puri D, Sangle SB, Al-Shourbaji I, Jabbari A, Kirner R, Alameen A, Migdady H, Abualigah L. LCADNet: a novel light CNN architecture for EEG-based Alzheimer disease detection. Phys Eng Sci Med 2024; 47:1037-1050. [PMID: 38862778 DOI: 10.1007/s13246-024-01425-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2023] [Accepted: 04/10/2024] [Indexed: 06/13/2024]
Abstract
Alzheimer's disease (AD) is a progressive and incurable neurologi-cal disorder with a rising mortality rate, worsened by error-prone, time-intensive, and expensive clinical diagnosis methods. Automatic AD detection methods using hand-crafted Electroencephalogram (EEG) signal features lack accuracy and reliability. A lightweight convolution neural network for AD detection (LCADNet) is investigated to extract disease-specific features while reducing the detection time. The LCADNet uses two convolutional layers for extracting complex EEG features, two fully connected layers for selecting disease-specific features, and a softmax layer for predicting AD detection probability. A max-pooling layer interlaced between convolutional layers decreases the time-domain redundancy in the EEG signal. The efficiency of the LCADNet and four pre-trained models using transfer learning is compared using a publicly available AD detection dataset. The LCADNet shows the lowest computation complexity in terms of both the number of floating point operations and inference time and the highest classification performance across six measures. The generalization of the LCADNet is assessed by cross-testing it with two other publicly available AD detection datasets. It outperforms existing EEG-based AD detection methods with an accuracy of 98.50%. The LCADNet may be a valuable aid for neurologists and its Python implemen- tation can be found at github.com/SandeepSangle12/LCADNet.git.
Collapse
Affiliation(s)
- Pramod Kachare
- Department of Electronics and Telecommunication, Ramrao Adik Institute of Technology, D. Y. Patil Campus, Navi-Mumbai, Maharashtra, 400706, India
| | - Digambar Puri
- Department of Electronics and Telecommunication, Ramrao Adik Institute of Technology, D. Y. Patil Campus, Navi-Mumbai, Maharashtra, 400706, India
| | - Sandeep B Sangle
- Department of Electronics and Telecommunication, Ramrao Adik Institute of Technology, D. Y. Patil Campus, Navi-Mumbai, Maharashtra, 400706, India
| | - Ibrahim Al-Shourbaji
- Department of Electrical and Electronics Engineering, Jazan University, Jazan, 45142, Saudi Arabia
- Department of Computer Science, University of Hertfordshire, Hatfield, UK
| | - Abdoh Jabbari
- Department of Electrical and Electronics Engineering, Jazan University, Jazan, 45142, Saudi Arabia
| | - Raimund Kirner
- Department of Computer Science, University of Hertfordshire, Hatfield, UK
| | - Abdalla Alameen
- Department of Computer Engineering and Information, College of Engineering in Wadi Alddawasir, Prince Sattam Bin Abdulaziz University, Wadi Alddawasir, 11991, Saudi Arabia
| | - Hazem Migdady
- CSMIS Department, Oman College of Management and Technology, 320, Barka, Oman
| | - Laith Abualigah
- Jadara Research Center, Jadara University, Irbid, 21110, Jordan.
- Computer Science Department, Al al-Bayt University, Mafraq, 25113, Jordan.
- MEU Research Unit, Middle East University, Amman, 11831, Jordan.
- Applied science research center, Applied science private university, Amman, 11931, Jordan.
| |
Collapse
|
2
|
Gaeta AM, Quijada-López M, Barbé F, Vaca R, Pujol M, Minguez O, Sánchez-de-la-Torre M, Muñoz-Barrutia A, Piñol-Ripoll G. Predicting Alzheimer's disease CSF core biomarkers: a multimodal Machine Learning approach. Front Aging Neurosci 2024; 16:1369545. [PMID: 38988328 PMCID: PMC11233742 DOI: 10.3389/fnagi.2024.1369545] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2024] [Accepted: 06/04/2024] [Indexed: 07/12/2024] Open
Abstract
Introduction Alzheimer's disease (AD) is a progressive neurodegenerative disorder. Current core cerebrospinal fluid (CSF) AD biomarkers, widely employed for diagnosis, require a lumbar puncture to be performed, making them impractical as screening tools. Considering the role of sleep disturbances in AD, recent research suggests quantitative sleep electroencephalography features as potential non-invasive biomarkers of AD pathology. However, quantitative analysis of comprehensive polysomnography (PSG) signals remains relatively understudied. PSG is a non-invasive test enabling qualitative and quantitative analysis of a wide range of parameters, offering additional insights alongside other biomarkers. Machine Learning (ML) gained interest for its ability to discern intricate patterns within complex datasets, offering promise in AD neuropathology detection. Therefore, this study aims to evaluate the effectiveness of a multimodal ML approach in predicting core AD CSF biomarkers. Methods Mild-moderate AD patients were prospectively recruited for PSG, followed by testing of CSF and blood samples for biomarkers. PSG signals underwent preprocessing to extract non-linear, time domain and frequency domain statistics quantitative features. Multiple ML algorithms were trained using four subsets of input features: clinical variables (CLINVAR), conventional PSG parameters (SLEEPVAR), quantitative PSG signal features (PSGVAR) and a combination of all subsets (ALL). Cross-validation techniques were employed to evaluate model performance and ensure generalizability. Regression models were developed to determine the most effective variable combinations for explaining variance in the biomarkers. Results On 49 subjects, Gradient Boosting Regressors achieved the best results in estimating biomarkers levels, using different loss functions for each biomarker: least absolute deviation (LAD) for the Aβ42, least squares (LS) for p-tau and Huber for t-tau. The ALL subset demonstrated the lowest training errors for all three biomarkers, albeit with varying test performance. Specifically, the SLEEPVAR subset yielded the best test performance in predicting Aβ42, while the ALL subset most accurately predicted p-tau and t-tau due to the lowest test errors. Conclusions Multimodal ML can help predict the outcome of CSF biomarkers in early AD by utilizing non-invasive and economically feasible variables. The integration of computational models into medical practice offers a promising tool for the screening of patients at risk of AD, potentially guiding clinical decisions.
Collapse
Affiliation(s)
- Anna Michela Gaeta
- Servicio de Neumología, Hospital Universitario Severo Ochoa, Leganés, Spain
| | - María Quijada-López
- Departamento de Bioingeniería, Universidad Carlos III de Madrid, Leganés, Spain
| | - Ferran Barbé
- Group of Translational Research in Respiratory Medicine, Hospital Universitari Arnau de Vilanova and Santa Maria, Institut de Recerca Biomedica de Lleida (IRBLleida), Lleida, Spain
- Centro de Investigación Biomédica en Red de Enfermedades Respiratorias (CIBERES), Madrid, Spain
| | - Rafaela Vaca
- Group of Translational Research in Respiratory Medicine, Hospital Universitari Arnau de Vilanova and Santa Maria, Institut de Recerca Biomedica de Lleida (IRBLleida), Lleida, Spain
| | - Montse Pujol
- Unitat Trastorns Cognitius, Clinical Neuroscience Research, Institut de Recerca Biomedica de Lleida (IRBLleida), Hospital Universitari Santa Maria, Lleida, Spain
| | - Olga Minguez
- Group of Translational Research in Respiratory Medicine, Hospital Universitari Arnau de Vilanova and Santa Maria, Institut de Recerca Biomedica de Lleida (IRBLleida), Lleida, Spain
| | - Manuel Sánchez-de-la-Torre
- Centro de Investigación Biomédica en Red de Enfermedades Respiratorias (CIBERES), Madrid, Spain
- Group of Precision Medicine in Chronic Diseases, Hospital Nacional de Parapléjicos, IDISCAM, Department of Nursing, Physiotherapy and Occupational Therapy, Faculty of Physiotherapy and Nursing, University of Castilla-La Mancha, Toledo, Spain
| | - Arrate Muñoz-Barrutia
- Departamento de Bioingeniería, Universidad Carlos III de Madrid, Leganés, Spain
- Departamento de Bioingegneria, Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain
| | - Gerard Piñol-Ripoll
- Unitat Trastorns Cognitius, Clinical Neuroscience Research, Institut de Recerca Biomedica de Lleida (IRBLleida), Hospital Universitari Santa Maria, Lleida, Spain
| |
Collapse
|
3
|
Li N, Ou J, He H, He J, Zhang L, Peng Z, Zhong J, Jiang N. Exploration of a machine learning approach for diagnosing sarcopenia among Chinese community-dwelling older adults using sEMG-based data. J Neuroeng Rehabil 2024; 21:69. [PMID: 38725065 PMCID: PMC11080130 DOI: 10.1186/s12984-024-01369-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Accepted: 04/25/2024] [Indexed: 05/13/2024] Open
Abstract
BACKGROUND In the practical application of sarcopenia screening, there is a need for faster, time-saving, and community-friendly detection methods. The primary purpose of this study was to perform sarcopenia screening in community-dwelling older adults and investigate whether surface electromyogram (sEMG) from hand grip could potentially be used to detect sarcopenia using machine learning (ML) methods with reasonable features extracted from sEMG signals. The secondary aim was to provide the interpretability of the obtained ML models using a novel feature importance estimation method. METHODS A total of 158 community-dwelling older residents (≥ 60 years old) were recruited. After screening through the diagnostic criteria of the Asian Working Group for Sarcopenia in 2019 (AWGS 2019) and data quality check, participants were assigned to the healthy group (n = 45) and the sarcopenic group (n = 48). sEMG signals from six forearm muscles were recorded during the hand grip task at 20% maximal voluntary contraction (MVC) and 50% MVC. After filtering recorded signals, nine representative features were extracted, including six time-domain features plus three time-frequency domain features. Then, a voting classifier ensembled by a support vector machine (SVM), a random forest (RF), and a gradient boosting machine (GBM) was implemented to classify healthy versus sarcopenic participants. Finally, the SHapley Additive exPlanations (SHAP) method was utilized to investigate feature importance during classification. RESULTS Seven out of the nine features exhibited statistically significant differences between healthy and sarcopenic participants in both 20% and 50% MVC tests. Using these features, the voting classifier achieved 80% sensitivity and 73% accuracy through a five-fold cross-validation. Such performance was better than each of the SVM, RF, and GBM models alone. Lastly, SHAP results revealed that the wavelength (WL) and the kurtosis of continuous wavelet transform coefficients (CWT_kurtosis) had the highest feature impact scores. CONCLUSION This study proposed a method for community-based sarcopenia screening using sEMG signals of forearm muscles. Using a voting classifier with nine representative features, the accuracy exceeds 70% and the sensitivity exceeds 75%, indicating moderate classification performance. Interpretable results obtained from the SHAP model suggest that motor unit (MU) activation mode may be a key factor affecting sarcopenia.
Collapse
Affiliation(s)
- Na Li
- The National Clinical Research Center for Geriatrics, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- Medical Equipment Innovation Research Center, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- The Med-X Center for Manufacturing, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Jiarui Ou
- College of Computer Science, Sichuan University, Chengdu, 610065, China
| | - Haoru He
- The National Clinical Research Center for Geriatrics, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- Medical Equipment Innovation Research Center, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- The Med-X Center for Manufacturing, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Jiayuan He
- The National Clinical Research Center for Geriatrics, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- Medical Equipment Innovation Research Center, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China
- The Med-X Center for Manufacturing, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Le Zhang
- College of Computer Science, Sichuan University, Chengdu, 610065, China
| | - Zhengchun Peng
- School of Electronic Information and ElectricaEngineering, Shanghaijiao Tong University, Shanghai, 200240, China
| | - Junwen Zhong
- Department of Electromechanical Engineering and Centre for Artificial Intelligence and Robotics, University of Macau, Macau, SAR, 999078, China
| | - Ning Jiang
- The National Clinical Research Center for Geriatrics, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China.
- Medical Equipment Innovation Research Center, West China Hospital of Sichuan University, Chengdu, Sichuan, 610041, China.
- The Med-X Center for Manufacturing, Sichuan University, Chengdu, Sichuan, 610041, China.
| |
Collapse
|
4
|
Chen S, Zhang C, Yang H, Peng L, Xie H, Lv Z, Hou ZG. A Multi-Modal Classification Method for Early Diagnosis of Mild Cognitive Impairment and Alzheimer's Disease Using Three Paradigms With Various Task Difficulties. IEEE Trans Neural Syst Rehabil Eng 2024; 32:1477-1486. [PMID: 38568773 DOI: 10.1109/tnsre.2024.3379891] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/05/2024]
Abstract
Alzheimer's Disease (AD) accounts for the majority of dementia, and Mild Cognitive Impairment (MCI) is the early stage of AD. Early and accurate diagnosis of dementia plays a vital role in more targeted treatments and effectively halting disease progression. However, the clinical diagnosis of dementia requires various examinations, which are expensive and require a high level of expertise from the doctor. In this paper, we proposed a classification method based on multi-modal data including Electroencephalogram (EEG), eye tracking and behavioral data for early diagnosis of AD and MCI. Paradigms with various task difficulties were used to identify different severity of dementia: eye movement task and resting-state EEG tasks were used to detect AD, while eye movement task and delayed match-to-sample task were used to detect MCI. Besides, the effects of different features were compared and suitable EEG channels were selected for the detection. Furthermore, we proposed a data augmentation method to enlarge the dataset, designed an extra ERPNet feature extract layer to extract multi-modal features and used domain-adversarial neural network to improve the performance of MCI diagnosis. We achieved an average accuracy of 88.81% for MCI diagnosis and 100% for AD diagnosis. The results of this paper suggest that our classification method can provide a feasible and affordable way to diagnose dementia.
Collapse
|
5
|
Kim SK, Kim H, Kim SH, Kim JB, Kim L. Electroencephalography-based classification of Alzheimer's disease spectrum during computer-based cognitive testing. Sci Rep 2024; 14:5252. [PMID: 38438453 PMCID: PMC10912091 DOI: 10.1038/s41598-024-55656-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2023] [Accepted: 02/26/2024] [Indexed: 03/06/2024] Open
Abstract
Alzheimer's disease (AD) is a progressive disease leading to cognitive decline, and to prevent it, researchers seek to diagnose mild cognitive impairment (MCI) early. Particularly, non-amnestic MCI (naMCI) is often mistaken for normal aging as the representative symptom of AD, memory decline, is absent. Subjective cognitive decline (SCD), an intermediate step between normal aging and MCI, is crucial for prediction or early detection of MCI, which determines the presence of AD spectrum pathology. We developed a computer-based cognitive task to classify the presence or absence of AD pathology and stage within the AD spectrum, and attempted to perform multi-stage classification through electroencephalography (EEG) during resting and memory encoding state. The resting and memory-encoding states of 58 patients (20 with SCD, 10 with naMCI, 18 with aMCI, and 10 with AD) were measured and classified into four groups. We extracted features that could reflect the phase, spectral, and temporal characteristics of the resting and memory-encoding states. For the classification, we compared nine machine learning models and three deep learning models using Leave-one-subject-out strategy. Significant correlations were found between the existing neurophysiological test scores and performance of our computer-based cognitive task for all cognitive domains. In all models used, the memory-encoding states realized a higher classification performance than resting states. The best model for the 4-class classification was cKNN. The highest accuracy using resting state data was 67.24%, while it was 93.10% using memory encoding state data. This study involving participants with SCD, naMCI, aMCI, and AD focused on early Alzheimer's diagnosis. The research used EEG data during resting and memory encoding states to classify these groups, demonstrating the significance of cognitive process-related brain waves for diagnosis. The computer-based cognitive task introduced in the study offers a time-efficient alternative to traditional neuropsychological tests, showing a strong correlation with their results and serving as a valuable tool to assess cognitive impairment with reduced bias.
Collapse
Affiliation(s)
- Seul-Kee Kim
- Bionics Research Center, Korea Institute of Science and Technology, Seoul, Republic of Korea
- Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea
| | - Hayom Kim
- Department of Neurology, Korea University Anam Hospital, Korea University College of Medicine, Seoul, Republic of Korea
| | - Sang Hee Kim
- Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea
| | - Jung Bin Kim
- Department of Neurology, Korea University Anam Hospital, Korea University College of Medicine, Seoul, Republic of Korea.
| | - Laehyun Kim
- Bionics Research Center, Korea Institute of Science and Technology, Seoul, Republic of Korea.
- Department of HY-KIST Bio-Convergence, Hanyang University, Seoul, Republic of Korea.
| |
Collapse
|
6
|
Klepl D, He F, Wu M, Blackburn DJ, Sarrigiannis P. Adaptive Gated Graph Convolutional Network for Explainable Diagnosis of Alzheimer's Disease Using EEG Data. IEEE Trans Neural Syst Rehabil Eng 2023; 31:3978-3987. [PMID: 37792656 DOI: 10.1109/tnsre.2023.3321634] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/06/2023]
Abstract
Graph neural network (GNN) models are increasingly being used for the classification of electroencephalography (EEG) data. However, GNN-based diagnosis of neurological disorders, such as Alzheimer's disease (AD), remains a relatively unexplored area of research. Previous studies have relied on functional connectivity methods to infer brain graph structures and used simple GNN architectures for the diagnosis of AD. In this work, we propose a novel adaptive gated graph convolutional network (AGGCN) that can provide explainable predictions. AGGCN adaptively learns graph structures by combining convolution-based node feature enhancement with a correlation-based measure of power spectral density similarity. Furthermore, the gated graph convolution can dynamically weigh the contribution of various spatial scales. The proposed model achieves high accuracy in both eyes-closed and eyes-open conditions, indicating the stability of learned representations. Finally, we demonstrate that the proposed AGGCN model generates consistent explanations of its predictions that might be relevant for further study of AD-related alterations of brain networks.
Collapse
|
7
|
Qiao R, Zhang H, Tian Y. EEG cortical network reveals the temporo-spatial mechanism of visual search. Brain Res Bull 2023; 203:110758. [PMID: 37704055 DOI: 10.1016/j.brainresbull.2023.110758] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2023] [Revised: 08/06/2023] [Accepted: 09/11/2023] [Indexed: 09/15/2023]
Abstract
This study aims to explore a method based on brain networks for implicit attention by using wavelet coherence as feature to identify individual targets in the visual field, find the optimal classification rhythm and time window, and investigate the relationship between the optimal rhythm and N2pc event-related potential. The study uses a weighted minimum norm estimate to locate the sources of the scalp EEG and reconstructs the source time series. The functional connectivity between brain areas during the visual search process is evaluated using wavelet coherence analysis, and a lateral difference network is constructed based on the difference in coherence values between the left and right visual fields. A support vector machine classifier is trained based on the wavelet coherence network features to identify the target in the left or right visual field. We also extract N2pc from the source activity data of the parieto-occipital brain region and record the time period in which N2pc occurred. The study finds that the best classification performance is achieved in the theta rhythm from 200 to 400 ms and achieved an average classification accuracy of 87% (chance level: 51.07%) in a serial search task. And this time window corresponds to the time period when N2pc appeared. The results show that the use of wavelet coherence analysis to evaluate the functional connectivity between brain areas during the visual search process provides a new approach for analyzing brain activity. The study's findings regarding the relationship between the N2pc and theta rhythm and the effectiveness of using wavelet coherence network features based on the theta rhythm for visual search classification contribute to the understanding of the neural mechanisms underlying visual search.
Collapse
Affiliation(s)
- Rui Qiao
- School of Bioinformatics, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
| | - Haiyong Zhang
- School of Bioinformatics, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
| | - Yin Tian
- School of Bioinformatics, Chongqing University of Posts and Telecommunications, Chongqing 400065, China; School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China; Institute for Advanced Sciences,Chongqing University of Posts and Telecommunications, Chongqing 400065, China; Chongqing Institute for Brain and Intelligence, Guangyang Bay Laboratory, Chongqing 400064, China.
| |
Collapse
|
8
|
Klepl D, He F, Wu M, Blackburn DJ, Sarrigiannis PG. Cross-Frequency Multilayer Network Analysis with Bispectrum-based Functional Connectivity: A Study of Alzheimer's Disease. Neuroscience 2023; 521:77-88. [PMID: 37121381 DOI: 10.1016/j.neuroscience.2023.04.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2022] [Revised: 02/08/2023] [Accepted: 04/04/2023] [Indexed: 05/02/2023]
Abstract
Alzheimer's disease (AD) is a neurodegenerative disorder known to affect functional connectivity (FC) across many brain regions. Linear FC measures have been applied to study the differences in AD by splitting neurophysiological signals, such as electroencephalography (EEG) recordings, into discrete frequency bands and analysing them in isolation from each other. We address this limitation by quantifying cross-frequency FC in addition to the traditional within-band approach. Cross-bispectrum, a higher-order spectral analysis approach, is used to measure the nonlinear FC and is compared with the cross-spectrum, which only measures the linear FC within bands. This work reports the reconstruction of a cross-frequency FC network where each frequency band is treated as a layer in a multilayer network with both inter- and intra-layer edges. Cross-bispectrum detects cross-frequency differences, mainly increased FC in AD cases in δ-θ coupling. Overall, increased strength of low-frequency coupling and decreased level of high-frequency coupling is observed in AD cases in comparison to healthy controls (HC). We demonstrate that a graph-theoretic analysis of cross-frequency brain networks is crucial to obtain a more detailed insight into their structure and function. Vulnerability analysis reveals that the integration and segregation properties of networks are enabled by different frequency couplings in AD networks compared to HCs. Finally, we use the reconstructed networks for classification. The extra cross-frequency coupling information can improve the classification performance significantly, suggesting an important role of cross-frequency FC. The results highlight the importance of studying nonlinearity and including cross-frequency FC in characterising AD.
Collapse
Affiliation(s)
- Dominik Klepl
- Centre for Computational Science and Mathematical Modelling, Coventry University, Coventry CV1 2JH, UK; Infocomm Research, A*STAR, Singapore
| | - Fei He
- Centre for Computational Science and Mathematical Modelling, Coventry University, Coventry CV1 2JH, UK.
| | - Min Wu
- Infocomm Research, A*STAR, Singapore
| | - Daniel J Blackburn
- Department of Neuroscience, University of Sheffield, SheffieldS10 2HQ, UK
| | | |
Collapse
|
9
|
Klepl D, He F, Min W, Blackburn D, Sarrigiannis P. Bispectrum-based Cross-frequency Functional Connectivity: Classification of Alzheimer's disease. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2022; 2022:305-308. [PMID: 36086488 DOI: 10.1109/embc48229.2022.9871366] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Alzheimer's disease (AD) is a neurodegenerative disease known to affect brain functional connectivity (FC). Linear FC measures have been applied to study the differences in AD by splitting neurophysiological signals such as electroencephalography (EEG) recordings into discrete frequency bands and analysing them in isolation. We address this limitation by quantifying cross-frequency FC in addition to the traditional within-band approach. Cross-bispectrum, a higher-order spectral analysis, is used to measure the nonlinear FC and is compared with the cross-spectrum, which only measures the linear FC within bands. Each frequency coupling is then used to construct an FC network, which is in turn vectorised and used to train a classifier. We show that fusing features from networks improves classification accuracy. Although both within-frequency and cross-frequency networks can be used to predict AD with high accuracy, our results show that bispectrum-based FC outperforms cross-spectrum suggesting an important role of cross-frequency FC. Clinical relevance-This establishes diagnostic relevance of cross-frequency coupling in Alzheimer's disease.
Collapse
|
10
|
Klepl D, He F, Wu M, Marco MD, Blackburn DJ, Sarrigiannis PG. Characterising Alzheimer's Disease with EEG-based Energy Landscape Analysis. IEEE J Biomed Health Inform 2021; 26:992-1000. [PMID: 34406951 DOI: 10.1109/jbhi.2021.3105397] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
Alzheimer's disease (AD) is one of the most common neurodegenerative diseases, with around 50 million patients worldwide. Accessible and non-invasive methods of diagnosing and characterising AD are therefore urgently required. Electroencephalography (EEG) fulfils these criteria and is often used when studying AD. Several features derived from EEG were shown to predict AD with high accuracy, e.g. signal complexity and synchronisation. However, the dynamics of how the brain transitions between stable states have not been properly studied in the case of AD and EEG. Energy landscape analysis is a method that can be used to quantify these dynamics. This work presents the first application of this method to both AD and EEG. Energy landscape assigns energy value to each possible state, i.e. pattern of activations across brain regions. The energy is inversely proportional to the probability of occurrence. By studying the features of energy landscapes of 20 AD patients and 20 age-matched healthy counterparts (HC), significant differences are found. The dynamics of AD patients' EEG are shown to be more constrained - with more local minima, less variation in basin size, and smaller basins. We show that energy landscapes can predict AD with high accuracy, performing significantly better than baseline models. Moreover, these findings are replicated in a separate dataset including 9 AD and 10 HC above 70 years old.
Collapse
|
11
|
Santos Toural JE, Montoya Pedrón A, Marañón Reyes EJ. A new method for classification of subjects with major cognitive disorder, Alzheimer type, based on electroencephalographic biomarkers. INFORMATICS IN MEDICINE UNLOCKED 2021. [DOI: 10.1016/j.imu.2021.100537] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022] Open
|
12
|
Santos Toural JE, Montoya Pedrón A, Marañón Reyes EJ. Classification among healthy, mild cognitive impairment and Alzheimer’s disease subjects based on wavelet entropy and relative beta and theta power. Pattern Anal Appl 2020. [DOI: 10.1007/s10044-020-00910-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
13
|
Pineda AM, Ramos FM, Betting LE, Campanharo ASLO. Quantile graphs for EEG-based diagnosis of Alzheimer's disease. PLoS One 2020; 15:e0231169. [PMID: 32502204 PMCID: PMC7274384 DOI: 10.1371/journal.pone.0231169] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2019] [Accepted: 03/17/2020] [Indexed: 02/07/2023] Open
Abstract
Known as a degenerative and progressive dementia, Alzheimer’s disease (AD) affects about 25 million elderly people around the world. This illness results in a decrease in the productivity of people and places limits on their daily lives. Electroencephalography (EEG), in which the electrical brain activity is recorded in the form of time series and analyzed using signal processing techniques, is a well-known neurophysiological AD biomarker. EEG is noninvasive, low-cost, has a high temporal resolution, and provides valuable information about brain dynamics in AD. Here, we present an original approach based on the use of quantile graphs (QGs) for classifying EEG data. QGs map frequency, amplitude, and correlation characteristics of a time series (such as the EEG data of an AD patient) into the topological features of a network. The five topological network metrics used here—clustering coefficient, mean jump length, betweenness centrality, modularity, and Laplacian Estrada index—showed that the QG model can distinguish healthy subjects from AD patients, with open or closed eyes. The QG method also indicates which channels (corresponding to 19 different locations on the patients’ scalp) provide the best discriminating power. Furthermore, the joint analysis of delta, theta, alpha, and beta wave results indicate that all AD patients under study display clear symptoms of the disease and may have it in its late stage, a diagnosis known a priori and supported by our study. Results presented here attest to the usefulness of the QG method in analyzing complex, nonlinear signals such as those generated from AD patients by EEGs.
Collapse
Affiliation(s)
- Aruane M. Pineda
- Department of Biostatistics, Institute of Biosciences, São Paulo State University (UNESP), Botucatu, São Paulo, Brazil
| | - Fernando M. Ramos
- National Institute for Space Research (INPE), Earth System Science Center (CCST), São José dos Campos, São Paulo, Brazil
| | - Luiz Eduardo Betting
- Department of Neurology, Psychology and Psychiatry, Institute of Biosciences, Botucatu Medical School, São Paulo State University (UNESP), Botucatu, São Paulo, Brazil
| | - Andriana S. L. O. Campanharo
- Department of Biostatistics, Institute of Biosciences, São Paulo State University (UNESP), Botucatu, São Paulo, Brazil
- * E-mail:
| |
Collapse
|
14
|
Devilbiss DM, Etnoyer-Slaski JL, Dunn E, Dussourd CR, Kothare MV, Martino SJ, Simon AJ. Effects of Exercise on EEG Activity and Standard Tools Used to Assess Concussion. JOURNAL OF HEALTHCARE ENGINEERING 2019; 2019:4794637. [PMID: 31183030 PMCID: PMC6515073 DOI: 10.1155/2019/4794637] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/01/2018] [Revised: 03/18/2019] [Accepted: 04/01/2019] [Indexed: 12/19/2022]
Abstract
A variety of cognitive assessment tools are used to determine the functional status of the brain before and after injury in athletes. Questionnaires, neuropsychological tests, and electroencephalographic (EEG) measures have been recently used to directly assess brain function on and near the playing field. However, exercise can affect cognitive performance and EEG measures of cortical activity. To date, little empirical evidence exists on the effects of acute exercise on these measures of neurological function. We therefore quantified athlete performance on a standardized battery of concussion assessment tools and EEG measurements immediately before and after acute exercise to simulate conditions of athletic competition. Heart rate and arterial oxygen levels were collected before and after the exercise challenge consisting of a 1-mile run. Together these data, from a gender-balanced cohort of collegiate athletes, demonstrated that moderate to hard levels of acute exercise improved performance on the King-Devick test (K-D test) and Standardized Assessment of Concussion (SAC) component of the Sport Concussion Assessment Tool (SCAT3). Gender played an important role in these effects, and performance was most affected by exercise in female athletes. EEG activity in the theta band (4-8 Hz) was decreased during periods of quiet resting with eyes open or eyes closed. Additionally, exercise produced a slowing of the EEG during the K-D test and a shift to higher frequencies during the balance assessment of the SCAT3. Together, these data indicate that exercise alone can influence outcome measures of cognitive assessment tools used to assess brain function in athletes. Finally, care must be taken to acquire postinjury measurements during a comparable physiologic state to that in which baseline assessment data were measured, and further research is needed into the factors influencing outcome measures of these tests.
Collapse
Affiliation(s)
- David M. Devilbiss
- Rowan University, Department of Cell Biology and Neuroscience, 2 Medical Center Drive, SC220, Stratford, NJ 08084, USA
| | - Jena L. Etnoyer-Slaski
- Lehigh University, Department of Sports Medicine, 641 Taylor Street, Bethlehem, PA 18015, USA
| | - Emily Dunn
- Lehigh University, Department of Sports Medicine, 641 Taylor Street, Bethlehem, PA 18015, USA
| | - Christopher R. Dussourd
- Lehigh University, Department of Sports Medicine, 641 Taylor Street, Bethlehem, PA 18015, USA
| | - Mayuresh V. Kothare
- Lehigh University, Department of Chemical & Biomolecular Engineering, B323/D322 Iacocca Hall, 111 Research Drive, Bethlehem, PA 18015, USA
| | - Stephen J. Martino
- Monmouth-Ocean Neurology, 1944 State Route 33, Suite 206, Neptune, NJ 07753, USA
| | - Adam J. Simon
- Cerora Inc., 116 Research Drive, Bethlehem, PA 18015, USA
| |
Collapse
|
15
|
Cassani R, Estarellas M, San-Martin R, Fraga FJ, Falk TH. Systematic Review on Resting-State EEG for Alzheimer's Disease Diagnosis and Progression Assessment. DISEASE MARKERS 2018; 2018:5174815. [PMID: 30405860 PMCID: PMC6200063 DOI: 10.1155/2018/5174815] [Citation(s) in RCA: 147] [Impact Index Per Article: 24.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/20/2018] [Revised: 07/12/2018] [Accepted: 07/29/2018] [Indexed: 12/17/2022]
Abstract
Alzheimer's disease (AD) is a neurodegenerative disorder that accounts for nearly 70% of the more than 46 million dementia cases estimated worldwide. Although there is no cure for AD, early diagnosis and an accurate characterization of the disease progression can improve the quality of life of AD patients and their caregivers. Currently, AD diagnosis is carried out using standardized mental status examinations, which are commonly assisted by expensive neuroimaging scans and invasive laboratory tests, thus rendering the diagnosis time consuming and costly. Notwithstanding, over the last decade, electroencephalography (EEG) has emerged as a noninvasive alternative technique for the study of AD, competing with more expensive neuroimaging tools, such as MRI and PET. This paper reports on the results of a systematic review on the utilization of resting-state EEG signals for AD diagnosis and progression assessment. Recent journal articles obtained from four major bibliographic databases were analyzed. A total of 112 journal articles published from January 2010 to February 2018 were meticulously reviewed, and relevant aspects of these papers were compared across articles to provide a general overview of the research on this noninvasive AD diagnosis technique. Finally, recommendations for future studies with resting-state EEG were presented to improve and facilitate the knowledge transfer among research groups.
Collapse
Affiliation(s)
- Raymundo Cassani
- Institut national de la recherche scientifique (INRS-EMT), University of Québec, Montreal, Canada
| | - Mar Estarellas
- Institut national de la recherche scientifique (INRS-EMT), University of Québec, Montreal, Canada
- Department of Bioengineering, Imperial College London, London, UK
| | - Rodrigo San-Martin
- Center for Mathematics, Computation and Cognition, Universidade Federal do ABC, São Bernardo do Campo, Brazil
| | - Francisco J. Fraga
- Engineering, Modeling and Applied Social Sciences Center, Universidade Federal do ABC, São Bernardo do Campo, Brazil
| | - Tiago H. Falk
- Institut national de la recherche scientifique (INRS-EMT), University of Québec, Montreal, Canada
| |
Collapse
|
16
|
Yin Y, Sun K, He S. Multiscale permutation Rényi entropy and its application for EEG signals. PLoS One 2018; 13:e0202558. [PMID: 30180194 PMCID: PMC6122795 DOI: 10.1371/journal.pone.0202558] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2017] [Accepted: 08/06/2018] [Indexed: 11/18/2022] Open
Abstract
There is considerable interest in analyzing the complexity of electroencephalography (EEG) signals. However, some traditional complexity measure algorithms only quantify the complexities of signals, but cannot discriminate different signals very well. To analyze the complexity of epileptic EEG signals better, a new multiscale permutation Rényi entropy (MPEr) algorithm is proposed. In this algorithm, the coarse-grained procedure is introduced by using weighting-averaging method, and the weighted factors are determined by analyzing nonlinear signals. We apply the new algorithm to analyze epileptic EEG signals. The experimental results show that MPEr algorithm has good performance for discriminating different EEG signals. Compared with permutation Rényi entropy (PEr) and multiscale permutation entropy (MPE), MPEr distinguishes different EEG signals successfully. The proposed MPEr algorithm is effective and has good applications prospects in EEG signals analysis.
Collapse
Affiliation(s)
- Yinghuang Yin
- School of Physics and Electronics, Central South University, Changsha, P.R.China
| | - Kehui Sun
- School of Physics and Electronics, Central South University, Changsha, P.R.China
- * E-mail:
| | - Shaobo He
- School of Computer Science and Technology, Hunan University of Arts and Science, Changde, P.R.China
| |
Collapse
|
17
|
Abstract
Alzheimer's disease (AD), a cognitive disability is analysed using a long range dependence parameter, hurst exponent (HE), calculated based on the time domain analysis of the measured electrical activity of brain. The electroencephalogram (EEG) signals of controls and mild cognitive impairment (MCI)-AD patients are evaluated under normal resting and mental arithmetic conditions. Simultaneous low pass filtering and total variation denoising algorithm is employed for preprocessing. Larger values of HE observed in the right hemisphere of the brain for AD patients indicated a decrease in irregularity of the EEG signal under cognitive task conditions. Correlations between HE and the neuropsychological indices are analysed using bivariate correlation analysis. The observed reduction in the values of Auto mutual information and cross mutual information in the local antero-frontal and distant regions in the brain hemisphere indicates the loss of information transmission in MCI-AD patients.
Collapse
|
18
|
Bachmann M, Päeske L, Kalev K, Aarma K, Lehtmets A, Ööpik P, Lass J, Hinrikus H. Methods for classifying depression in single channel EEG using linear and nonlinear signal analysis. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2018; 155:11-17. [PMID: 29512491 DOI: 10.1016/j.cmpb.2017.11.023] [Citation(s) in RCA: 81] [Impact Index Per Article: 13.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/24/2016] [Revised: 11/14/2017] [Accepted: 11/24/2017] [Indexed: 05/14/2023]
Abstract
BACKGROUND AND OBJECTIVE Depressive disorder is one of the leading causes of burden of disease today and it is presumed to take the first place in the world in 2030. Early detection of depression requires a patient-friendly inexpensive method based on easily measurable objective indicators. This study aims to compare various single-channel electroencephalographic (EEG) measures in application for detection of depression. METHODS The EEG recordings were performed on a group of 13 medication-free depressive outpatients and 13 gender and age matched controls. The recorded 30-channel EEG signal was analysed using linear methods spectral asymmetry index, alpha power variability and relative gamma power and nonlinear methods Higuchi's fractal dimension, detrended fluctuation analysis and Lempel-Ziv complexity. Classification accuracy between depressive and control subjects was calculated using logistic regression analysis with leave-one-out cross-validation. Calculations were performed separately for each EEG channel. RESULTS All calculated measures indicated increase with depression. Maximal testing accuracy using a single measure was 81% for linear and 77% for nonlinear measures. Combination of two linear measures provides the accuracy of 88% and two nonlinear measures of 85%. Maximal classification accuracy of 92% was indicated using mixed combination of three linear and three nonlinear measures. CONCLUSIONS The results of this preliminary study confirm that single-channel EEG analysis, employing the combination of measures, can provide discrimination of depression at the level of multichannel EEG analysis. The performed study shows that there is no single superior measure for detection of depression.
Collapse
Affiliation(s)
- Maie Bachmann
- Centre for Biomedical Engineering, Department of Health Technologies, Tallinn University of Technology, Ehitajate tee 5, Tallinn 19086, Estonia.
| | - Laura Päeske
- Centre for Biomedical Engineering, Department of Health Technologies, Tallinn University of Technology, Ehitajate tee 5, Tallinn 19086, Estonia
| | - Kaia Kalev
- Centre for Biomedical Engineering, Department of Health Technologies, Tallinn University of Technology, Ehitajate tee 5, Tallinn 19086, Estonia
| | - Katrin Aarma
- Centre for Biomedical Engineering, Department of Health Technologies, Tallinn University of Technology, Ehitajate tee 5, Tallinn 19086, Estonia
| | - Andres Lehtmets
- Psychiatric Centre, West Tallinn Central Hospital, Paldiski mnt 68, Tallinn 10617, Estonia
| | - Pille Ööpik
- Ädala Family Medicine Center, Madara tn 29, Tallinn 10612, Estonia; Department of Family Medicine, University of Tartu, Ülikooli 18, Tartu 50090, Estonia
| | - Jaanus Lass
- Centre for Biomedical Engineering, Department of Health Technologies, Tallinn University of Technology, Ehitajate tee 5, Tallinn 19086, Estonia
| | - Hiie Hinrikus
- Centre for Biomedical Engineering, Department of Health Technologies, Tallinn University of Technology, Ehitajate tee 5, Tallinn 19086, Estonia
| |
Collapse
|
19
|
Nimmy John T, D Puthankattil S, Menon R. Analysis of long range dependence in the EEG signals of Alzheimer patients. Cogn Neurodyn 2018; 12:183-199. [PMID: 29564027 DOI: 10.1007/s11571-017-9467-8] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2017] [Revised: 11/14/2017] [Accepted: 12/19/2017] [Indexed: 11/28/2022] Open
Abstract
Alzheimer's disease (AD), a cognitive disability is analysed using a long range dependence parameter, hurst exponent (HE), calculated based on the time domain analysis of the measured electrical activity of brain. The electroencephalogram (EEG) signals of controls and mild cognitive impairment (MCI)-AD patients are evaluated under normal resting and mental arithmetic conditions. Simultaneous low pass filtering and total variation denoising algorithm is employed for preprocessing. Larger values of HE observed in the right hemisphere of the brain for AD patients indicated a decrease in irregularity of the EEG signal under cognitive task conditions. Correlations between HE and the neuropsychological indices are analysed using bivariate correlation analysis. The observed reduction in the values of Auto mutual information and cross mutual information in the local antero-frontal and distant regions in the brain hemisphere indicates the loss of information transmission in MCI-AD patients.
Collapse
Affiliation(s)
- T Nimmy John
- 1Department of Electrical Engineering, National Institute of Technology Calicut, Kozhikode, India
| | - Subha D Puthankattil
- 1Department of Electrical Engineering, National Institute of Technology Calicut, Kozhikode, India
| | - Ramshekhar Menon
- 2Department of Neurology, Sree Chitra Tirunal Institute for Medical Sciences and Technology, Thiruvananthapuram, India
| |
Collapse
|
20
|
The research of constructing dynamic cognition model based on brain network. Saudi J Biol Sci 2017; 24:548-555. [PMID: 28386179 PMCID: PMC5372456 DOI: 10.1016/j.sjbs.2017.01.025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2016] [Revised: 01/05/2017] [Accepted: 01/09/2017] [Indexed: 11/24/2022] Open
Abstract
Estimating the functional interactions and connections between brain regions to corresponding process in cognitive, behavioral and psychiatric domains is a central pursuit for understanding the human connectome. Few studies have examined the effects of dynamic evolution on cognitive processing and brain activation using brain network model in scalp electroencephalography (EEG) data. Aim of this study was to investigate the brain functional connectivity and construct dynamic programing model from EEG data and to evaluate a possible correlation between topological characteristics of the brain connectivity and cognitive evolution processing. Here, functional connectivity between brain regions is defined as the statistical dependence between EEG signals in different brain areas and is typically determined by calculating the relationship between regional time series using wavelet coherence. We present an accelerated dynamic programing algorithm to construct dynamic cognitive model that we found that spatially distributed regions coherence connection difference, the topologic characteristics with which they can transfer information, producing temporary network states. Our findings suggest that brain dynamics give rise to variations in complex network properties over time after variation audio stimulation, dynamic programing model gives the dynamic evolution processing at different time and frequency. In this paper, by applying a new construct approach to understand whole brain network dynamics, firstly, brain network is constructed by wavelet coherence, secondly, different time active brain regions are selected by network topological characteristics and minimum spanning tree. Finally, dynamic evolution model is constructed to understand cognitive process by dynamic programing algorithm, this model is applied to the auditory experiment, results showed that, quantitatively, more correlation was observed after variation audio stimulation, the EEG function connection dynamic evolution model on cognitive processing is feasible with wavelet coherence EEG recording.
Collapse
|