Abstract
Mild cognitive impairment (MCI) is a neuropsychological syndrome that is characterized by cognitive impairments. It typically affects adults 60 years of age and older. It is a noticeable decline in the cognitive function of the patient, and if left untreated it gets converted to Alzheimer’s disease (AD). For that reason, early diagnosis of MCI is important as it slows down the conversion of the disease to AD. Early and accurate diagnosis of MCI requires recognition of the clinical characteristics of the disease, extensive testing, and long-term observations. These observations and tests can be subjective, expensive, incomplete, or inaccurate. Electroencephalography (EEG) is a powerful choice for the diagnosis of diseases with its advantages such as being non-invasive, based on findings, less costly, and getting results in a short time. In this study, a new EEG-based model is developed which can effectively detect MCI patients with higher accuracy. For this purpose, a dataset consisting of EEG signals recorded from a total of 34 subjects, 18 of whom were MCI and 16 control groups was used, and their ages ranged from 40 to 77. To conduct the experiment, the EEG signals were denoised using Multiscale Principal Component Analysis (MSPCA), and to increase the size of the dataset Data Augmentation (DA) method was performed. The tenfold cross-validation method was used to validate the model, moreover, the power spectral density (PSD) of the EEG signals was extracted from the EEG signals using three spectral analysis methods, the periodogram, welch, and multitaper. The PSD graphs of the EEG signals showed signal differences between the subjects of control and the MCI group, indicating that the signal power of MCI patients is lower compared to control groups. To classify the subjects, one of the best classifiers of deep learning algorithms called the Bi-directional long-short-term-memory (Bi-LSTM) was used, and several machine learning algorithms, such as decision tree (DT), support vector machine (SVM), and k-nearest neighbor (KNN). These algorithms were trained and tested using the extracted feature vectors from the control and the MCI groups. Additionally, the values of the coefficient matrix of those algorithms were compared and evaluated with the performance evaluation matrix to determine which one performed the best overall. According to the experimental results, the proposed deep learning model of multitaper spectral analysis approach with Bi-LSTM deep learning algorithm attained the highest number of correctly classified samples for diagnosing MCI patients and achieved a remarkable accuracy compared to the other proposed models. The achieved classification results of the deep learning model are reported to be 98.97% accuracy, 98.34% sensitivity, 99.67% specificity, 99.70% precision, 99.02% f1 score, and 97.94% Matthews correlation coefficient (MCC).
Similar content being viewed by others
Data availability
The EEG signals are taken from a publicly available dataset. The dataset was downloaded from “https://misp.mui.ac.ir/fa/eeg-data”.
References
Alden EC, Pudumjee SB, Lundt ES, Albertson SM, Machulda MM, Kremers WK, Knopman DS, Petersen RC, Mielke MM, Stricker NH (2021) Diagnostic accuracy of the Cogstate Brief Battery for prevalent MCI and prodromal AD (MCI A+ T+) in a population-based sample. Alzh Demen 17:584–94. https://doi.org/10.1002/alz.12219
Altan A, Karasu S (2020) Recognition of COVID-19 disease from X-ray images by hybrid model consisting of 2D curvelet transform, chaotic salp swarm algorithm and deep learning technique. Chao Solit Fract 140:110071. https://doi.org/10.1016/j.chaos.2020.110071
Alvi AM, Siuly S, Wang H (2022a) A long short-term memory based framework for early detection of mild cognitive impairment from EEG signals. IEEE Trans Emerg Top Comp Intell. https://doi.org/10.1109/TETCI.2022.3186180
Alvi AM, Siuly S, Wang H, Wang K, Whittaker F (2022b) A deep learning based framework for diagnosis of mild cognitive impairment. Knowl Based Syst 248:108815. https://doi.org/10.1016/j.knosys.2022.108815
Ashok P, Jackermeier M, Jagtap P, Křetínský J, Weininger M, Zamani M (2020) dtControl: decision tree learning algorithms for controller representation. In Proceedings of the 23rd international conference on hybrid systems: computing and controling DOI: https://doi.org/10.1145/3365365.3382220
Bai X (2018) Text classification based on LSTM and attention. In 2018 Thirteenth Internatioal Conference on Digital Information and Management (ICDIM) IEEE DOI: https://doi.org/10.1109/ICDIM.2018.8847061
Barrow D K, Crone S F (2013) Crogging (cross-validation aggregation) for forecasting—a novel algorithm of neural network ensembles on time series subsamples. In 2013 International joint conference on neural network (IJCNN) IEEE DOI: https://doi.org/10.1109/IJCNN.2013.6706740
Bastos NS, Marques BP, Adamatti DF, Billa CZ (2020) Analyzing EEG signals using decision trees: a study of modulation of amplitude. Comput Intell Neuroscie. https://doi.org/10.1155/2020/3598416
Battineni G, Sagaro GG, Chinatalapudi N, Amenta F (2020) Applications of machine learning predictive models in the chronic disease diagnosis. J Pers Med 10:21. https://doi.org/10.3390/jpm10020021
Candy J V (2019) Multitaper spectral estimation: an alternative to the welch periodogram approach. Lawrence Livermore Nation Lab. (LLNL). https://www.osti.gov/servlets/purl/1560107. Accessed 13 January 2023
Chaiyapong A, Wattatham S, Sakolnakorn TPN (2023) The methods and challenges of managing a smart health program during the COVID-19 pandemic in Thailand. Int J Interdisc Glob Stud 18:99. https://doi.org/10.18848/2324-755X/CGP/v18i02/99-114
Chan JY, Yau ST, Kwok TC, Tsoi KK (2021) Diagnostic performance of digital cognitive tests for the identification of MCI and dementia: a systematic review. Ageing Res Rev 72:101506. https://doi.org/10.1016/j.arr.2021.101506
Chandrasekar A, Rakkiyappan R, Cao J, Lakshmanan S (2014) Synchronization of memristor-based recurrent neural networks with two delay components based on second-order reciprocally convex approach. Neur Netw 57:79–93. https://doi.org/10.1016/j.neunet.2014.06.001
Chandrasekar A, Radhika T, Zhu Q (2022) Further results on input-to-state stability of stochastic Cohen-Grossberg BAM neural networks with probabilistic time-varying delays. Neur Proc Lett 56:1–23. https://doi.org/10.1007/s11063-021-10649-w
Chandrasekar A, Radhika T, Zhu Q (2022) State estimation for genetic regulatory networks with two delay components by using second-order reciprocally convex approach. Neur Proc Lett 21:1–19. https://doi.org/10.1007/s11063-021-10633-4
Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Elect Eng 40:16–28. https://doi.org/10.1016/j.compeleceng.2013.11.024
Chiang HS, Sangaiah AK, Chen MY, Liu JY (2020) A novel artificial bee colony optimization algorithm with SVM for bio-inspired software-defined networking. Int J Parall Prog 48:310–328. https://doi.org/10.1007/s10766-018-0594-6
Daş B (2020) A comparative study on the performance of classification algorithms for effective diagnosis of liver diseases. Sak Univ J Com Infor Scien 3:366–75. https://doi.org/10.35377/saucis.03.03.815556
Das P, Babadi B (2020) Multitaper spectral analysis of neuronal spiking activity driven by latent stationary processes. Sign Process 170:107429. https://doi.org/10.1016/j.sigpro.2019.107429
Das S, Subba Rao S, Yang J (2021) Spectral methods for small sample time series: a complete periodogram approach. J Time Ser Anal 42:597–621. https://doi.org/10.1111/jtsa.12584
Deng Z, Zhu X, Cheng D, Zong M, Zhang S (2016) Efficient kNN classification algorithm for big data. Neurocomput 195:143–148. https://doi.org/10.1016/j.neucom.2015.08.112
Dileep P, Rao KN, Bodapati P, Gokuruboyina S, Peddi R, Grover A, Sheetal A (2023) An automatic heart disease prediction using cluster-based bi-directional LSTM (C-BiLSTM) algorithm. Neur Comp Appl 35:7253–7266. https://doi.org/10.1007/s00521-022-07064-0
Forouzannezhad P, Abbaspour A, Li C, Fang C, Williams U, Cabrerizo M, Barreto A, Andrian J, Rishe N, Curiel RE, Loewenstein D, Duara R, Adjouadiad M, Adjouadi M (2020) A Gaussian-based model for early detection of mild cognitive impairment using multimodal neuroimaging. J of Neurosci Methods 333:108544. https://doi.org/10.1016/j.jneumeth.2019.108544
Ganaie MA, Tanveer M, Jangir J (2023) EEG signal classification via pinball universum twin support vector machine. Ann Oper Res 328:451–492. https://doi.org/10.1007/s10479-022-04922-x
Geng D, Wang C, Fu Z, Zhang Y, Yang K, An H (2022) Sleep EEG-based approach to detect mild cognitive impairment. Front Aging Neurosci 14:865558. https://doi.org/10.3389/fnagi.2022.865558
Greff K, Srivastava RK, Koutník J, Steunebrink BR, Schmidhuber J (2016) LSTM: a search space odyssey. IEEE Transac Neural Netw Learn Syst 28:2222–2232. https://doi.org/10.1109/TNNLS.2016.2582924
Güneç K, Kasim Ö, Tosun M, Büyükköroğlu E (2021) Estimation of pain threshold from EEG signals of subjects in physical therapy using long-short-term memory deep learning model. Uludağ Univ J Facul Eng 26:447–460. https://doi.org/10.17482/uumfd.883100
Guo H, Zhang Y (2020) Resting state fMRI and improved deep learning algorithm for earlier detection of Alzheimer’s disease. IEEE Access 8:115383–115392. https://doi.org/10.1109/ACCESS.2020.3003424
Hadiyoso S, Tati L E (2018) Mild Cognitive Impairment Classification using Hjorth Descriptor Based on EEG Signal. In: 2018 international conference on control, electronics, renewable energy and communication (ICCEREC), IEEE DOI: https://doi.org/10.1109/ICCEREC.2018.8712095
Hadiyoso S, Cynthia C, Zakaria H (2019) Early detection of mild cognitive impairment using quantitative analysis of EEG signals. In 2019 2nd International conference on bioinformatics, biotechnology and biomedical engineering (BioMIC)-bioinformatics and biomedical engineering. IEEE DOI: https://doi.org/10.1109/BioMIC48413.2019.9034892
Hazra S, Pratap AA, Agrawal O, Nandy A (2021) On effective cognitive state classification using novel feature extraction strategies. Cognit Neurodyn 15:1125–1155. https://doi.org/10.1007/s11571-021-09688-9
Houssein EH, Hammad A, Ali AA (2022) Human emotion recognition from EEG-based brain–computer interface using machine learning: a comprehensive review. Neur Comput Appl 34:12527–12557. https://doi.org/10.1007/s00521-022-07292-4
Hsiao YT, Wu CT, Tsai CF, Liu YH, Trinh TT, Lee CY (2021b) EEG-based classification between individuals with mild cognitive impairment and healthy controls using conformal kernel-based fuzzy support vector machine. Int J Fuzzy Syst 23:2432–2448. https://doi.org/10.1007/s40815-021-01186-8
Hsiao YT, Tsai CF, Wu CT, Trinh TT, Lee CY, Liu YH (2021) MCI detection using kernel eigen-relative-power features of EEG signals. In: Actuators. MDPI DOI: https://doi.org/10.3390/act10070152
Jamaloo F, Mikaeili M, Noroozian M (2020) Multi metric functional connectivity analysis based on continuous hidden Markov model with application in early diagnosis of Alzheimer’s disease. Biomed Signal Process Control 61:102056. https://doi.org/10.1016/j.bspc.2020.102056
Javaid H, Manor R, Kumarnsit E, Chatpun S (2021) Decision tree in working memory task effectively characterizes EEG signals in healthy aging adults. IRBM 43:705–714. https://doi.org/10.1016/j.irbm.2021.12.001
Kashefpoor M, Rabbani H, Barekatain M (2016) Automatic diagnosis of mild cognitive impairment using electroencephalogram spectral features. J Med Sign Sens 6:25
Kashefpoor M, Rabbani H, Barekatain M (2019) Supervised dictionary learning of EEG signals for mild cognitive impairment diagnosis. Biomed Signal Process Control 53:101559. https://doi.org/10.1016/j.bspc.2019.101559
Kasper S, Bancher C, Eckert A, Förstl H, Frslich L, Hort J, Korczyn AD, Kressig RW, Levin O, Palomo MSM (2020) Management of mild cognitive impairment (MCI): the need for national and international guidelines. World J Biol Psychiat 21:579–594. https://doi.org/10.1080/15622975.2019.1696473
Kevric J, Subasi A (2014) The effect of multiscale PCA de-noising in epileptic seizure detection. J Med Syst 38:1–13. https://doi.org/10.1007/s10916-014-0131-0
Khatun S, Morshed BI, Bidelman GM (2019) A single-channel EEG-based approach to detect mild cognitive impairment via speech-evoked brain responses. IEEE Transac Neural Syst Rehab Eng 27:1063–1070. https://doi.org/10.1109/TNSRE.2019.2911970
Lan H, White PR, Li N, Li J, Sun D (2020) Coherently averaged power spectral estimate for signal detection. Signal Process 169:107414. https://doi.org/10.1016/j.sigpro.2019.107414
Lashgari E, Liang D, Maoz U (2020) Data augmentation for deep-learning-based electroencephalography. J Neurosci Methods 346:108885. https://doi.org/10.1016/j.jneumeth.2020.108885
Li YH, Harfiya LN, Purwandari K, Lin YD (2020) Real-time cuffless continuous blood pressure estimation using deep learning model. Sens 20:5606. https://doi.org/10.3390/s20195606
Li Q, Cheng R, Ge H (2023) Short-term vehicle speed prediction based on BiLSTM-GRU model considering driver heterogeneity. Physica A 610:128410
Liu G, Guo J (2019) Bidirectional LSTM with attention mechanism and convolutional layer for text classification. Neurocomput 337:325–338. https://doi.org/10.1016/j.neucom.2019.01.078
Lombardi G, Crescioli G, Cavedo E, Lucenteforte E, Casazza G, Bellatorre AG, Lista C, Costantino G, Frisoni G, Virgili G, Filippini G (2020) Structural magnetic resonance imaging for the early diagnosis of dementia due to Alzheimer’s disease in people with mild cognitive impairment. Cochrane Datab Syst Rev. https://doi.org/10.1002/14651858.CD009628.pub2
Lu Y, Liu C, Yu D, Fawkes S, Ma J, Zhang M, Li C (2021) Prevalence of mild cognitive impairment in community-dwelling Chinese populations aged over 55 years: a meta-analysis and systematic review. BMC Geriatr 21:1–16. https://doi.org/10.1186/s12877-020-01948-3
Madhyastha T (2023). Neuroimaging workflows in the cloud. https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Madhyastha+T+%282023%29.+Neuroimaging+workflows+in+the+cloud.&btnG= Accessed 18 August 2023
Mahmood U, Fu Z, Calhoun V, Plis S (2023). Glacier: glass-box transformer for interpretable dynamic neuroimaging. In ICASSP 2023–2023 IEEE International Conference on Acoustics, and Signal Process (ICASSP) IEEE, pp. 1–5 DOI: https://doi.org/10.1109/ICASSP49357.2023.10097126
Ng WB, Saidatul A, Chong YF, Ibrahim Z (2019) PSD-based features extraction for EEG signal during typing task. In IOP conference in series: materials science and engineering. IOP publishing. https://doi.org/10.1088/1757-899X/557/1/012032
Özçelik YB, Altan A (2023) Classification of diabetic retinopathy by machine learning algorithm using entorpy-based features. https://www.izdas.org/cankaya Accessed 1 September 2023
Rabcan J, Levashenko V, Zaitseva E, Kvassay M (2021) EEG signal classification based on fuzzy classifiers. IEEE Trans Industr Inf 18:757–766. https://doi.org/10.1109/TII.2021.3084352
Radhika T, Chandrasekar A, Vijayakumar V, Zhu Q (2023) Analysis of markovian jump stochastic cohen-grossberg bam neural networks with time delays for exponential input-to-state stability. Neur Process Lett 64:1–18. https://doi.org/10.1007/s11063-023-11364-4
Rahmat R F., Faza S, Adnan S, Situmorang D T E, Gunawan D, Lini T Z (2021) News articles classification for electronic information and transaction law in indonesia using support vector machine. In 2021 International Conference on Data Science, Artificial Intelligence, and Business Analytics (DATABIA) IEEE DOI: https://doi.org/10.1109/DATABIA53375.2021.9650285
Rakkiyappan R, Chandrasekar A, Cao J (2014) Passivity and passification of memristor-based recurrent neural networks with additive time-varying delays. IEEE Transac Neur Netw Learn Syst 26:2043–2057. https://doi.org/10.1109/TNNLS.2014.2365059
Rivera MJ, Teruel MA, Mate A, Trujillo J (2022) Diagnosis and prognosis of mental disorders by means of EEG and deep learning: a systematic mapping study. Artif Intell Rev 56:1–43. https://doi.org/10.1007/s10462-021-09986-y
Sakai A, Minoda Y, Morikawa K (2017) Data augmentation methods for machine-learning-based classification of bio-signals. In Procedings of the 10th Biomedical and Engineering in International Conference: IEEE DOI: https://doi.org/10.1109/BMEiCON.2017.8229109
Siami-Namini S, Tavakoli N, Namin AS (2019) The performance of LSTM and BiLSTM in forecasting time series. In 2019 IEEE international conference on big data (big data) DOI: https://doi.org/10.1109/BigData47090.2019.9005997
Siuly S, Alçin ÖF, Kabir E, Şengür A, Wang H, Zhang Y, Whittaker F (2020) A new framework for automatic detection of patients with mild cognitive impairment using resting-state EEG signals. IEEE Transact Neur Syst Rehabilitat Eng 28:1966–1976. https://doi.org/10.1109/TNSRE.2020.3013429
Soori M, Arezoo B, Dastres R (2023) Artificial intelligence, machine learning and deep learning in advanced robotics, a review. Cogn Robot. https://doi.org/10.1016/j.cogr.2023.04.0013
Tamil Thendral M, Ganesh Babu TR, Chandrasekar A, Cao Y (2022) Synchronization of Markovian jump neural networks for sampled data control systems with additive delay components: analysis of image encryption technique. Math Meth Appl Scien. https://doi.org/10.1002/mma.8774
Theodosiou AA, Read RC (2023) Artificial intelligence, machine learning and deep learning: potential resources for the infection clinician. J Infec 7:6. https://doi.org/10.1016/j.jinf.2023.07.006
Trauth MH (2021) Spectral analysis in quaternary sciences. Quatern Sci Rev 270:107157. https://doi.org/10.1016/j.quascirev.2021.107157
Van Vugt MK, Sederberg PB, Kahana MJ (2007) Comparison of spectral analysis methods for characterizing brain oscillations. J Neurosc Meth 162:49–63. https://doi.org/10.1152/physiol.00062.2015
Vu HL, Ng KTW, Richter A, An C (2022) Analysis of input set characteristics and variances on k-fold cross validation for a recurrent neural network model on waste disposal rate estimation. J of Environm Manag 311:114869. https://doi.org/10.1016/j.jenvman.2022.114869
Wang Q, Zeng W, Dai X (2022) Gait classification for early detection and severity rating of Parkinson’s disease based on hybrid signal processing and machine learning methods. Cognit Neurodyn 30:1–24. https://doi.org/10.1007/s11571-022-09925-9
Wang Y, Huang M, Zhu X, Zhao L (2016) Attention-based LSTM for aspect-level sentiment classification. In Proceed of the 2016 Conf on Empiric Meth in Natur Lang Process. https://aclanthology.org/D16-1058.pdf. Accessed 13 January 2023
World Health Organization (WHO) (2017) Global action plan on the public health response to dementia 2017–2025. https://apps.who.int/iris/bitstream/handle/10665/259615/?sequence=1 Accessed 13 January 2023
Xie W, She Y, Guo Q (2021) Research on multiple classification based on improved SVM algorithm for balanced binary decision tree. Sci Program 1:11. https://doi.org/10.1155/2021/5560465
Xiong Q, Zhang X, Wang WF, Gu Y (2020) A parallel algorithm framework for feature extraction of EEG signals on MPI. Comput Mathemat Methods Medic 2020. https://doi.org/10.1155/2020/9812019
Yan T, Shen SL, Zhou A, Chen X (2022) Prediction of geological characteristics from shield operational parameters by integrating grid search and K-fold cross validation into stacking classification algorithm. J Rock Mechan Geotech Eng 14:1292–1303. https://doi.org/10.1016/j.jrmge.2022.03.002
Yin J, Cao J, Siuly S, Wang H (2019) An integrated MCI detection framework based on spectral-temporal analysis. Int J Autom Comput 16:786–799. https://doi.org/10.1007/s11633-019-1197-4
Zhang S (2020) Cost-Sensitive KNN Classification. Neurocomputing 391:234–242. https://doi.org/10.1016/j.neucom.2018.11.101
Zhang S, Li X, Zong M, Zhu X, Wang R (2017) Efficient kNN classification with different numbers of nearest neighbors. IEEE Transact Neur Netw Learn Syst 29:1774–1785. https://doi.org/10.1109/TNNLS.2017.2673241
Author information
Authors and Affiliations
Contributions
A.S.: Designing conception, visualization and the data analysis of the study, writing of manuscript and revised the paper. H.G.: Conception of the study and implementation of the methods, conceived the original idea, supervised the project, and revised the paper.
Corresponding author
Ethics declarations
Conflict of interest
We explicitly state that we have no conflict of interest.
Ethical approval
This article does not contain any studies with animals or human subjects conducted by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Said, A., Göker, H. Spectral analysis and Bi-LSTM deep network-based approach in detection of mild cognitive impairment from electroencephalography signals. Cogn Neurodyn 18, 597–614 (2024). https://doi.org/10.1007/s11571-023-10010-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11571-023-10010-y