An explainable Artificial Intelligence approach to study MCI to AD conversion via HD-EEG processing

Abstract

An explainable Artificial Intelligence (xAI) approach is proposed to longitudinally monitor subjects affected by Mild Cognitive Impairment (MCI) by using high-density electroencephalography (HD-EEG). To this end, a group of MCI patients was enrolled at IRCCS Centro Neurolesi Bonino Pulejo of Messina (Italy) within a follow-up protocol that included two evaluations steps: T0 (first evaluation) and T1 (three months later). At T1, four MCI patients converted to Alzheimer’s Disease (AD) and were included in the analysis as the goal of this work was to use xAI to detect individual changes in EEGs possibly related to the degeneration from MCI to AD. The proposed methodology consists in mapping segments of HD-EEG into channel-frequency maps by means of the power spectral density. Such maps are used as input to a Convolutional Neural Network (CNN), trained to label the maps as “T0” (MCI state) or “T1” (AD state). Experimental results reported high intra-subject classification performance (accuracy rate up to 98.97% (95% confidence interval: 98.68–99.26)). Subsequently, the explainability of the proposed CNN is explored via a Grad-CAM approach. The procedure detected which EEG-channels (i.e., head region) and range of frequencies (i.e., sub-bands) were more active in the progression to AD. The xAI analysis showed that the main information is included in the delta sub-band and that, limited to the analyzed dataset, the highest relevant areas are: the left-temporal and central-frontal lobe for Sb01, the parietal lobe for Sb02, the left-frontal lobe for Sb03 and the left-frontotemporal region for Sb04.

Keywords

High-Density Electroencephalography Mild Cognitive Impairment Alzheimer’s Disease Convolutional Neural Network explainable Artificial Intelligence

Get full access to this article

View all access options for this article.

References

Sperling

Aisen

Beckett

et al. Toward Defining the Preclinical Stages of Alzheimer’s Disease: Ecommendations From the National Institute on Aging-Alzheimer’s Association Workgroups on Diagnostic Guidelines for Alzheimer’s Disease. Alzheimer’s Dementia 2011;7(3):280-292.

Jeong

. EEG Dynamics in Patients with Alzheimer’s Disease. Clinical Neurophysiol 2004;115(7):1490-1505.

Nunez

Srinivasan

. Electric fields of the brain: the neurophysics of EEG. Oxford University Press, USA, 2006.

Aghajani

Zahedi

Jalili

et al. . Diagnosis of Early Alzheimer’s Disease Based on EEG Source Localization and a Standardized Realistic Head Model. IEEE J Biomed Health Inform 2013;17(6):1039-1045.

Dubovik

Bouzerda-Wahlen

Nahum

et al. Adaptive Reorganization of Cortical Networks in Alzheimer’s Disease. Clin Neurophysiol 2013;123(1):35-43.

Mammone

De Salvo

Bonanno

et al. Brain Network Analysis of Compressive Sensed High-density EEG Signals in AD and MCI Subjects. IEEE T Ind Inform 2018;15(1):527-536.

Huang

Wahlund

Dierks

et al. Discrimination of Alzheimer’s Disease and Mild Cognitive Impairment by Equivalent EEG Sources: a Cross-sectional and Longitudinal Study. Clin Neurophysiol 2000;111(11):1961-1967.

Jelic

Johansson

Almkvist

et al. Quantitative Electroencephalography in Mild Cognitive Impairment: Longitudinal Changes and Possible Prediction of Alzheimer’s Disease. Neurobiol Aging 2000;21(4):533-540.

Moretti

Frisoni

Fracassi

et al. MCI Patients’ EEGs Show Group Differences Between those Who Progress and those Who Do Not Progress to AD. Neurobiol Aging 2011;32(4):563-571.

10.

Luckhaus

Grass-Kapanke

Blaeser

et al. Quantitative EEG in Progressing Vs Stable Mild Cognitive Impairment (MCI): Results of a 1-year Follow-up Study. Inter J Geriatr Psychiat: A J Psychiat Late Life Allied Sci 2008;23(11):1148-115.

11.

Morabito

Campolo

Labate

et al. A Longitudinal EEG Study of Alzheimer’s Disease Progression Based on a Complex Network Approach. Intern J Neural Syste 2015;25(02):1550005.

12.

Mammone

De Salvo

Ieracitano

et al. A Permutation Disalignment Index-based Complex Network Approach to Evaluate Longitudinal Changes in Brain-electrical Connectivity. Entropy 2017;19(10):548.

13.

Mammone

Ieracitano

Adeli

et al. . Permutation Jaccard Distance-based Hierarchical Clustering to Estimate EEG Network Density Modifications in MCI Subjects. IEEE T Neural Networks Learning Syst 2018;29(10):5122-5134.

14.

Dattola

La Foresta

. An ELORETA Longitudinal Analysis of Resting State EEG Rhythms in Alzheimer’s Disease. Appl Sci 2020;10(16):5666.

15.

Şeker

Özbek

Yener

Özerdem

. Complexity of EEG Dynamics for Early Diagnosis of Alzheimer’s Disease Using Permutation Entropy Neuromarker. Compu Meth Progra Bio 2021;206:106116.

16.

Huggins

Escudero

Parra

et al. Deep Learning of Resting-state Electroencephalogram Signals for 3-class Classification of Alzheimer’s Disease, Mild Cognitive Impairment and Healthy Ageing. J Neural Eng 2021; (): –.

17.

Toural

JES

Pedrón

Reyes

EJM

. A New Method for Classification of Subjects with Major Cognitive Disorder, Alzheimer Type, Based on Electroencephalographic Biomarkers. Inform Med Unlocked 2021;23:100537.

18.

Ieracitano

Mammone

Bramanti

et al. . A Convolutional Neural Network Approach for Classification of Dementia Stages Based on 2D-spectral Representation of EEG Recordings. Neurocomputing 2019;323:96-107.

19.

Morabito

Campolo

Ieracitano

et al. Deep convolutional neural networks for classification of mild cognitive impaired and Alzheimer’s disease patients from scalp EEG recordings. in 2016 IEEE 2nd International Forum on Research and Technologies for Society and Industry Leveraging a better tomorrow (RTSI):1–6IEEE, 2016.

20.

Ieracitano

Mammone

Hussain

et al. . A Novel Multi-modal Machine Learning Based Approach for Automatic Classification of EEG Recordings in Dementia. Neural Networks 2020;123:176-190.

21.

Edition

. Diagnostic and Statistical Manual of Mental Disorders. Am Psychiatric Assoc 2013;21.

22.

Kayser

Tenke

. On the Benefits of Using Surface Laplacian (current Source Density) Methodology in Electrophysiology. Intern J Psychophysiol 2015;97(3):171.

23.

Heinzel

Rüdiger

Schilling

, Spectrum and spectral density estimation by the Discrete Fourier transform (DFT), including a comprehensive list of window functions and some new at-top windows, 2002.

24.

Yan

Yoshua

Geoffrey

. Deep Learning. Nature 2015;521(7553):436-444.

25.

Krizhevsky

Sutskever

Hinton

. Imagenet Classification with Deep Convolutional Neural Networks. Adv Neural Inform Proc Syst 2012;25:1097-1105.

26.

Holzinger

Malle

Saranti

et al. . Towards Multi-modal Causability with Graph Neural Networks Enabling Information Fusion for Explainable AI. Inform Fusion 2021;71:28-37.

27.

Selvaraju

Cogswell

Das

et al. . Grad-cam: Visual explanations from deep networks via gradient-based localization. in Proceedings of the IEEE international conference on computer vision:618–626, 2017.

28.

Hazra

. Using the Confidence Interval Confidently. Thoracic Disease 2017;9(10):4125.

29.

Bian

Wang

et al. . Relative Power and Coherence of EEG Series are Related to Amnestic Mild Cognitive Impairment in Diabetes. Frontiers Aging Neurosci 2014;6:11.

30.

Mammone

De Salvo

Ieracitano

et al. Compressibility of High-Density EEG Signals in Stroke Patients. Sensors 2018;18(12):4107.