Alzheimer’s disease (AD) is considered the main cause of dementia in Western countries. Consequently, there is a need for an accurate, universal, specific and cost-effective biomarker for early AD diagnosis, to follow disease progression and therapy response. This article describes a new diagnostic approach to quantitative electroencephalogram (QEEG) diagnosis of mild and moderate AD. The data set used in this study was composed of EEG signals recorded from 2 groups: (S1) 74 normal subjects, 33 females and 41 males (mean age 67 years, standard deviation = 8) and (S2) 88 probable AD patients (NINCDS-ADRDA criteria), 55 females and 33 males (mean age 74.7 years, standard deviation = 7.8) with mild to moderate symptoms (DSM-IV-TR). Attention is given to sample size and the use of state of the art open source tools (LetsWave and WEKA) to process the EEG data. This innovative technique consists in associating Morlet wavelet filter with a support vector machine technique. A total of 111 EEG features (attributes) were obtained for 162 probands. The results were accuracy of 92.72% and area under the curve of 0.92 (percentage split test). Most important, comparing a single patient versus the total data set resulted in accuracy of 84.56% (leave-one-patient-out test). Particular emphasis was on clinical diagnosis and feasibility of implementation of this low-cost procedure, because programming knowledge is not required. Consequently, this new method can be useful to support AD diagnosis in resource-limited settings.
NitriniRBottinoCMAlbalaC. Prevalence of dementia in Latin America: a collaborative study of population-based cohorts. Int Psychogeriatr. 2009;21:622-630.
2.
LopesMABottinoCM. Prevalence of dementia in several regions of the world: analysis of epidemiologic studies from 1994 to 2000 [in Portuguese]. Arq Neuropsiquiatr. 2002;60:61-69.
3.
TerryRD. Neuropathological changes in Alzheimer disease. Prog Brain Res. 1994;101:383-390.
4.
SarazinMde SouzaLCLehéricySDuboisB. Clinical and research diagnostic criteria for Alzheimer’s disease. Neuroimaging Clin N Am. 2012;22:23-32.
5.
FonsecaLCTedrusGMLetroGHBossoniAS. Dementia, mild cognitive impairment and quantitative EEG in patients with Parkinson’s disease. Clin EEG Neurosci. 2009;40:168-172.
6.
VecchioFBabiloniC. Direction of information flow in Alzheimer’s disease and MCI patients. Int J Alzheimers Dis. 2011;2011:214580.
7.
BabiloniCLizioRVecchioF. Reactivity of cortical alpha rhythms to eye opening in mild cognitive impairment and Alzheimer’s disease: an EEG study. J Alzheimers Dis. 2010;22:1047-1064.
8.
FonsecaLCTedrusGMFondelloMAReisINFontouraDS. EEG theta and alpha reactivity on opening the eyes in the diagnosis of Alzheimer’s disease. Clin EEG Neurosci. 2011;42:185-189.
9.
HierDBMangoneCAGanellenR. Quantitative measurement of delta activity in Alzheimer’s disease. Clin Electroencephalogr. 1991;22:178-182.
10.
KnottVMohrEHacheNMahoneyCMendisT. EEG and the passive P300 in dementia of the Alzheimer type. Clin EEG Neurosci. 1999;30:64-72.
11.
FonsecaLCTedrusGMLetroGHBossoniAS. Dementia, mild cognitive impairment and quantitative EEG in patients with Parkinson’s disease. Clin EEG Neurosci. 2009;40:168-172.
12.
SandmannMCPianaERSousaDSBittencourtPR. Digital EEG with brain mapping in Alzheimer’s dementia and Parkinson’s disease. A prospective controlled study [in Portuguese]. Arq Neuropsiquiatr. 1996;54:50-56.
13.
SneddonRShankleWRHaraJRodriquezAHoffmanDSahaU. QEEG monitoring of Alzheimer’s disease treatment: a preliminary report of three case studies. Clin EEG Neurosci. 2006;37:54-59.
14.
PetrosianAAProkhorovDVLajara-NansonWSchifferRB. Recurrent neural network-based approach for early recognition of Alzheimer’s disease in EEG. Clin Neurophysiol. 2001;112:1378-1387.
15.
Symposia, Clinical EEG and Neuroscience. Clin EEG Neurosci. 2009;40:43-58.
16.
SelvamVSShenbagadeviS. Brain tumor detection using scalp EEG with modified wavelet-ICA and multi layer feed forward neural network. Conf Proc IEEE Eng Med Biol Soc. 2011;2011:6104-6109.
17.
YuanQZhouWZhangJLiSCaiDZengY. EEG classification approach based on the extreme learning machine and wavelet transform. Clin EEG Neurosci. 2012;43:127-132.
18.
LinW-C. A Case Study on Support Vector Machines Versus Artificial Neural Networks [master’s thesis]. Pittsburgh, PA: University of Pittsburgh; 2004.
LehmannCKoenigTJelicV., Application and comparison of classification algorithms for recognition of Alzheimer’s disease in electrical brain activity (EEG). J Neurosci Methods. 2007;161:342-350.
21.
MourauxARossionBHuLIannettiG. Letswave, a free EEG signal-processing toolbox. Laboratoire de neurophysiologie, Universite Catholique de Louvain, Brussels, Belgium. http://nocions.webnode.com/letswave/
22.
BouckaertRRFrankEHallMA. WEKA—experiences with a java open-source project. J Machine Learn Res. 2010;11: 2533-2541.
23.
FanRChenPLinC. Working set selection using second order information for training SVM. J Machine Learn Res. 2005;6:1889-1918.
24.
MorrisJ. The Clinical Dementia Rating (CDR): current version and scoring rules. Neurology. 1993;43(11):2412-4.
25.
BruckiSMNitriniRCaramelliPBertolucciPHOkamotoIH. Suggestions for utilization of the mini-mental state examination in Brazil [in Portuguese]. Arq Neuropsiquiatr. 2003;61(3B):777-781.
26.
McKhannGDrachmanDFolsteinMKatzmanRPriceDStadlanEM. 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;34:939-944.
27.
American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders. 4th ed (Text Revision). Washington, DC: American Psychiatric Association; 2002.
28.
WeaverJXuYHealyDCromwellL. Filtering noise from images with wavelet transforms. Magn Reson Med. 1991;21:288-295.
29.
GoupillaudPGrossmanAMorletJ. Cycle-octave and related transforms in seismic signal analysis. Geoexploration. 1984;23:85-102.
30.
FargeM. Wavelet transforms and their applications to turbulence. Annu Rev Fluid Mech. 1992;24:395-457.
31.
KempfnerJSorensenGLSorensenHBJennumP. Automatic REM sleep detection associated with idiopathic REM sleep behavior disorder. Conf Proc IEEE Eng Med Biol Soc. 2011;2011:6063-6066.
32.
IannettiGDHughesNPLeeMCMourauxA. Determinants of laser-evoked EEG responses: pain perception or stimulus saliency?J Neurophysiol. 2008;100:815-828.
33.
RioulOVetterliM. Wavelets and signal processing. IEEE Signal Process Mag. 1991;8(4):14-38.
34.
AnghinahR. Estudo da densidade espectral e da coerência do eletroencefalograma em indivíduos adultos normais e com doença de Alzheimer provável. São Paulo, Universidade de São Paulo, Faculdade de Medicina;2003.
35.
ZhaoJZhouWLiuKCaiD. Application of SVM and wavelet analysis in EEG classification [in Chinese]. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2011;28:277-279.
36.
GaoJLuLYangYYuGNaLRaoN. A novel concealed information test method based on independent component analysis and support vector machine. Clin EEG Neurosci. 2012;43:54-63.
37.
KhalighiSSousaTOliveiraDPiresGNunesU. Efficient feature selection for sleep staging based on maximal overlap discrete wavelet transform and SVM. Conf Proc IEEE Eng Med Biol Soc. 2011;2011:3306-3309.
38.
VapnikVN. The Nature of Statistical Learning Theory. Berlin, Germany: Springer-Verlag; 1995.
39.
CampbellC. An introduction to kernel methods. Stud Fuzziness Soft Comput. 2001;66:155-192.
40.
ChapelleOVapnikVBousquetOMukherjeeS. Choosing multiple parameters for support vector machines. Machine Learn. 2002;46:131-159.
41.
CristianiniNShawe-TaylorJ. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge, UK: Cambridge University Press; 2000.
42.
WittenIFrankE. Data Mining: Practical Machine Learning Tools and Techniques. Amsterdam, Netherlands: Elsevier; 2005.
43.
FanRChangKHsiehCWangXLinC. LIBLINEAR: a library for large linear classification. J Machine Learn Res. 2008;9:1871-1874.
44.
KeerthiSLinC. Asymptotic behaviors of support vector machines with Gaussian kernel. Neural Comput. 2003;15:1667-1689.
45.
YuanGXHoCHLinCJ. Recent advances of large-scale linear classification. Proc IEEE. 2012;100:2584-2603.
46.
NielsenTMontplaisirJLassondeM. Decreased interhemisferic EEG coherene during sleep in agenesis of the corpus calosum. Eur Neurol. 1993;33:173-176.
47.
HotPRauchsGBertranF. Changes in sleep theta rhythm are related to episodic memory impairment in early Alzheimer’s disease. Biol Psychol. 2011;87:334-339.
48.
WittenIHFrankEHallMA. Data Mining. Practical Machine Learning Tools and Techniques. 3rd ed.Burlington, MA: Morgan Kaufmann; 2011.
49.
BrookmeyerRJohnsonEZiegler-GrahamKArrighiHM. Forecasting the global burden of Alzheimer’s disease. Alzheimers Dement. 2007;3:186-191.
VerasRP. Brazil is getting older: demographic changes and epidemiological challenges. Rev Saude Publica. 1991;25:476-488.
52.
OttABretelerMMvan HarskampF. Prevalence of Alzheimer’s disease and vascular dementia: association with education. The Rotterdam study. BMJ. 1995;310:970-973.
53.
HerreraEJrCaramelliPSilveiraASNitriniR. Epidemiologic survey of dementia in a community-dwelling Brazilian population. Alzheimer Dis Assoc Disord. 2002;16:103-108.
54.
HerreraEJrCaramelliPNitriniR. Estudo epidemiológico populacional de demência na cidade de Catanduva–Estado de São Paulo–Brasil. Rev Psiquiatr Clin. 1988;25:70-73.
55.
BabiloniCLizioRDel PercioC. Cortical sources of resting state EEG rhythms are sensitive to the progression of Alzheimer’s disease at early stage. J Alzheimers Dis. 2013;34:1015-1035.
56.
SankariZAdeliHAdeliA. Wavelet coherence model for diagnosis of Alzheimer disease. Clin EEG Neurosci. 2012;43:268-278.
57.
SchinkelSMarwanNKurthsJ. Order patterns recurrence plots in the analysis of ERP data. Cogn Neurodyn. 2007;1:317-325.
58.
AhmadlouMAdeliH. Wavelet-synchronization methodology: a new approach for EEG-based diagnosis of ADHD. Clin EEG Neurosci. 2010;41:1-10.
59.
SankariZAdeliH. Probabilistic neural networks for diagnosis of Alzheimer’s disease using conventional and wavelet coherence. J Neurosci Methods. 2011;197:165-170.
60.
StaudingerTPolikarR. Analysis of complexity based EEG features for the diagnosis of Alzheimer’s disease. Conf Proc IEEE Eng Med Biol Soc. 2011;2011:2033-2036.
61.
SiulyLiYWenPP. Clustering technique-based least square support vector machine for EEG signal classification. Comput Methods Programs Biomed. 2011;104:358-372.
62.
ArabMRSuratgarAAAshtianiAR. Electroencephalogram signals processing for topographic brain mapping and epilepsies classification. Comput Biol Med. 2010;40:733-739.
63.
FengZY. Analysis of rat electroencephalogram during slow wave sleep and transition sleep using wavelet transform. Sheng Wu Hua Xue Yu Sheng Wu Wu Li Xue Bao (Shanghai). 2003;35:741-746.
64.
EngelJJrBraginAStabaRModyI. High-frequency oscillations: what is normal and what is not?Epilepsia. 2009;50:598-604.
WangXJ. Neurophysiological and computational principles of cortical rhythms in cognition. Physiol Rev. 2010;90:1195-1268.
67.
AkinM. Comparison of wavelet transform and FFT methods in the analysis of EEG signals. J Med Syst. 2002;26:241-247.
68.
WanBMingDFuXYangCQiHChenB. Study on a quantitative electroencephalography power spectrum typical of Chinese Han Alzheimer’s disease patients by using wavelet transforms. J Neural Eng. 2006;3:71-77.
69.
PolikarRTopalisAGreenDKouniosJClarkCM. Comparative multiresolution wavelet analysis of ERP spectral bands using an ensemble of classifiers approach for early diagnosis of Alzheimer’s disease. Comput Biol Med. 2007;37:542-558.
70.
LehmannD. Multichannel topography of human alpha EEG fields. Electroencephalogr Clin Neurophysiol. 1971;31:439-449.
71.
TrambaiolliLRFalkTHFragaFJAnghinahRLorenaAC. EEG spectro-temporal modulation energy: a new feature for automated diagnosis of Alzheimer’s disease. Conf Proc IEEE Eng Med Biol Soc. 2011;2011:3828-3831.
72.
FalkTHFragaFJTrambaiolliLRAnghinahR. EEG amplitude modulation analysis for semi-automated diagnosis of Alzheimer’s disease. EURASIP J Adv Signal Process. 2012;2012:192.
