Abstract
Reliable diagnosis of depressive disorder is essential for both optimal treatment and prevention of fatal outcomes. This study aimed to elucidate the effectiveness of two non-linear measures, Higuchi’s Fractal Dimension (HFD) and Sample Entropy (SampEn), in detecting depressive disorders when applied on EEG. HFD and SampEn of EEG signals were used as features for seven machine learning algorithms including Multilayer Perceptron, Logistic Regression, Support Vector Machines with the linear and polynomial kernel, Decision Tree, Random Forest, and Naïve Bayes classifier, discriminating EEG between healthy control subjects and patients diagnosed with depression. This study confirmed earlier observations that both non-linear measures can discriminate EEG signals of patients from healthy control subjects. The results suggest that good classification is possible even with a small number of principal components. Average accuracy among classifiers ranged from 90.24 to 97.56%. Among the two measures, SampEn had better performance. Using HFD and SampEn and a variety of machine learning techniques we can accurately discriminate patients diagnosed with depression vs controls which can serve as a highly sensitive, clinically relevant marker for the diagnosis of depressive disorders.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Acharya UR, Faust O, Kannathal N, Chua T, Laxminarayan S (2005) Nonlinear analysis of EEG signal at various sleep stages. Comput Methods Programs Biomed 80(1):37–45. https://doi.org/10.1016/j.cmpb.2005.06.011
Acharya UR, Sudarshan VK, Adeli H, Santhosh J, Koh JE, Puthankatti SD, Adeli A (2015) A novel depression diagnosis index using nonlinear features in EEG signals. Eur Neurol 74(1–2):79–83. https://doi.org/10.1159/000438457
Ahmadlou M, Adeli H, Adeli A (2012) Fractal analysis of frontal brain in major depressive disorder. Int J Psychophysiol 8(2):206–211. https://doi.org/10.1016/j.ijpsycho.2012.05.001
Al-Kayasi AM, Al-Ani A, Loo CK, Powell TY, Martin DM, Breakspear M, Boonstra TW (2017) Predicting tDCS treatment outcomes of patients with major depressive disorder using automated EEG classification. J Affect Disord 208:597–603
Allen JJB, Urry HL, Hitt SK, Coan JA (2004) The stability of resting frontal electroencephalographic asymmetry in depression. Psychophysiology 41:269–280. https://doi.org/10.1111/j.1469-8986.2003.00149.x
American Psychiatric Association (2013) Diagnostic and statistical manual of mental disorders, 5th edn. Washington, DC
Arnone D, McIntosh AM, Ebmeier KP, Munafò MR, Anderson IM (2012) Magnetic resonance imaging studies in unipolar depression: systematic review and meta-regression analyses. Eur Neuropsychopharmacol 22:1–16. https://doi.org/10.1016/j.euroneuro.2011.05.003
Arnone D, McKie S, Elliott R, Juhasz G, Thomas EJ, Downey D, Anderson IM (2013) State-dependent changes in hippocampal grey matter in depression. Molecular Psychiatry 18:1265–1272. https://doi.org/10.1038/mp.2012.150
Bachmann M, Lass J, Suhhova A, Hinrikus H (2013) Spectral asymmetry and Higuchi’s fractal dimension of depression electroencephalogram. Comput Math Methods Med. https://doi.org/10.1155/2013/251638
Bachmann M, Päeske L, Kalev K, Aarma K, Lehtmetmets A, Ööpik P, Lass J, Hinrikus H (2018) Methods for classifying depression in single channel EEG using linear and nonlinear signal analysis. Comput Methods Programs Biomed 155:11–17
Bairy GM, Bhat S, Eugene LWJ, Niranjan UC, Puthankatti SD, Joseph PK (2015) Automated classification of depression electroencephalographic signals using discrete cosine transform and nonlinear dynamics. J Med Imaging Health Inf 5(3):1–6. https://doi.org/10.1166/jmihi.2015.1418
Basar E, Guntekin B, Atagun I (2011) Brain’s alpha activity is highly reduced in euthymic bipolar disorder patients. Cogn Neurodyn. https://doi.org/10.1007/s11571-011-9172-y
Bishop C (1995) Neural Networks for pattern recognition. Oxford University Press, Oxford, pp 116–160
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Burges CJC (1998) A tutorial for support vector machines for pattern recognition. Data mining and knowledge discovery 2. Kluwer Academic Publishers, Boston, pp 121–167
Burns T, Ramesh R (2015) Combining complexity measures of EEG data: multiplying measures reveal previously hidden information. F1000Research 4:137. https://doi.org/10.12688/f1000research.6590.1
Castiglioni P (2010) What is wrong with Katz’s method? Comments on: a note on fractal dimensions of biomedical waveforms. Comput Biol Med 40(11–12):950–952. https://doi.org/10.1016/j.compbiomed.2010.10.001
Cox DR (1958) The regression analysis of binary sequences (with discussion). J R Stat Soc B 20:215–242
de Kwaasteniet B, Ruhe E, Caan M, Rive M, Olabarriaga S, Groefsema M (2013) Relation between structural and functional connectivity in major depressive disorder. Biol Psychiat 74:40–47. https://doi.org/10.1016/j.biopsych.2012.12.024
Devijver PA, Kittler J (1982) Pattern recognition: a statistical approach. Prentice-Hall, London
Devore JL (2012) Probability and statistics for engineering and the sciences, 8th edn. Brooks/Cole, Boston
Efron B, Tibshirani R (1997) Improvements on cross-validation: the 632 + bootstrap method. J Am Stat Assoc 92(438):548–560. https://doi.org/10.2307/2965703
Eke A, Herman P, Koscis L, Kozak LR (2002) Fractal characterization of complexity in temporal physiological signals. Phys Meas 23(1):R1–R38
Esteller R, Vachtsevanos G, Echauz J, Litt B (2001) A comparison of waveform fractal dimension algorithms. Circuits Syst I: Fundam Theory Appl 48(2):177–183
Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27:861–874. https://doi.org/10.1016/j.patrec.2005.10.010
Friedman JH, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting (with discussion). Ann Stat 28:337–407. https://doi.org/10.1214/aos/1016218223
Goldberger AL, Peng CK, Lipsitz LA (2002) What is physiologic complexity and how does it change with aging and disease? Neurobiol Aging 23:23–26
Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. ACM SIGKDD Explor Newsl 11(1):10–18. https://doi.org/10.1145/1656274.1656278
Hand RJA, Till DJ (2012) Simple generalization of the area under the ROC curve for multiple class classification problems. Mach Learn 45:171–186. https://doi.org/10.1023/A:101092081
Haykin S (2008) Neural networks and learning machines, 3rd edn. Pearson Education, New York, pp 122–218
Higuchi T (1988) Approach to an irregular time series on the basis of the fractal theory. Physica D 31:277–283. https://doi.org/10.1016/0167-2789(88)90081-4
Hosseinifard B, Moradi MH, Rostami R (2013) Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal. Comput Methods Programs Biomed 109(3):339–345. https://doi.org/10.1016/j.cmpb.2012.10.008
Hussain L (2018) Detecting epileptic seizure with different feature extracting strategies using robust machine learning classification techniques by applying advance parameter optimization approach. Cogn Neurodyn 12(3):271–294
John GH, Langley P (1995) Estimating continuous distributions in bayesian classifiers. In Proceedings of the eleventh conference on uncertainty in artificial intelligence, San Mateo, pp 338–345
Jolliffe JL (2002) Principal component analysis, 2nd edn. Springer, New York, pp 10–150
Kalauzi A, Bojic T, Vuckovic A (2012) Modeling the relationship between Higuchi’s fractal dimension and Fourier spectra of physiological signals. Med Biol Eng Comput 50(7):689–699. https://doi.org/10.1007/s11517-012-0913-9
Kecman V (2001) Learning and soft computing: support vector machines, neural networks and fazzy logic models. A Bradford Book. The MIT Press, Cambridge
Kemp AH, Griffiths K, Felgham KL, Shankman SA, Drinkenburg W, Arns M, Clark CR, Bryant RA (2010) Disorder specificity despite comorbidity: resting EEG alpha asymmetry in major depressive disorder and post-traumatic stress disorder. Biol Psychol 85(2):350–354. https://doi.org/10.1016/j.biopsycho.2010.08.001
Khajehpour H, Mohagheghian F, Ekhtiari H, Makkiabadi B, Jafari AH, Eqlimi E, Harirchian MH (2019) Computer-aided classifying and characterizing of methamphetamine use disorder using resting-state EEG. Cogn Neurodyn 13(6):519–530
Kim D, Bolbecker AR, Howell J, Rass O, Sporns O, Hetrick WP, Breier A, O’Donnell BF (2013) Disturbed resting state EEG synchronization in bipolar disorder: a graph-theoretic analysis. Neuroimage Clin 2:414–423. https://doi.org/10.1016/j.nicl.2013.03.007
Klonowski W (2007) From conformons to human brains: an informal overview of nonlinear dynamics and its applications in biomedicine. Nonlinear Bio Phys 1(1):5. https://doi.org/10.1186/1753-4631-1-5
Knott V, Mahoney C, Kennedy S, Evans K (2000) Pre-treatment EEG and its relationship to depression severity and paroxetine treatment outcome. Pharmacopsychiatry 33:201–205. https://doi.org/10.1055/s-2000-8356
Kohavi RA (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the fourteenth international joint conference on artificial intelligence, vol 2. Morgan Kaufmann, San Mateo, pp 1137–1143
Köhler S, Ashton CH, Marsh R, Thomas AJ, Barnett NA, O’Brien JT (2011) Electrophysiological changes in late life depression and their relation to structural brain changes. Int Psychogeriatr 23(1):141–148
Koolschijn PC, van Haren NE, Lensvelt-Mulders GJ, Hulshoff Pol HE, Kahn RS (2009) Brain volume abnormalities in major depressive disorder: a meta-analysis of magnetic resonance imaging studies. Hum Brain Mapp 30:3719–3735. https://doi.org/10.1002/hbm.20801
Liang Z, Wang Y, Sun X, Li D, Voss LJ, Sleigh JW, Hagihira S, Li X (2015) EEG entropy measures in anesthesia. Front Comput Neurosci 9:16. https://doi.org/10.3389/fncom.2015.00016
Lichman M (2013) UCI machine learning repository (http://archive.ics.uci.edu/ml). Irvine, CA: University of California, School of Information and Computer Science
Mathews CD, Loncar D (2006) Projections of Global Mortality and Burden of Disease from 2002 to 2030. PlosMedicine 3(11):e442. https://doi.org/10.1371/journal.pmed.0030442
Mitchell TM (1997) Machine learning. McGraw-Hill, New York, pp 177–180
Molina-Picó A, Cuesta-Frau D, Aboy M, Crespo C, Miró-Martínez P, Oltra-Crespo S (2011) Comparative study of approximate entropy and sample entropy robustness to spikes. Artif Intell Med 53(2):97–106. https://doi.org/10.1016/j.artmed.2011.06.007
Mora-Sánchez A, Dreyfus G, Vialatte FB (2019) Scale-free behaviour and metastable brain-state switching driven by human cognition, an empirical approach. Cogn Neurodyn 13(5):437–452
Murray CJ, Vos T, Lozano R, Naghavi M, Flaxman AD, Michaud C, Ezzati M, Shibuya K, Salomon JA, Abdalla S (2013) Disability-adjusted life years (DALYs) for 291 diseases and injuries in 21 regions, 1990-2010: a systematic analysis for the Global Burden of Disease Study 2010. The Lancet 380:2197–2223. https://doi.org/10.1016/S0140-6736(12)61689-4
Netherlands Study of Depression and anxiety—NESDA 2018. http://www.emgo.nl/research/international-collaborations/longitudinal-cohort-studies/netherlands-study-of-depression-and-anxiety
Nissen C, Feige B, Nofzinger EA, Voderholzer U, Berger M, Riemann D (2006) EEG slow wave activity regulation in major depression. Somnologie 10:36–42. https://doi.org/10.1111/j.1439-054X.2006.00083.x
Oldfield RC (1971) The assessment and analysis of handedness: the Edinburgh inventory. Neuropsychologia 9:97–113
Picard R, Cook D (1984) Cross-validation of regression models. J Am Stat Assoc 79:575–583. https://doi.org/10.1080/01621459.1984.10478083
Pivick RT, Broughton RJ, Copola R, Davidson EJ, Fox N, Nuwer MR (1993) Guidelines for the recording and quantitative analysis of encephalographic activity in research contexts. Psychophysiology 30(6):547–558. https://doi.org/10.1111/j.1469-8986.1993.tb02081.x
Platt J (1998) Fast training of support vector machines using sequential minimal optimization. In: Schölkopf B, Burges CJC (eds) Advances in kernel methods—support vector learning. MIT Press, Cambridge, pp 41–65
Pokrajac D, Lazarevic A, Kecman V, Marcano A, Markushin Y, Vance T, Reljin N, McDaniel S, Melikechi N (2014) Automatic classification of laser-induced breakdown spectroscopy (LIBS) data of protein biomarker solutions. Appl Spectrosc 68(9):1067–1075. https://doi.org/10.1366/14-07488
Quinlan R (1993) Programs for machine learning. Morgan Kaufmann Publishers, San Mateo, pp 17–45
Rabinovich MI, Varona P, Selverston AI, Abarbanel HDI (2006) Dynamical principles in neuroscience. Rev Mod Phys 78(4):1213–1265. https://doi.org/10.1103/revmodphys.78.1213
Raghu N, Sriraam G, Kumar P (2017) Classification of epileptic seizures using wavelet packet log energy and norm entropies with recurrent Elman neural network classifier. Cogn Neurodyn 11(1):51–66
Ricardo-Garcell J, Gonzalez-Olvera JJ, Miranda E, Harmony T, Reyes E, Almeida L, Galan L, Diaz D, Ramirez L, Fernandez-Rouzas A, Aubert E (2009) EEG sources in a group of patients with major depressive disorders. Int J Psychophysiol 71(1):70–74. https://doi.org/10.1016/j.ijpsycho.2008.07.021
Richman JS, Moorman JR (2000) Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol Heart Circ Physiol 278(6):2039–2049
Roh SC, Park EJ, Shim M, Lee SH (2016) EEG beta and low gamma power correlates with inattention in patients with major depressive disorder. J Affect Disord 204:124–130. https://doi.org/10.1016/j.jad.2016.06.033
Shahaf G, Yariv S, Bloch B, Nitzan U, Segev A, Reshef A, Bloch Y (2017) A pilot study of possible easy-to-use electrophysiological index for early detection of antidepressant treatment non-response. Front Psychiatry. https://doi.org/10.3389/fpsyt.2017.00128
Spasić S, Kalauzi A, Culić M, Grbić G, Lj Martać (2005) Fractal analysis of rat brain activity after injury. Med Biol Eng Comput 43:345–348. https://doi.org/10.1007/BF02345811
Stam CJ (2005) Nonlinear dynamical analysis of EEG and MEG: a review of emerging field. Clin Neurophysiol 116(10):2266–3211
Stewart JL, Bismark AW, Towers DN, Coan JA, Allen JJB (2010) Resting frontal EEG asymmetry as an endophenotype for depression risk: sex-specific patterns of frontal brain asymmetry. J Abnorm Psychol 119:502–512. https://doi.org/10.1037/a0019196
Stokić M, Milovanović D, Ljubisavljević M, Nenadović V, Čukić M (2015) Memory load effect in auditory-verbal short-term memory task: EEG fractal and spectral analysis. Exp Brain Res 233(10):3023–3038. https://doi.org/10.1007/s00221-015-4372-z
Tafreshi TF, Daliri MH, Ghodousi M (2019) Functional and effective connectivity based features of EEG signals for object recognition. Cogn Neurodyn 13(6):555–566
Unnikrishnan P, Kumar DK, Arjunan SP, Kumar H, Mitchell P, Kawasaki R (2016) Development of health parameter model for risk prediction of CVD using SVM. Comput Math Methods Med. https://doi.org/10.1155/2016/3016245
Van der Vinne N, Vollebregt MA, van Putten MJAM, Arns M (2017) Frontal alpha asymmetry as a diagnostic marker in depression: fact or fiction? A meta-analysis. Neuroimage Clin 16:79–87
Vapnik VN (1988) Statistical learning theory (chapter 10, p 42). John Willey and Sons Inc., New York
Vederine FE, Wessa M, Leboyer M, Houenou J (2011) A meta-analysis of whole-brain diffusion tensor imaging studies in bipolar disorder. Prog Neuropsychopharmacol Biol Psychiatry 35:1820–1826. https://doi.org/10.1016/j.pnpbp.2011.05.009
Witten IH, Frank E (2005) Data mining: practical learning tools and techniques, 2nd edn. Elsevier, Amsterdam, pp 90–97
World Health Organization (2017) Depression and other common mental disorders. http://apps.who.int/iris/bitstream/10665/254610/1/WHO-MSD-MER-2017.2-eng.pdf
World organization of Mental Health (2012) Depression: a global crisis; world mental health day, October 10, 2012 http://www.who.int/mental_health/management/depression/wfmh_paper_depression_wmhd_2012.pdf
Acknowledgements
We would like to thank Christopher Stewart, PhD, analytical linguist from Google for help in improving the text and Dr. Tomasz Smolinski from Delaware State University for useful discussions. Also, we want to thank Slavoljub Radenković, Senior web developet from TomTom for refinement of HFD algorithm. This study was supported by RISEWISE Project H2020-MSCA-RISE-2015-690874. Dr. Miodrag Stokić was granted by Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja (178027 and 32032)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Čukić, M., Stokić, M., Simić, S. et al. The successful discrimination of depression from EEG could be attributed to proper feature extraction and not to a particular classification method. Cogn Neurodyn 14, 443–455 (2020). https://doi.org/10.1007/s11571-020-09581-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11571-020-09581-x