Skip to main content

A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (MDD)

Medical & Biological Engineering & Computing volume 56, pages 233–246 (2018)Cite this article

Abstract

Major depressive disorder (MDD), a debilitating mental illness, could cause functional disabilities and could become a social problem. An accurate and early diagnosis for depression could become challenging. This paper proposed a machine learning framework involving EEG-derived synchronization likelihood (SL) features as input data for automatic diagnosis of MDD. It was hypothesized that EEG-based SL features could discriminate MDD patients and healthy controls with an acceptable accuracy better than measures such as interhemispheric coherence and mutual information. In this work, classification models such as support vector machine (SVM), logistic regression (LR) and Naïve Bayesian (NB) were employed to model relationship between the EEG features and the study groups (MDD patient and healthy controls) and ultimately achieved discrimination of study participants. The results indicated that the classification rates were better than chance. More specifically, the study resulted into SVM classification accuracy = 98%, sensitivity = 99.9%, specificity = 95% and f-measure = 0.97; LR classification accuracy = 91.7%, sensitivity = 86.66%, specificity = 96.6% and f-measure = 0.90; NB classification accuracy = 93.6%, sensitivity = 100%, specificity = 87.9% and f-measure = 0.95. In conclusion, SL could be a promising method for diagnosing depression. The findings could be generalized to develop a robust CAD-based tool that may help for clinical purposes.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3

References

  1. A. American Psychiatric Association and A. P. Association (1994) Diagnostic and statistical manual of mental disorders

  2. A. P. Association (2013) Diagnostic and statistical manual of mental disorders (DSM-5®). American Psychiatric Pub, Arlington

    Book  Google Scholar 

  3. Acharya UR, Faust O, Kannathal N, Chua T, Laxminarayan S (2005) Non-linear analysis of EEG signals at various sleep stages. Comput Methods Programs Biomed 80:37–45

    Article  Google Scholar 

  4. Acharya UR, Sree SV, Alvin APC, Yanti R, Suri JS (2012) Application of non-linear and wavelet based features for the automated identification of epileptic EEG signals. Int J Neural Syst 22:1–14

    Article  Google Scholar 

  5. Acharya UR, Sudarshan V, Adeli H, Santhosh J, Koh J, Adeli A (2015) Computer-aided diagnosis of depression using EEG signals. Eur Neurol 73:329–336

    Article  PubMed  Google Scholar 

  6. Acharya UR, Sudarshan VK, Adeli H, Santhosh J, Koh JE, Puthankatti SD et al (2015) A novel depression diagnosis index using nonlinear features in EEG signals. Eur Neurol 74:79–83

    Article  PubMed  Google Scholar 

  7. Adeli H, Ghosh-Dastidar S, Dadmehr N (2007) A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy. IEEE Trans Biomed Eng 54:205–211

    Article  PubMed  Google Scholar 

  8. Ahmadlou M, Adeli H, Adeli A (2012) Fractality analysis of frontal brain in major depressive disorder. Int J Psychophysiol 85:206–211

    Article  PubMed  Google Scholar 

  9. Alhaj H, Wisniewski G, McAllister-Williams RH (2011) The use of the EEG in measuring therapeutic drug action: focus on depression and antidepressants. J Psychopharmacol 25:1175–1191

    CAS  Article  PubMed  Google Scholar 

  10. Anand A, Li Y, Wang Y, Wu J, Gao S, Bukhari L et al (2005) Activity and connectivity of brain mood regulating circuit in depression: a functional magnetic resonance study. Biol Psychiatry 57:1079–1088

    Article  PubMed  Google Scholar 

  11. Bae JN, MacFall JR, Krishnan KRR, Payne ME, Steffens DC, Taylor WD (2006) Dorsolateral prefrontal cortex and anterior cingulate cortex white matter alterations in late-life depression. Biol Psychiatry 60:1356–1363

    Article  PubMed  Google Scholar 

  12. Berg P, Scherg M (1994) A multiple source approach to the correction of eye artifacts. Electroencephalogr Clin Neurophysiol 90:229–241

    CAS  Article  PubMed  Google Scholar 

  13. Culpepper L (2014) Misdiagnosis of bipolar depression in primary care practices. J Clin Psychiatry 75:e05–e05

    Article  PubMed  Google Scholar 

  14. Erguzel TT, Ozekes S, Tan O, Gultekin S (2015) Feature selection and classification of electroencephalographic signals an artificial neural network and genetic algorithm based approach. Clin EEG Neurosci 46:321–326

    Article  PubMed  Google Scholar 

  15. Fingelkurts AA, Fingelkurts AA, Rytsälä H, Suominen K, Isometsä E, Kähkönen S (2007) Impaired functional connectivity at EEG alpha and theta frequency bands in major depression. Hum Brain Mapp 28:247–261

    Article  PubMed  Google Scholar 

  16. Greenberg PE, Fournier A-A, Sisitsky T, Pike CT, Kessler RC (2015) The economic burden of adults with major depressive disorder in the United States (2005 and 2010). J Clin Psychiatry 76:155–162

    Article  PubMed  Google Scholar 

  17. Guo H, Cao X, Liu Z, Li H, Chen J, Zhang K (2012) Machine learning classifier using abnormal brain network topological metrics in major depressive disorder. NeuroReport 23:1006–1011

    Article  PubMed  Google Scholar 

  18. Hamilton JP, Gotlib IH (2008) Neural substrates of increased memory sensitivity for negative stimuli in major depression. Biol Psychiatry 63:1155–1162

    Article  PubMed  PubMed Central  Google Scholar 

  19. Hoechstetter K, Berg P, Scherg M (2010) BESA research tutorial 4: distributed source imaging. BESA Research Tutorial, pp 1–29

  20. Hosmer DW Jr, Lemeshow S (2004) Applied logistic regression. Wiley, New York

    Google Scholar 

  21. 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 109:339–345

    Article  PubMed  Google Scholar 

  22. Jalili M, Knyazeva MG (2011) EEG-based functional networks in schizophrenia. Comput Biol Med 41:1178–1186

    Article  PubMed  Google Scholar 

  23. Jasper HH (1958) The ten twenty electrode system of the international federation. Electroencephalogr Clin Neurophysiol 10:371–375

    Google Scholar 

  24. Kalatzis I, Piliouras N, Ventouras E, Papageorgiou CC, Rabavilas AD, Cavouras D (2004) Design and implementation of an SVM-based computer classification system for discriminating depressive patients from healthy controls using the P600 component of ERP signals. Comput Methods Programs Biomed 75:11–22

    CAS  Article  PubMed  Google Scholar 

  25. Klöppel S, Abdulkadir A, Jack CR, Koutsouleris N, Mourão-Miranda J, Vemuri P (2012) Diagnostic neuroimaging across diseases. Neuroimage 61:457–463

    Article  PubMed  Google Scholar 

  26. Knott V, Mahoney C, Kennedy S, Evans K (2001) EEG power, frequency, asymmetry and coherence in male depression. Psychiatry Res Neuroimaging 106:123–140

    CAS  Article  PubMed  Google Scholar 

  27. Lee J-S, Yang B-H, Lee J-H, Choi J-H, Choi I-G, Kim S-B (2007) Detrended fluctuation analysis of resting EEG in depressed outpatients and healthy controls. Clin Neurophysiol 118:2489–2496

    Article  PubMed  Google Scholar 

  28. Lee T-W, Wu Y-T, Yu YW-Y, Chen M-C, Chen T-J (2011) The implication of functional connectivity strength in predicting treatment response of major depressive disorder: a resting EEG study. Psychiatry Res Neuroimaging 194:372–377

    Article  PubMed  Google Scholar 

  29. Lehmann C, Koenig T, Jelic V, Prichep L, John RE, Wahlund L-O et al (2007) Application and comparison of classification algorithms for recognition of Alzheimer’s disease in electrical brain activity (EEG). J Neurosci Methods 161:342–350

    Article  PubMed  Google Scholar 

  30. Li Y, Li Y, Tong S, Tang Y, Zhu Y (2007) More normal EEGs of depression patients during mental arithmetic than rest. In: Noninvasive functional source imaging of the brain and heart and the international conference on functional biomedical imaging, 2007. Joint meeting of the 6th international symposium on NFSI-ICFBI 2007, pp 165–168

  31. Liu H, Motoda H (2007) Computational methods of feature selection. CRC Press, Boca Raton

    Google Scholar 

  32. Magnin B, Mesrob L, Kinkingnéhun S, Pélégrini-Issac M, Colliot O, Sarazin M et al (2009) Support vector machine-based classification of Alzheimer’s disease from whole-brain anatomical MRI. Neuroradiology 51:73–83

    Article  PubMed  Google Scholar 

  33. Mahmud WMRW, Awang A, Herman I, Mohamed MN (2004) Analysis of the psychometric properties of the Malay version of Beck Depression Inventory II (BDI-II) among postpartum women in Kedah, north west of peninsular Malaysia. Malays J Med Sci MJMS 11:19

    Article  Google Scholar 

  34. Mamitsuka H (2006) Selecting features in microarray classification using ROC curves. Pattern Recogn 39:2393–2404

    Article  Google Scholar 

  35. Mitchell TM (1997) Machine learning. WCB ed: McGraw-Hill, Boston

  36. Mohammadi M, Al-Azab F, Raahemi B, Richards G, Jaworska N, Smith D et al (2015) Data mining EEG signals in depression for their diagnostic value. BMC Med Inform Decis Mak 15:1

    Article  Google Scholar 

  37. Mumtaz W, Malik AS, Yasin MAM, Xia L (2015) Review on EEG and ERP predictive biomarkers for major depressive disorder. Biomed Signal Process Control 22:85–98

    Article  Google Scholar 

  38. Mumtaz W, Vuong PL, Xia L, Malik AS, Rashid RBA (2016) Automatic diagnosis of alcohol use disorder using EEG features. Knowl-Based Syst 105:48–59

    Article  Google Scholar 

  39. Mumtaz W, Xia L, Ali SSA, Yasin MAM, Hussain M, Malik AS (2017) Electroencephalogram (EEG)-based computer-aided technique to diagnose major depressive disorder (MDD). Biomed Signal Process Control 31:108–115

    Article  Google Scholar 

  40. Mwangi B, Ebmeier KP, Matthews K, Steele JD (2012) Multi-centre diagnostic classification of individual structural neuroimaging scans from patients with major depressive disorder. Brain 135:1508–1521

    Article  PubMed  Google Scholar 

  41. Olbrich S, Arns M (2013) EEG biomarkers in major depressive disorder: discriminative power and prediction of treatment response. Int Rev Psychiatry 25:604–618

    Article  PubMed  Google Scholar 

  42. Olbrich S, Tränkner A, Chittka T, Hegerl U, Schönknecht P (2014) Functional connectivity in major depression: increased phase synchronization between frontal cortical EEG-source estimates. Psychiatry Res Neuroimaging 222:91–99

    Article  PubMed  Google Scholar 

  43. Olofsen E, Sleigh J, Dahan A (2008) Permutation entropy of the electroencephalogram: a measure of anaesthetic drug effect. Br J Anaesth 101:810–821

    CAS  Article  PubMed  Google Scholar 

  44. Orrù G, Pettersson-Yeo W, Marquand AF, Sartori G, Mechelli A (2012) Using support vector machine to identify imaging biomarkers of neurological and psychiatric disease: a critical review. Neurosci Biobehav Rev 36:1140–1152

    Article  PubMed  Google Scholar 

  45. Park C-A, Kwon R-J, Kim S, Jang H-R, Chae J-H, Kim T et al (2006) Decreased phase synchronization of the EEG in patients with major depressive disorder. World Congress Med Phys Biomed Eng 2007:1095–1098

    Google Scholar 

  46. Puthankattil SD, Joseph PK (2012) Classification of EEG signals in normal and depression conditions by ANN using RWE and signal entropy. J Mech Med Biol 12:1240019

    Article  Google Scholar 

  47. Qin Y, Xu P, Yao D (2010) A comparative study of different references for EEG default mode network: the use of the infinity reference. Clin Neurophysiol 121:1981–1991

    Article  PubMed  Google Scholar 

  48. Ramasubbu R, Brown MR, Cortese F, Gaxiola I, Goodyear B, Greenshaw AJ et al (2016) Accuracy of automated classification of major depressive disorder as a function of symptom severity. NeuroImage Clin 12:320–331

    Article  PubMed  PubMed Central  Google Scholar 

  49. Stam C, Van Dijk B (2002) Synchronization likelihood: an unbiased measure of generalized synchronization in multivariate data sets. Phys D 163:236–251

    Article  Google Scholar 

  50. Stam C, Montez T, Jones B, Rombouts S, Van Der Made Y, Pijnenburg Y et al (2005) Disturbed fluctuations of resting state EEG synchronization in Alzheimer’s disease. Clin Neurophysiol 116:708–715

    CAS  Article  PubMed  Google Scholar 

  51. Takens F (1981) Detecting strange attractors in turbulence. In: Dynamical systems and turbulence, Warwick 1980 (ed). Springer, pp. 366–381

  52. Theiler J (1986) Spurious dimension from correlation algorithms applied to limited time-series data. Phys Rev A 34:2427

    CAS  Article  Google Scholar 

  53. Vapnik VN, Vapnik V (1998) Statistical learning theory, vol 2. Wiley, New York

    Google Scholar 

  54. Volkert J, Schulz H, Härter M, Wlodarczyk O, Andreas S (2013) The prevalence of mental disorders in older people in Western countries—a meta-analysis. Ageing Res Rev 12:339–353

    Article  PubMed  Google Scholar 

  55. Willner P, Scheel-Krüger J, Belzung C (2013) The neurobiology of depression and antidepressant action. Neurosci Biobehav Rev 37:2331–2371

    CAS  Article  PubMed  Google Scholar 

  56. Zeng LL, Shen H, Liu L, Hu D (2014) Unsupervised classification of major depression using functional connectivity MRI. Hum Brain Mapp 35:1630–1641

    Article  PubMed  Google Scholar 

Download references

Acknowledgement

This research work was supported by HiCoE research fund, Grant Number (0153CA-005), Ministry of Higher Education (MoHE), Malaysia.

Author information

Author notes

    Affiliations

    1. Center for Intelligent Signal and Imaging Research, Electrical and Electronic Engineering Department, Universiti Teknologi PETRONAS, 32610, Seri Iskandar, Malaysia

      Wajid Mumtaz, Syed Saad Azhar Ali & Aamir Saeed Malik

    2. Department of Psychiatry, Hospital Universiti Sains Malaysia, Kubang Kerian, Kelantan, Malaysia

      Mohd Azhar Mohd Yasin

    Authors
    1. Wajid Mumtaz
      View author publications

      You can also search for this author in PubMed Google Scholar

    2. Syed Saad Azhar Ali
      View author publications

      You can also search for this author in PubMed Google Scholar

    3. Mohd Azhar Mohd Yasin
      View author publications

      You can also search for this author in PubMed Google Scholar

    4. Aamir Saeed Malik
      View author publications

      You can also search for this author in PubMed Google Scholar

    Corresponding author

    Correspondence to Aamir Saeed Malik.

    Ethics declarations

    Conflict of interest

    There is no conflict of interest found for this study.

    Additional information

    All authors have equal contribution for this research work.

    Rights and permissions

    Reprints and Permissions

    About this article

    Verify currency and authenticity via CrossMark

    Cite this article

    Mumtaz, W., Ali, S.S.A., Yasin, M.A.M. et al. A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (MDD). Med Biol Eng Comput 56, 233–246 (2018). https://doi.org/10.1007/s11517-017-1685-z

    Download citation

    • Received:

    • Accepted:

    • Published:

    • Issue Date:

    • DOI: https://doi.org/10.1007/s11517-017-1685-z

    Keywords

    • Major depressive disorder
    • Machine learning-based diagnosis
    • Computer-aided diagnosis (CAD) for depression
    • EEG-based machine learning techniques for depression
    • Synchronization likelihood (SL) features