Attentional bias in MDD: ERP components analysis and classification using a dot-probe task

BACKGROUND AND OBJECTIVE Strands of evidence have supported existence of negative attentional bias in patients with depression. This study aimed to assess the behavioral and electrophysiological signatures of attentional bias in major depressive disorder (MDD) and explore whether ERP components contain valuable information for discriminating between MDD patients and healthy controls (HCs). METHODS Electroencephalography data were collected from 17 patients with MDD and 17 HCs in a dot-probe task, with emotional-neutral pairs as experimental materials. Fourteen features related to ERP waveform shape were generated. Then, Correlated Feature Selection (CFS), ReliefF and GainRatio (GR) were applied for feature selection. For discriminating between MDDs and HCs, k-nearest neighbor (KNN), C4.5, Sequential Minimal Optimization (SMO) and Logistic Regression (LR) were used. RESULTS Behaviorally, MDD patients showed significantly shorter reaction time (RT) to valid than invalid sad trials, with significantly higher bias score for sad-neutral pairs. Analysis of split-half reliability in RT indices indicated a strong reliability in RT, while coefficients of RT bias scores neared zero. These behavioral effects were supported by ERP results. MDD patients had higher P300 amplitude with the probe replacing a sad face than a neutral face, indicating difficult attention disengagement from negative emotional faces. Meanwhile, data mining analysis based on ERP components suggested that CFS was the best feature selection algorithm. Especially for the P300 induced by valid sad trials, the classification accuracy of CFS combination with any classifier was above 85%, and the KNN (k = 3) classifier achieved the highest accuracy (94%). CONCLUSIONS MDD patients show difficulty in attention disengagement from negative stimuli, reflected by P300. The CFS over other methods leads to a good overall performance in most cases, especially when KNN classifier is used for P300 component classification, illustrating that ERP component may be applied as a tool for auxiliary diagnosis of depression.

[1]  Brandon E. Gibb,et al.  Attentional biases in children of depressed mothers: An event-related potential (ERP) study. , 2016, Journal of abnormal psychology.

[2]  J. Hadwin,et al.  Psychometric properties of reaction time based experimental paradigms measuring anxiety-related information-processing biases in children. , 2014, Journal of anxiety disorders.

[3]  Gregory A. Miller,et al.  Electrophysiological evidence of the time course of attentional bias in non-patients reporting symptoms of depression with and without co-occurring anxiety , 2014, Front. Psychol..

[4]  E. Naito,et al.  Enhanced neural activity in response to dynamic facial expressions of emotion: an fMRI study. , 2004, Brain research. Cognitive brain research.

[5]  T. Sejnowski,et al.  Removing electroencephalographic artifacts by blind source separation. , 2000, Psychophysiology.

[6]  L. Bai,et al.  The Development of Native Chinese Affective Picture System-A pretest in 46 College Students , 2005 .

[7]  E. Gordon,et al.  Face to face: visual scanpath evidence for abnormal processing of facial expressions in social phobia , 2004, Psychiatry Research.

[8]  Steven J. Luck,et al.  ERPLAB: an open-source toolbox for the analysis of event-related potentials , 2014, Front. Hum. Neurosci..

[9]  T. Ortiz,et al.  Alterations of P300 wave in occipital lobe in depressive patients. , 2007, Actas espanolas de psiquiatria.

[10]  N. Farb,et al.  A two-factor model of relapse/recurrence vulnerability in unipolar depression. , 2015, Journal of abnormal psychology.

[11]  Daxing Wu,et al.  Time course of affective processing bias in major depression: An ERP study , 2011, Neuroscience Letters.

[12]  Geoff Holmes,et al.  Benchmarking Attribute Selection Techniques for Discrete Class Data Mining , 2003, IEEE Trans. Knowl. Data Eng..

[13]  E. Fox,et al.  Attentional bias for threat: Evidence for delayed disengagement from emotional faces , 2002, Cognition & emotion.

[14]  D. Mantini,et al.  Neural Correlates of Drug-Related Attentional Bias in Heroin Dependence , 2018, Front. Hum. Neurosci..

[15]  Michael B First,et al.  Diagnostic and statistical manual of mental disorders, 5th edition, and clinical utility. , 2013, The Journal of nervous and mental disease.

[16]  Ruth Ann Atchley,et al.  Do the early attentional components of ERPs reflect attentional bias in depression? It depends on the stimulus presentation time , 2011, Clinical Neurophysiology.

[17]  T OrtizAlonso,et al.  P300 clinical utility in major depression , 2002 .

[18]  C. Beevers,et al.  Attentional biases and the persistence of sad mood in major depressive disorder. , 2013, Journal of abnormal psychology.

[19]  Michela Sarlo,et al.  Out of sight, but still in mind: Electrocortical correlates of attentional capture in spider phobia as revealed by a ‘dot probe’ paradigm , 2015, Brain and Cognition.

[20]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[21]  P. Ekman,et al.  American-Japanese cultural differences in intensity ratings of facial expressions of emotion , 1989 .

[22]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[23]  Ioannis Kalatzis,et al.  Design and implementation of an SVM-based computer classification system for discriminating depressive patients from healthy controls using the P600 component of ERP signals , 2004, Comput. Methods Programs Biomed..

[24]  Raveendran Paramesran,et al.  Using genetic algorithm to identify the discriminatory subset of multi-channel spectral bands for visual response , 2002, Appl. Soft Comput..

[25]  Margot J. Taylor,et al.  Early processing of the six basic facial emotional expressions. , 2003, Brain research. Cognitive brain research.

[26]  David Huepe,et al.  What event-related potentials (ERPs) bring to social neuroscience? , 2012, Social neuroscience.

[27]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[28]  Lisa Talbot,et al.  Biased processing of emotional information in girls at risk for depression. , 2007, Journal of abnormal psychology.

[29]  F. McGlone,et al.  The role of spatial attention in the processing of facial expression: An ERP study of rapid brain responses to six basic emotions , 2003, Cognitive, affective & behavioral neuroscience.

[30]  Khader M. Hasan,et al.  Prediction of individual subject's age across the human lifespan using diffusion tensor imaging: A machine learning approach , 2013, NeuroImage.

[31]  I. Gotlib,et al.  Selective attention to emotional faces following recovery from depression. , 2007, Journal of abnormal psychology.

[32]  Steven J. Luck,et al.  Behavioral and ERP measures of attentional bias to threat in the dot-probe task: poor reliability and lack of correlation with anxiety , 2014, Front. Psychol..

[33]  D. Pizzagalli,et al.  Electroencephalography Source Functional Connectivity Reveals Abnormal High-Frequency Communication Among Large-Scale Functional Networks in Depression. , 2018, Biological psychiatry. Cognitive neuroscience and neuroimaging.

[34]  Natalia Jaworska,et al.  The temporal electrocortical profile of emotive facial processing in depressed males and females and healthy controls. , 2012, Journal of affective disorders.

[35]  Kyveli Kompatsiari,et al.  Test-retest reliability of ERP components: A short-term replication of a visual Go/NoGo task in ADHD subjects , 2016, Neuroscience Letters.

[36]  J R Sveinsson,et al.  Parallel principal component neural networks for classification of event-related potential waveforms. , 1997, Medical engineering & physics.

[37]  P. Philippot,et al.  Is the P300 deficit in alcoholism associated with early visual impairments (P100, N170)? An oddball paradigm , 2007, Clinical Neurophysiology.

[38]  G. Dunbar,et al.  The Mini International Neuropsychiatric Interview (MINI). A short diagnostic structured interview: reliability and validity according to the CIDI , 1997, European Psychiatry.

[39]  B. Mwangi,et al.  Predictive classification of individual magnetic resonance imaging scans from children and adolescents , 2013, European Child & Adolescent Psychiatry.

[40]  Bin Hu,et al.  EEG-based mild depressive detection using feature selection methods and classifiers , 2016, Comput. Methods Programs Biomed..

[41]  Ernst H. W. Koster,et al.  Understanding vulnerability for depression from a cognitive neuroscience perspective: A reappraisal of attentional factors and a new conceptual framework , 2010, Cognitive, affective & behavioral neuroscience.

[42]  Huiqing Liu,et al.  A comparative study on feature selection and classification methods using gene expression profiles and proteomic patterns. , 2002, Genome informatics. International Conference on Genome Informatics.

[43]  Andrew D. Engell,et al.  Probabilistic atlases for face and biological motion perception: An analysis of their reliability and overlap , 2013, NeuroImage.

[44]  A. Curtin,et al.  Early perceptual anomaly of negative facial expression in depression: An event-related potential study , 2015, Neurophysiologie Clinique/Clinical Neurophysiology.

[45]  Kevin S LaBar,et al.  Happy and fearful emotion in cues and targets modulate event-related potential indices of gaze-directed attentional orienting. , 2007, Social cognitive and affective neuroscience.

[46]  I. Gotlib,et al.  Attentional biases for negative interpersonal stimuli in clinical depression. , 2004, Journal of abnormal psychology.

[47]  M. Thase,et al.  Can’t shake that feeling: event-related fMRI assessment of sustained amygdala activity in response to emotional information in depressed individuals , 2002, Biological Psychiatry.

[48]  B. Hjorth.  EEG analysis based on time domain properties. , 1970, Electroencephalography and clinical neurophysiology.

[49]  C. Beevers,et al.  Neural mechanisms of the cognitive model of depression , 2011, Nature Reviews Neuroscience.