Multi-view classification of psychiatric conditions based on saccades

Graphical abstractDisplay Omitted HighlightsUsing saccadic information to classify different psychiatric conditions.Classifiers could be used to reduce the possible diagnoses for a given patient.Simple descriptors are extracted from the saccades.Fictitious saccades help to improve the classification accuracy. Early diagnosis of psychiatric conditions can be enhanced by taking into account eye movement behavior. However, the implementation of prediction algorithms which are able to assist physicians in the diagnostic is a difficult task. In this paper we propose, for the first time, an automatic approach for classification of multiple psychiatric conditions based on saccades. In particular, the goal is to classify 6 medical conditions: Alcoholism, Alzheimer's disease, opioid dependence (two groups of subjects with measurements respectively taken prior to and after administering synthetic opioid), Parkinson's disease, and Schizophrenia. Our approach integrates different feature spaces corresponding to complementary characterizations of the saccadic behavior. We define a multi-view model of saccades in which the feature representations capture characteristic temporal and amplitude patterns of saccades. Four of the current most advanced classification methods are used to discriminate among the psychiatric conditions and leave-one-out cross-validation is used to evaluate the classifiers. Classification accuracies well above the chance levels are obtained for the different classification tasks investigated. The confusion matrices reveal that it is possible to separate conditions into different groups. We conclude that using relatively simple descriptors of the saccadic behavior it is possible to simultaneously classify among 6 different types of psychiatric conditions. Conceptually, our multi-view classification method excels other approaches that focus on statistical differences in the saccadic behavior of cases and controls because it can be used for predicting unseen cases. Classification integrating different characterizations of the saccades can actually help to predict the conditions of new patients, opening the possibility to integrate automatic analysis of saccades as a practical procedure for differential diagnosis in Psychiatry.

[1]  P. Rolan,et al.  Utility of saccadic eye movement analysis as an objective biomarker to detect the sedative interaction between opioids and sleep deprivation in opioid-naive and opioid-tolerant populations , 2010, Journal of psychopharmacology.

[2]  Piotr Habela,et al.  Data Mining and Machine Learning on the Basis from Reflexive Eye Movements Can Predict Symptom Development in Individual Parkinson's Patients , 2014, MICAI.

[3]  J. Sharpe,et al.  Saccadic eye movement dysfunction in Alzheimer's disease , 1986, Annals of neurology.

[4]  Yongdong Zhang,et al.  Multiview Spectral Embedding , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[5]  Chusak Limsakul,et al.  Evaluating Feature Extraction Methods of Electrooculography (EOG) Signal for Human-Computer Interface , 2012 .

[6]  L. Crevits,et al.  Antisaccades and remembered saccades in mild traumatic brain injury , 2000, Journal of Neurology.

[7]  Pawel Kasprowski,et al.  Enhancing eye-movement-based biometric identification method by using voting classifiers , 2005, SPIE Defense + Commercial Sensing.

[8]  Roberto Hornero,et al.  Neural network based detection of hard exudates in retinal images , 2009, Comput. Methods Programs Biomed..

[9]  Cecilia R. Aragon,et al.  Biometric authentication via oculomotor plant characteristics , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[10]  José Antonio Lozano,et al.  Using Multidimensional Bayesian Network Classifiers to Assist the Treatment of Multiple Sclerosis , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[11]  Gerhard Tröster,et al.  Eye Movement Analysis for Activity Recognition Using Electrooculography , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Concha Bielza,et al.  Affinity propagation enhanced by estimation of distribution algorithms , 2011, GECCO '11.

[13]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[14]  B. Fischer,et al.  Characteristics of “anti” saccades in man , 2004, Experimental Brain Research.

[15]  Michele Leone,et al.  Clustering by soft-constraint affinity propagation: applications to gene-expression data , 2007, Bioinform..

[16]  M. Mazo,et al.  System for assisted mobility using eye movements based on electrooculography , 2002, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[17]  C. Masters,et al.  Spectrum of saccade system function in Alzheimer disease. , 2003, Archives of neurology.

[18]  Daniel W. Hommer,et al.  A quantitative analysis of saccades and smooth pursuit during visual pursuit tracking A comparison of schizophrenics with normals and substance abusing controls , 1992, Schizophrenia Research.

[19]  Aboul Ella Hassanien,et al.  A random forest classifier for lymph diseases , 2014, Comput. Methods Programs Biomed..

[20]  Sean O'Connor,et al.  Saccadic eye movements are associated with a family history of alcoholism at baseline and after exposure to alcohol. , 2002, Alcoholism, clinical and experimental research.

[21]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[22]  Concha Bielza,et al.  Machine Learning in Bioinformatics , 2008, Encyclopedia of Database Systems.

[23]  Richard D. Jones,et al.  Impaired eye movements in post-concussion syndrome indicate suboptimal brain function beyond the influence of depression, malingering or intellectual ability. , 2009, Brain : a journal of neurology.

[24]  Johnalan Keegan,et al.  An electrooculogram-based binary saccade sequence classification (BSSC) technique for augmentative communication and control , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[25]  Dimitrios I. Fotiadis,et al.  A six stage approach for the diagnosis of the Alzheimer's disease based on fMRI data , 2010, J. Biomed. Informatics.

[26]  David W. Aha,et al.  Instance-Based Learning Algorithms , 1991, Machine Learning.

[27]  W A Fletcher,et al.  Smooth pursuit dysfunction in Alzheimer's disease , 1988, Neurology.

[28]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[29]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[30]  D. Munoz,et al.  Altered control of visual fixation and saccadic eye movements in attention-deficit hyperactivity disorder. , 2003, Journal of neurophysiology.

[31]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[32]  J. Felblinger,et al.  Saccadic eye movement changes in Parkinson's disease dementia and dementia with Lewy bodies. , 2005, Brain : a journal of neurology.

[33]  Oleg V. Komogortsev,et al.  Standardization of Automated Analyses of Oculomotor Fixation and Saccadic Behaviors , 2010, IEEE Transactions on Biomedical Engineering.

[34]  Andreas Ziegler,et al.  Mining data with random forests: current options for real‐world applications , 2014, Wiley Interdiscip. Rev. Data Min. Knowl. Discov..

[35]  Pedro Larrañaga,et al.  Learning Factorizations in Estimation of Distribution Algorithms Using Affinity Propagation , 2010, Evolutionary Computation.

[36]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[37]  A.R. Kherlopian,et al.  Electrooculogram based system for computer control using a multiple feature classification model , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[38]  Mario Dzemidzic,et al.  Comparison of vertical and horizontal saccade measures and their relation to gray matter changes in premanifest and manifest Huntington disease , 2012, Journal of Neurology.