Diagnosis of autism through EEG processed by advanced computational algorithms: A pilot study

BACKGROUND Multi-Scale Ranked Organizing Map coupled with Implicit Function as Squashing Time algorithm(MS-ROM/I-FAST) is a new, complex system based on Artificial Neural networks (ANNs) able to extract features of interest in computerized EEG through the analysis of few minutes of their EEG without any preliminary pre-processing. A proof of concept study previously published showed accuracy values ranging from 94%-98% in discerning subjects with Mild Cognitive Impairment and/or Alzheimer's Disease from healthy elderly people. The presence of deviant patterns in simple resting state EEG recordings in autism, consistent with the atypical organization of the cerebral cortex present, prompted us in applying this potent analytical systems in search of a EEG signature of the disease. AIM OF THE STUDY The aim of the study is to assess how effectively this methodology distinguishes subjects with autism from typically developing ones. METHODS Fifteen definite ASD subjects (13 males; 2 females; age range 7-14; mean value = 10.4) and ten typically developing subjects (4 males; 6 females; age range 7-12; mean value 9.2) were included in the study. Patients received Autism diagnoses according to DSM-V criteria, subsequently confirmed by the ADOS scale. A segment of artefact-free EEG lasting 60 seconds was used to compute input values for subsequent analyses. MS-ROM/I-FAST coupled with a well-documented evolutionary system able to select predictive features (TWIST) created an invariant features vector input of EEG on which supervised machine learning systems acted as blind classifiers. RESULTS The overall predictive capability of machine learning system in sorting out autistic cases from normal control amounted consistently to 100% with all kind of systems employed using training-testing protocol and to 84% - 92.8% using Leave One Out protocol. The similarities among the ANN weight matrixes measured with apposite algorithms were not affected by the age of the subjects. This suggests that the ANNs do not read age-related EEG patterns, but rather invariant features related to the brain's underlying disconnection signature. CONCLUSION This pilot study seems to open up new avenues for the development of non-invasive diagnostic testing for the early detection of ASD.

[1]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[2]  T. Kemper,et al.  Histoanatomic observations of the brain in early infantile autism , 1985, Neurology.

[3]  Paolo Massimo Buscema,et al.  The IFAST model, a novel parallel nonlinear EEG analysis technique, distinguishes mild cognitive impairment and Alzheimer's disease patients with high degree of accuracy , 2007, Artif. Intell. Medicine.

[4]  M. Sigman,et al.  A big-world network in ASD: Dynamical connectivity analysis reflects a deficit in long-range connections and an excess of short-range connections , 2010, Neuropsychologia.

[5]  John J. Foxe,et al.  Neurophysiological Indices of Atypical Auditory Processing and Multisensory Integration are Associated with Symptom Severity in Autism , 2014, Journal of Autism and Developmental Disorders.

[6]  S. Rogers,et al.  Brief report: Early intervention in autism , 1996, Journal of autism and developmental disorders.

[7]  Janet B W Williams,et al.  Diagnostic and Statistical Manual of Mental Disorders , 2013 .

[8]  B. Kowalski,et al.  K-Nearest Neighbor Classification Rule (pattern recognition) applied to nuclear magnetic resonance spectral interpretation , 1972 .

[9]  Brian Reichow,et al.  Overview of Meta-Analyses on Early Intensive Behavioral Intervention for Young Children with Autism Spectrum Disorders , 2011, Journal of Autism and Developmental Disorders.

[10]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[11]  Pat Langley,et al.  Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[12]  Eric Courchesne,et al.  Patches of disorganization in the neocortex of children with autism. , 2014, The New England journal of medicine.

[13]  A. Chauhan,et al.  Brain Region–Specific Decrease in the Activity and Expression of Protein Kinase A in the Frontal Cortex of Regressive Autism , 2011, PloS one.

[14]  Massimo Buscema,et al.  Training with Input Selection and Testing (TWIST) Algorithm: A Significant Advance in Pattern Recognition Performance of Machine Learning , 2013 .

[15]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

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

[17]  C. Nelson,et al.  EEG complexity as a biomarker for autism spectrum disorder risk , 2011, BMC medicine.

[18]  G. Lyon,et al.  NEUROPATHOLOGICAL STUDY OF A CASE OF AUTISTIC SYNDROME WITH SEVERE MENTAL RETARDATION , 1996, Developmental medicine and child neurology.

[19]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[20]  Madalena Costa,et al.  Multiscale entropy analysis of biological signals. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[21]  R. Landa.  Early communication development and intervention for children with autism. , 2007, Mental retardation and developmental disabilities research reviews.

[22]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[23]  C Babiloni,et al.  The I.F.A.S.T. model allows the prediction of conversion to Alzheimer disease in patients with mild cognitive impairment with high degree of accuracy. , 2010, Current Alzheimer research.

[24]  M. Casanova,et al.  Review: Cortical construction in autism spectrum disorder: columns, connectivity and the subplate , 2016, Neuropathology and applied neurobiology.

[25]  Massimo Buscema,et al.  Is it possible to automatically distinguish resting EEG data of normal elderly vs. mild cognitive impairment subjects with high degree of accuracy? , 2008, Clinical Neurophysiology.

[26]  Irina Rish,et al.  An empirical study of the naive Bayes classifier , 2001 .

[27]  M. Kendall,et al.  Rank Correlation Methods , 1949 .

[28]  R. Thuraisingham,et al.  On multiscale entropy analysis for physiological data , 2006 .

[29]  S. Cessie,et al.  Ridge Estimators in Logistic Regression , 1992 .

[30]  T. Kemper,et al.  Neuropathology of infantile autism. , 1998, Journal of neuropathology and experimental neurology.

[31]  Massimo Buscema,et al.  A global immune deficit in Alzheimer's disease and mild cognitive impairment disclosed by a novel data mining process. , 2014, Journal of Alzheimer's disease : JAD.

[32]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[33]  Irva Hertz-Picciotto,et al.  The CHARGE Study: An Epidemiologic Investigation of Genetic and Environmental Factors Contributing to Autism , 2006, Environmental health perspectives.

[34]  S. Sathiya Keerthi,et al.  Convergence of a Generalized SMO Algorithm for SVM Classifier Design , 2002, Machine Learning.

[35]  F. Volkmar,et al.  Practice parameter for the assessment and treatment of children and adolescents with autism spectrum disorder. , 2014, Journal of the American Academy of Child and Adolescent Psychiatry.

[36]  D. Pinto,et al.  Rare familial 16q21 microdeletions under a linkage peak implicate cadherin 8 (CDH8) in susceptibility to autism and learning disability , 2010, Journal of Medical Genetics.

[37]  Massimo Buscema,et al.  K-CM: a new artificial neural network. Application to supervised pattern recognition , 2014 .

[38]  Paolo Massimo Buscema,et al.  An improved I-FAST system for the diagnosis of Alzheimer's disease from unprocessed electroencephalograms by using robust invariant features , 2015, Artif. Intell. Medicine.

[39]  A. Bailey,et al.  A clinicopathological study of autism. , 1998, Brain : a journal of neurology.

[40]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .