A Simple Preprocessing Method Enhances Machine Learning Application to EEG Data for Differential Diagnosis of Autism

Abstract

A new pre-processing approach of EEG data to detect topological EEG features has been applied to a continuous segment of artifact-free EEG data lasting 10 minutes in ASCII format derived from 50 ASD children and 50 children with other Neuro-Psychiatric Disorders (NPD), matched for age and male/female ratios. Each EEG is transformed in a triangular matrix of 171 values expressing all reciprocal Manhattan distances among the 19 electrodes of to the international 10-20 system. From this matrix, the minimum spanning tree (MST) is calculated. Electrode identification serial codes sorted according to the decreasing number of links in MST, and the number of links in MST are taken as input vectors for machine learning systems.  Machine learning systems have been applied to build up a predictive model to distinguish between the two diagnostic classes (autism vs NPD) following a rigorous validation protocol. The best machine learning system (KNN algorithm) obtained a global accuracy of 93.2% (92.37 % sensitivity and 94.03 % specificity) in differentiating ASD subjects from NPD subjects. The results obtained in this study suggest that, thanks to the new pre-processing method introduced, there is the possibility to discriminate subjects with autism from subjects affected by other psychiatric disorders with a modest computational time reducing the information to 38 figures.