Prediction of the autism spectrum disorder diagnosis with linear discriminant analysis classifier and K-nearest neighbor in children

Abstract

Autism Spectrum Disorder (ASD) negatively affects the whole life of people. The main indications of ASD are seen as lack of social interaction and communication, repetitive patterns of behavior, fixed interests and activities. It is very important that ASD is diagnosed at an early age. In this study, the classification method for ASD diagnosis was used in children aged 4–11 years. The Linear Discriminant Analysis (LDA) and The K-Nearest Neighbor (KNN) algorithms are used for classification. To test the algorithms, 30 percent of the data set was selected as test data and 70 percent as training data. As a result of the work done; In the LDA algorithm, the accuracy is 90.8%, whereas the accuracy of the KNN algorithm is 88.5%. For the LDA algorithm, sensitivity and specificity values are calculated as 0.9524 and .08667, respectively. For KNN algorithm, these values are calculated as 0.9762 and 0.80. F-measure values are calculated as 0.9091 for the LDA algorithm and 0.8913 for the KNN algorithm.