Che Zawiyah Che Hasan, Rozita Jailani, Nooritawati Md Tahir
artificial neural network, autism spectrum disorders, gait classification, gait feature, kinematic, statistical analysis, stepwise discriminant analysis
Autism spectrum disorders (ASD) are a permanent neurological disorder that can be recognized at the early stage of the developmental period and are recently associated with movement disturbances. The aim of this study was to classify gait abnormalities in children with ASD based on their respective three-dimensional (3D) kinematic data. The gait analysis of 30 ASD children and 30 normal healthy children was assessed using a state-of-the-art 3D motion analysis system during self-selected speed barefoot walking. Kinematic gait features from the sagittal, frontal and transverse joint angles waveforms at the pelvis, hip, knee, and ankle were extracted using time-series parameterization. Two statistical analysis techniques, namely the between-group tests (independent samples t-test and Mann-Whitney U test) and stepwise discriminant analysis (SWDA) were adopted as feature selector to select the dominant gait features that were then used for the purpose of training and testing of the artificial neural networks (ANN). The results indicate that the selected gait features using SWDA technique are more reliable for ASD gait classification with 91.7% accuracy, 93.3% sensitivity, and 90.0% specificity. These promising findings suggest that the kinematic gait features with the combination of SWDA feature selector and ANN classifier are potentially effective for the diagnosis of ASD gait patterns. Early detection of gait abnormalities could ensure rapid quantitative clinical decision and further facilitate for appropriate treatments to the ASD patients needing therapies.
Cite this paper
Che Zawiyah Che Hasan, Rozita Jailani, Nooritawati Md Tahir. (2017) Automated Classification of Gait Abnormalities in Children with Autism Spectrum Disorders Based on Kinematic Data. International Journal of Psychiatry and Psychotherapy, 2, 10-15