Using Machine Learning to compare walking patterns in children with and without autism

  • Rinehart, Nicole (Primary Chief Investigator (PCI))
  • Venkatesh, Svetha (Chief Investigator (CI))
  • Le, Vuong (Chief Investigator (CI))
  • Saha, Budhaditya (Chief Investigator (CI))
  • Enticott, Peter (Chief Investigator (CI))
  • Lum, Jarrad A.G. (Chief Investigator (CI))
  • Papadopoulos, Nicole (Chief Investigator (CI))
  • Barata de Morais, Romero Fernando Almeida (Chief Investigator (CI))
  • James, Lachlan (Chief Investigator (CI))
  • Whelan, Moira (Chief Investigator (CI))
  • Painter, Felicity (Chief Investigator (CI))
  • Alberts, Zoe (Chief Investigator (CI))

Project: Research

Project Details

Project Description

This research will be the first to use machine-learning techniques to analyse children’s patterns of walking. The analysis of these patterns may be used to detect unique differences in walking patterns in children with ASD, which may be further developed into a diagnostic tool for ASD in the future. Thus, the current study aims to use a machine learning algorithm to detect gait and postural disturbances of children with a diagnosis of ASD while walking, in comparison to a group of children without an ASD diagnosis. These results may be used to develop a marker pattern of ASD-related motor impairment, which could further be developed into a novel and objective diagnostic tool in the future. The primary aim of this study is to understand if digital videos of children walking, analysed using novel machine learning techniques, can be used to find unique patterns which may help detect developmental differences in children with a diagnosis of ASD, relative to children without this diagnosis.
Effective start/end date1/08/181/08/22


  • gait
  • Machine learning