Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
, 12 (8), e0182652
eCollection

Applying Machine Learning to Identify Autistic Adults Using Imitation: An Exploratory Study

Affiliations

Applying Machine Learning to Identify Autistic Adults Using Imitation: An Exploratory Study

Baihua Li et al. PLoS One.

Abstract

Autism spectrum condition (ASC) is primarily diagnosed by behavioural symptoms including social, sensory and motor aspects. Although stereotyped, repetitive motor movements are considered during diagnosis, quantitative measures that identify kinematic characteristics in the movement patterns of autistic individuals are poorly studied, preventing advances in understanding the aetiology of motor impairment, or whether a wider range of motor characteristics could be used for diagnosis. The aim of this study was to investigate whether data-driven machine learning based methods could be used to address some fundamental problems with regard to identifying discriminative test conditions and kinematic parameters to classify between ASC and neurotypical controls. Data was based on a previous task where 16 ASC participants and 14 age, IQ matched controls observed then imitated a series of hand movements. 40 kinematic parameters extracted from eight imitation conditions were analysed using machine learning based methods. Two optimal imitation conditions and nine most significant kinematic parameters were identified and compared with some standard attribute evaluators. To our knowledge, this is the first attempt to apply machine learning to kinematic movement parameters measured during imitation of hand movements to investigate the identification of ASC. Although based on a small sample, the work demonstrates the feasibility of applying machine learning methods to analyse high-dimensional data and suggest the potential of machine learning for identifying kinematic biomarkers that could contribute to the diagnostic classification of autism.

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Time-lapse diagram of experiment.
Each trial began with a fixation cross, followed by a still image of a hand and a video clip of a hand sequence. Participants imitated when the exclamation mark appeared.
Fig 2
Fig 2. Position, velocity and acceleration traces for a rightward pointing hand movement.
a) position in horizontal (blue) and vertical (red) directions. b) velocity in horizontal direction. c) acceleration in horizontal direction. Roman numerals refer to kinematic parameters in Table 2
Fig 3
Fig 3. Histograms of kinematic parameters of NTF (Non-Targeted Fast, left column) and NTE (Non-Targeted Elevated, right column) experimental conditions.
Fig 4
Fig 4. Average weights of SVMs trained on 40 NTF/NTE standard deviations showing importance of kinematic parameters.
The 1st-20 th SD parameters are from NTF and the followings 20 parameters are from NTE. The parameter index are in order as shown in Table 2.
Fig 5
Fig 5. Average impact on accuracy when dropping one kinematic parameter out.
The 1st-20 th SD parameters are from NTF and the followings 20 parameters are from NTE, in order as shown in Table 2.
Fig 6
Fig 6. Occurrences of kinematic features selected at each iteration.
The 1st-20 th parameters are from NTF and the followings 20 parameters are from NTE. The index are in order as shown in Table 2.

Similar articles

See all similar articles

References

    1. American Psychiatric Association, Diagnostic and statistical manual of mental disorders (5th ed.). Arlington, VA: American Psychiatric Publishing; 2013.
    1. Gowen E, Hamilton A. Motor abilities in autism: a review using a computational context. Journal of autism and developmental disorders. 2013;43(2):323–344. 10.1007/s10803-012-1574-0 - DOI - PubMed
    1. Fournier KA, Hass CJ, Naik SK, Lodha N, Cauraugh JH. Motor coordination in autism spectrum disorders: a synthesis and meta-analysis. Journal of autism and developmental disorders. 40(10):1227–1240. 10.1007/s10803-010-0981-3 - DOI - PubMed
    1. Bhat AN, Landa RJ, Galloway JCC. Current perspectives on motor functioning in infants, children, and adults with autism spectrum disorders. Physical Therapy. 2011;91(7):1116–1129. 10.2522/ptj.20100294 - DOI - PubMed
    1. Torres EB, Donnellan AM. Autism: The movement perspective. Frontiers Media; SA; 2015. - PMC - PubMed

Grant support

Original data collection was funded by a Medical Research Council DTA Studentship.
Feedback