A diagnostic evaluation of tablet serious games for the assessment of autism spectrum disorder in young children

Lindsay Millar, Alex McConnachie, Helen Minnis, Phil Wilson, Lucy Thompson, Anna Anzulewicz, Krzysztof Sobota, Philip Rowe, Christopher Gillberg, Jonathan Delafield-Butt

Research output: Contribution to journalArticle

Abstract

Recent evidence suggests an underlying movement disruption may be a core component of Autism Spectrum Disorder (ASD) and a new, accessible early biomarker. Mobile smart technologies such as iPads contain inertial movement and touch-screen sensors capable of recording sub second movement patterns during gameplay. A previous pilot study employed machine learning analysis of motor patterns recorded from children 3-5 years old. It identified those with ASD from age- and gender-matched controls with 93% accuracy, presenting an attractive assessment method suitable for use in the home, clinic or classroom. This is a Phase III prospective, diagnostic classification study designed according to the Standards for Reporting Diagnostic Accuracy Studies (STARD) guidelines. Three cohorts are investigated: children developing typically (TD); children with a clinical diagnosis of ASD; and children with a diagnosis of another neurodevelopmental disorder (OND) that is not ASD. The study will be completed in Glasgow, U.K., and Gothenburg, Sweden. The recruitment target is 760 children (280 TD, 280 ASD and 200 OND). Children play two games on the iPad then a third party data acquisition and analysis algorithm (Play.Care, Harimata sp. z o.o., Poland) will classify the data as positively or negatively associated with ASD. The results are blind until data collection is complete, when the algorithm’s classification will be compared against medical diagnosis. Furthermore, parents of participants will complete three questionnaires: Strengths and Difficulties Questionnaire; ESSENCE Questionnaire; and the Adaptive Behavioural Assessment System. The primary outcome measure is sensitivity and specificity of Play.Care to detect ASD. Secondary outcomes include the ability of Play.Care to differentiate ASD from OND.
LanguageEnglish
Pages1-17
Number of pages17
JournalPsyArXiv Preprints
DOIs
Publication statusPublished - 31 Oct 2018

Fingerprint

Tablets
Aptitude
Autism Spectrum Disorder
Poland
Sweden
Biomarkers
Parents
Outcome Assessment (Health Care)
Guidelines
Technology
Sensitivity and Specificity
Surveys and Questionnaires

Keywords

  • autism
  • diagnosis
  • digital health
  • machine learning
  • motor control
  • smart technology

Cite this

Millar, Lindsay ; McConnachie, Alex ; Minnis, Helen ; Wilson, Phil ; Thompson, Lucy ; Anzulewicz, Anna ; Sobota, Krzysztof ; Rowe, Philip ; Gillberg, Christopher ; Delafield-Butt, Jonathan. / A diagnostic evaluation of tablet serious games for the assessment of autism spectrum disorder in young children. In: PsyArXiv Preprints. 2018 ; pp. 1-17.
@article{82c892c0a5074b85a4492fb1d63649ab,
title = "A diagnostic evaluation of tablet serious games for the assessment of autism spectrum disorder in young children",
abstract = "Recent evidence suggests an underlying movement disruption may be a core component of Autism Spectrum Disorder (ASD) and a new, accessible early biomarker. Mobile smart technologies such as iPads contain inertial movement and touch-screen sensors capable of recording sub second movement patterns during gameplay. A previous pilot study employed machine learning analysis of motor patterns recorded from children 3-5 years old. It identified those with ASD from age- and gender-matched controls with 93{\%} accuracy, presenting an attractive assessment method suitable for use in the home, clinic or classroom. This is a Phase III prospective, diagnostic classification study designed according to the Standards for Reporting Diagnostic Accuracy Studies (STARD) guidelines. Three cohorts are investigated: children developing typically (TD); children with a clinical diagnosis of ASD; and children with a diagnosis of another neurodevelopmental disorder (OND) that is not ASD. The study will be completed in Glasgow, U.K., and Gothenburg, Sweden. The recruitment target is 760 children (280 TD, 280 ASD and 200 OND). Children play two games on the iPad then a third party data acquisition and analysis algorithm (Play.Care, Harimata sp. z o.o., Poland) will classify the data as positively or negatively associated with ASD. The results are blind until data collection is complete, when the algorithm’s classification will be compared against medical diagnosis. Furthermore, parents of participants will complete three questionnaires: Strengths and Difficulties Questionnaire; ESSENCE Questionnaire; and the Adaptive Behavioural Assessment System. The primary outcome measure is sensitivity and specificity of Play.Care to detect ASD. Secondary outcomes include the ability of Play.Care to differentiate ASD from OND.",
keywords = "autism, diagnosis, digital health, machine learning, motor control, smart technology",
author = "Lindsay Millar and Alex McConnachie and Helen Minnis and Phil Wilson and Lucy Thompson and Anna Anzulewicz and Krzysztof Sobota and Philip Rowe and Christopher Gillberg and Jonathan Delafield-Butt",
year = "2018",
month = "10",
day = "31",
doi = "10.31234/osf.io/hdjwe",
language = "English",
pages = "1--17",
journal = "PsyArXiv Preprints",

}

A diagnostic evaluation of tablet serious games for the assessment of autism spectrum disorder in young children. / Millar, Lindsay; McConnachie, Alex; Minnis, Helen; Wilson, Phil; Thompson, Lucy ; Anzulewicz, Anna; Sobota, Krzysztof; Rowe, Philip; Gillberg, Christopher; Delafield-Butt, Jonathan.

In: PsyArXiv Preprints, 31.10.2018, p. 1-17.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A diagnostic evaluation of tablet serious games for the assessment of autism spectrum disorder in young children

AU - Millar, Lindsay

AU - McConnachie, Alex

AU - Minnis, Helen

AU - Wilson, Phil

AU - Thompson, Lucy

AU - Anzulewicz, Anna

AU - Sobota, Krzysztof

AU - Rowe, Philip

AU - Gillberg, Christopher

AU - Delafield-Butt, Jonathan

PY - 2018/10/31

Y1 - 2018/10/31

N2 - Recent evidence suggests an underlying movement disruption may be a core component of Autism Spectrum Disorder (ASD) and a new, accessible early biomarker. Mobile smart technologies such as iPads contain inertial movement and touch-screen sensors capable of recording sub second movement patterns during gameplay. A previous pilot study employed machine learning analysis of motor patterns recorded from children 3-5 years old. It identified those with ASD from age- and gender-matched controls with 93% accuracy, presenting an attractive assessment method suitable for use in the home, clinic or classroom. This is a Phase III prospective, diagnostic classification study designed according to the Standards for Reporting Diagnostic Accuracy Studies (STARD) guidelines. Three cohorts are investigated: children developing typically (TD); children with a clinical diagnosis of ASD; and children with a diagnosis of another neurodevelopmental disorder (OND) that is not ASD. The study will be completed in Glasgow, U.K., and Gothenburg, Sweden. The recruitment target is 760 children (280 TD, 280 ASD and 200 OND). Children play two games on the iPad then a third party data acquisition and analysis algorithm (Play.Care, Harimata sp. z o.o., Poland) will classify the data as positively or negatively associated with ASD. The results are blind until data collection is complete, when the algorithm’s classification will be compared against medical diagnosis. Furthermore, parents of participants will complete three questionnaires: Strengths and Difficulties Questionnaire; ESSENCE Questionnaire; and the Adaptive Behavioural Assessment System. The primary outcome measure is sensitivity and specificity of Play.Care to detect ASD. Secondary outcomes include the ability of Play.Care to differentiate ASD from OND.

AB - Recent evidence suggests an underlying movement disruption may be a core component of Autism Spectrum Disorder (ASD) and a new, accessible early biomarker. Mobile smart technologies such as iPads contain inertial movement and touch-screen sensors capable of recording sub second movement patterns during gameplay. A previous pilot study employed machine learning analysis of motor patterns recorded from children 3-5 years old. It identified those with ASD from age- and gender-matched controls with 93% accuracy, presenting an attractive assessment method suitable for use in the home, clinic or classroom. This is a Phase III prospective, diagnostic classification study designed according to the Standards for Reporting Diagnostic Accuracy Studies (STARD) guidelines. Three cohorts are investigated: children developing typically (TD); children with a clinical diagnosis of ASD; and children with a diagnosis of another neurodevelopmental disorder (OND) that is not ASD. The study will be completed in Glasgow, U.K., and Gothenburg, Sweden. The recruitment target is 760 children (280 TD, 280 ASD and 200 OND). Children play two games on the iPad then a third party data acquisition and analysis algorithm (Play.Care, Harimata sp. z o.o., Poland) will classify the data as positively or negatively associated with ASD. The results are blind until data collection is complete, when the algorithm’s classification will be compared against medical diagnosis. Furthermore, parents of participants will complete three questionnaires: Strengths and Difficulties Questionnaire; ESSENCE Questionnaire; and the Adaptive Behavioural Assessment System. The primary outcome measure is sensitivity and specificity of Play.Care to detect ASD. Secondary outcomes include the ability of Play.Care to differentiate ASD from OND.

KW - autism

KW - diagnosis

KW - digital health

KW - machine learning

KW - motor control

KW - smart technology

U2 - 10.31234/osf.io/hdjwe

DO - 10.31234/osf.io/hdjwe

M3 - Article

SP - 1

EP - 17

JO - PsyArXiv Preprints

T2 - PsyArXiv Preprints

JF - PsyArXiv Preprints

ER -