Phase 3 diagnostic evaluation of a smart tablet serious game to identify autism in 760 children 3-5 years old in Sweden and the United Kingdom

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

Research output: Contribution to journalArticle

Abstract

Introduction 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 subsecond 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-matched and gender-matched controls with 93% accuracy, presenting an attractive assessment method suitable for use in the home, clinic or classroom. Methods and analysis This is a phase III prospective, diagnostic classification study designed according to the Standards for Reporting Diagnostic Accuracy Studies guidelines. Three cohorts are investigated: children typically developing (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, UK 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) 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 in the ASD and OND groups will complete three questionnaires: Strengths and Difficulties Questionnaire; Early Symptomatic Syndromes Eliciting Neurodevelopmental Clinical Examinations Questionnaire and the Adaptive Behavioural Assessment System-3 or Vineland Adaptive Behavior Scales-II. The primary outcome measure is sensitivity and specificity of Play.Care to differentiate ASD children from TD children. Secondary outcomes measures include the accuracy of Play.Care to differentiate ASD children from OND children. Ethics and dissemination This study was approved by the West of Scotland Research Ethics Service Committee 3 and the University of Strathclyde Ethics Committee. Results will be disseminated in peer-reviewed publications and at international scientific conferences. Trial registration number NCT03438994; Pre-results.

LanguageEnglish
Article numbere026226
Number of pages7
JournalBMJ Open
Volume9
Issue number7
DOIs
Publication statusPublished - 16 Jul 2019

Fingerprint

Autistic Disorder
autism
Sweden
Tablets
diagnostic
evaluation
Touch screens
Biomarkers
Learning systems
Data acquisition
Sensors
questionnaire
moral philosophy
Outcome Assessment (Health Care)
United Kingdom
Serious games
Autism Spectrum Disorder
Ethics Committees
research ethics
Research Ethics Committees

Keywords

  • autism
  • diagnosis
  • digital health
  • machine learning
  • motor control
  • smart technology
  • autism spectrum disorder (ASD)

Cite this

Millar, Lindsay ; McConnachie, Alex ; Minnis, Helen ; Wilson, Philip ; Thompson, Lucy ; Anzulewicz, Anna ; Sobota, Krzysztof ; Rowe, Philip ; Gillberg, Christopher ; Delafield-Butt, Jonathan. / Phase 3 diagnostic evaluation of a smart tablet serious game to identify autism in 760 children 3-5 years old in Sweden and the United Kingdom. In: BMJ Open. 2019 ; Vol. 9, No. 7.
@article{6202654e98dc4547a88df1a978a0a9cd,
title = "Phase 3 diagnostic evaluation of a smart tablet serious game to identify autism in 760 children 3-5 years old in Sweden and the United Kingdom",
abstract = "Introduction 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 subsecond 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-matched and gender-matched controls with 93{\%} accuracy, presenting an attractive assessment method suitable for use in the home, clinic or classroom. Methods and analysis This is a phase III prospective, diagnostic classification study designed according to the Standards for Reporting Diagnostic Accuracy Studies guidelines. Three cohorts are investigated: children typically developing (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, UK 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) 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 in the ASD and OND groups will complete three questionnaires: Strengths and Difficulties Questionnaire; Early Symptomatic Syndromes Eliciting Neurodevelopmental Clinical Examinations Questionnaire and the Adaptive Behavioural Assessment System-3 or Vineland Adaptive Behavior Scales-II. The primary outcome measure is sensitivity and specificity of Play.Care to differentiate ASD children from TD children. Secondary outcomes measures include the accuracy of Play.Care to differentiate ASD children from OND children. Ethics and dissemination This study was approved by the West of Scotland Research Ethics Service Committee 3 and the University of Strathclyde Ethics Committee. Results will be disseminated in peer-reviewed publications and at international scientific conferences. Trial registration number NCT03438994; Pre-results.",
keywords = "autism, diagnosis, digital health, machine learning, motor control, smart technology, autism spectrum disorder (ASD)",
author = "Lindsay Millar and Alex McConnachie and Helen Minnis and Philip Wilson and Lucy Thompson and Anna Anzulewicz and Krzysztof Sobota and Philip Rowe and Christopher Gillberg and Jonathan Delafield-Butt",
year = "2019",
month = "7",
day = "16",
doi = "10.1136/bmjopen-2018-026226",
language = "English",
volume = "9",
journal = "BMJ Open",
issn = "2044-6055",
number = "7",

}

Phase 3 diagnostic evaluation of a smart tablet serious game to identify autism in 760 children 3-5 years old in Sweden and the United Kingdom. / Millar, Lindsay; McConnachie, Alex; Minnis, Helen; Wilson, Philip; Thompson, Lucy ; Anzulewicz, Anna; Sobota, Krzysztof; Rowe, Philip; Gillberg, Christopher; Delafield-Butt, Jonathan.

In: BMJ Open, Vol. 9, No. 7, e026226, 16.07.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Phase 3 diagnostic evaluation of a smart tablet serious game to identify autism in 760 children 3-5 years old in Sweden and the United Kingdom

AU - Millar, Lindsay

AU - McConnachie, Alex

AU - Minnis, Helen

AU - Wilson, Philip

AU - Thompson, Lucy

AU - Anzulewicz, Anna

AU - Sobota, Krzysztof

AU - Rowe, Philip

AU - Gillberg, Christopher

AU - Delafield-Butt, Jonathan

PY - 2019/7/16

Y1 - 2019/7/16

N2 - Introduction 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 subsecond 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-matched and gender-matched controls with 93% accuracy, presenting an attractive assessment method suitable for use in the home, clinic or classroom. Methods and analysis This is a phase III prospective, diagnostic classification study designed according to the Standards for Reporting Diagnostic Accuracy Studies guidelines. Three cohorts are investigated: children typically developing (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, UK 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) 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 in the ASD and OND groups will complete three questionnaires: Strengths and Difficulties Questionnaire; Early Symptomatic Syndromes Eliciting Neurodevelopmental Clinical Examinations Questionnaire and the Adaptive Behavioural Assessment System-3 or Vineland Adaptive Behavior Scales-II. The primary outcome measure is sensitivity and specificity of Play.Care to differentiate ASD children from TD children. Secondary outcomes measures include the accuracy of Play.Care to differentiate ASD children from OND children. Ethics and dissemination This study was approved by the West of Scotland Research Ethics Service Committee 3 and the University of Strathclyde Ethics Committee. Results will be disseminated in peer-reviewed publications and at international scientific conferences. Trial registration number NCT03438994; Pre-results.

AB - Introduction 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 subsecond 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-matched and gender-matched controls with 93% accuracy, presenting an attractive assessment method suitable for use in the home, clinic or classroom. Methods and analysis This is a phase III prospective, diagnostic classification study designed according to the Standards for Reporting Diagnostic Accuracy Studies guidelines. Three cohorts are investigated: children typically developing (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, UK 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) 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 in the ASD and OND groups will complete three questionnaires: Strengths and Difficulties Questionnaire; Early Symptomatic Syndromes Eliciting Neurodevelopmental Clinical Examinations Questionnaire and the Adaptive Behavioural Assessment System-3 or Vineland Adaptive Behavior Scales-II. The primary outcome measure is sensitivity and specificity of Play.Care to differentiate ASD children from TD children. Secondary outcomes measures include the accuracy of Play.Care to differentiate ASD children from OND children. Ethics and dissemination This study was approved by the West of Scotland Research Ethics Service Committee 3 and the University of Strathclyde Ethics Committee. Results will be disseminated in peer-reviewed publications and at international scientific conferences. Trial registration number NCT03438994; Pre-results.

KW - autism

KW - diagnosis

KW - digital health

KW - machine learning

KW - motor control

KW - smart technology

KW - autism spectrum disorder (ASD)

UR - https://bmjopen.bmj.com/content/9/7/e026226

U2 - 10.1136/bmjopen-2018-026226

DO - 10.1136/bmjopen-2018-026226

M3 - Article

VL - 9

JO - BMJ Open

T2 - BMJ Open

JF - BMJ Open

SN - 2044-6055

IS - 7

M1 - e026226

ER -