A Machine Learning-Based Analysis of Game Data for Attention Deficit Hyperactivity Disorder Assessment

Monika D. Heller, Kurt Roots, Sanjana Srivastava, Jennifer Schumann, Jaideep Srivastava, T. Sigi Hale

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Objective: Attention deficit hyperactivity disorder (ADHD) is found in 9.5 percent of the U.S. population and poses lifelong challenges. Current diagnostic approaches rely on evaluation forms completed by teachers and/or parents, although they are not specifically trained to recognize cognitive disorders. The most accurate diagnosis is by a psychiatrist, often only available to children with severe symptoms. Development of a tool that is engaging and objective and aids medical providers is needed in the diagnosis of ADHD. The goal of this research is to work toward the development of such a tool. Materials and Methods: The proposed approach takes advantage of two trends: The rapid adoption of tangible user interface devices and the popularity of interactive videogames. CogCubed Inc. (Minneapolis, MN) has created "Groundskeeper," a game on the Sifteo Cubes (Sifteo, Inc., San Francisco, CA) game system with elements that exercise skills affected by ADHD. "Groundskeeper" was evaluated for 52 patients, with and without ADHD. Gameplay data were mathematically transformed into ADHD-indicative feature variables and subjected to machine learning algorithms to develop diagnostic models to aid psychiatric clinical assessments of ADHD. The effectiveness of the developed model was evaluated against the diagnostic impressions of two licensed child/adolescent psychiatrists using semistructured interviews. Results: Our predictive algorithms were highly accurate in correctly predicting diagnoses based on gameplay of "Groundskeeper." The F-measure, a measure of diagnosis accuracy, from the predictive models gave values as follows: ADHD, inattentive type, 78 percent (P>0.05); ADHD, combined type, 75 percent (P<0.05); anxiety disorders, 71%; and depressive disorders, 76%. Conclusions: This represents a promising new approach to screening tools for ADHD.

Original languageEnglish
Pages (from-to)291-298
Number of pages8
JournalGames for health journal
Volume2
Issue number5
DOIs
Publication statusPublished - 1 Oct 2013
Externally publishedYes

Fingerprint

ADHD
Attention Deficit Disorder with Hyperactivity
Learning systems
learning
Psychiatry
diagnostic
Learning algorithms
psychiatrist
User interfaces
Screening
Machine Learning
San Francisco
predictive model
Depressive Disorder
Anxiety Disorders
user interface
popularity
parents
Parents
Interviews

ASJC Scopus subject areas

  • Health(social science)
  • Computer Science Applications
  • Public Health, Environmental and Occupational Health
  • Rehabilitation

Cite this

A Machine Learning-Based Analysis of Game Data for Attention Deficit Hyperactivity Disorder Assessment. / Heller, Monika D.; Roots, Kurt; Srivastava, Sanjana; Schumann, Jennifer; Srivastava, Jaideep; Hale, T. Sigi.

In: Games for health journal, Vol. 2, No. 5, 01.10.2013, p. 291-298.

Research output: Contribution to journalArticle

Heller, Monika D. ; Roots, Kurt ; Srivastava, Sanjana ; Schumann, Jennifer ; Srivastava, Jaideep ; Hale, T. Sigi. / A Machine Learning-Based Analysis of Game Data for Attention Deficit Hyperactivity Disorder Assessment. In: Games for health journal. 2013 ; Vol. 2, No. 5. pp. 291-298.
@article{8742d5e0c5aa4f4fa20a755c01894fce,
title = "A Machine Learning-Based Analysis of Game Data for Attention Deficit Hyperactivity Disorder Assessment",
abstract = "Objective: Attention deficit hyperactivity disorder (ADHD) is found in 9.5 percent of the U.S. population and poses lifelong challenges. Current diagnostic approaches rely on evaluation forms completed by teachers and/or parents, although they are not specifically trained to recognize cognitive disorders. The most accurate diagnosis is by a psychiatrist, often only available to children with severe symptoms. Development of a tool that is engaging and objective and aids medical providers is needed in the diagnosis of ADHD. The goal of this research is to work toward the development of such a tool. Materials and Methods: The proposed approach takes advantage of two trends: The rapid adoption of tangible user interface devices and the popularity of interactive videogames. CogCubed Inc. (Minneapolis, MN) has created {"}Groundskeeper,{"} a game on the Sifteo Cubes (Sifteo, Inc., San Francisco, CA) game system with elements that exercise skills affected by ADHD. {"}Groundskeeper{"} was evaluated for 52 patients, with and without ADHD. Gameplay data were mathematically transformed into ADHD-indicative feature variables and subjected to machine learning algorithms to develop diagnostic models to aid psychiatric clinical assessments of ADHD. The effectiveness of the developed model was evaluated against the diagnostic impressions of two licensed child/adolescent psychiatrists using semistructured interviews. Results: Our predictive algorithms were highly accurate in correctly predicting diagnoses based on gameplay of {"}Groundskeeper.{"} The F-measure, a measure of diagnosis accuracy, from the predictive models gave values as follows: ADHD, inattentive type, 78 percent (P>0.05); ADHD, combined type, 75 percent (P<0.05); anxiety disorders, 71{\%}; and depressive disorders, 76{\%}. Conclusions: This represents a promising new approach to screening tools for ADHD.",
author = "Heller, {Monika D.} and Kurt Roots and Sanjana Srivastava and Jennifer Schumann and Jaideep Srivastava and Hale, {T. Sigi}",
year = "2013",
month = "10",
day = "1",
doi = "10.1089/g4h.2013.0058",
language = "English",
volume = "2",
pages = "291--298",
journal = "Games for health journal",
issn = "2161-783X",
publisher = "Mary Ann Liebert Inc.",
number = "5",

}

TY - JOUR

T1 - A Machine Learning-Based Analysis of Game Data for Attention Deficit Hyperactivity Disorder Assessment

AU - Heller, Monika D.

AU - Roots, Kurt

AU - Srivastava, Sanjana

AU - Schumann, Jennifer

AU - Srivastava, Jaideep

AU - Hale, T. Sigi

PY - 2013/10/1

Y1 - 2013/10/1

N2 - Objective: Attention deficit hyperactivity disorder (ADHD) is found in 9.5 percent of the U.S. population and poses lifelong challenges. Current diagnostic approaches rely on evaluation forms completed by teachers and/or parents, although they are not specifically trained to recognize cognitive disorders. The most accurate diagnosis is by a psychiatrist, often only available to children with severe symptoms. Development of a tool that is engaging and objective and aids medical providers is needed in the diagnosis of ADHD. The goal of this research is to work toward the development of such a tool. Materials and Methods: The proposed approach takes advantage of two trends: The rapid adoption of tangible user interface devices and the popularity of interactive videogames. CogCubed Inc. (Minneapolis, MN) has created "Groundskeeper," a game on the Sifteo Cubes (Sifteo, Inc., San Francisco, CA) game system with elements that exercise skills affected by ADHD. "Groundskeeper" was evaluated for 52 patients, with and without ADHD. Gameplay data were mathematically transformed into ADHD-indicative feature variables and subjected to machine learning algorithms to develop diagnostic models to aid psychiatric clinical assessments of ADHD. The effectiveness of the developed model was evaluated against the diagnostic impressions of two licensed child/adolescent psychiatrists using semistructured interviews. Results: Our predictive algorithms were highly accurate in correctly predicting diagnoses based on gameplay of "Groundskeeper." The F-measure, a measure of diagnosis accuracy, from the predictive models gave values as follows: ADHD, inattentive type, 78 percent (P>0.05); ADHD, combined type, 75 percent (P<0.05); anxiety disorders, 71%; and depressive disorders, 76%. Conclusions: This represents a promising new approach to screening tools for ADHD.

AB - Objective: Attention deficit hyperactivity disorder (ADHD) is found in 9.5 percent of the U.S. population and poses lifelong challenges. Current diagnostic approaches rely on evaluation forms completed by teachers and/or parents, although they are not specifically trained to recognize cognitive disorders. The most accurate diagnosis is by a psychiatrist, often only available to children with severe symptoms. Development of a tool that is engaging and objective and aids medical providers is needed in the diagnosis of ADHD. The goal of this research is to work toward the development of such a tool. Materials and Methods: The proposed approach takes advantage of two trends: The rapid adoption of tangible user interface devices and the popularity of interactive videogames. CogCubed Inc. (Minneapolis, MN) has created "Groundskeeper," a game on the Sifteo Cubes (Sifteo, Inc., San Francisco, CA) game system with elements that exercise skills affected by ADHD. "Groundskeeper" was evaluated for 52 patients, with and without ADHD. Gameplay data were mathematically transformed into ADHD-indicative feature variables and subjected to machine learning algorithms to develop diagnostic models to aid psychiatric clinical assessments of ADHD. The effectiveness of the developed model was evaluated against the diagnostic impressions of two licensed child/adolescent psychiatrists using semistructured interviews. Results: Our predictive algorithms were highly accurate in correctly predicting diagnoses based on gameplay of "Groundskeeper." The F-measure, a measure of diagnosis accuracy, from the predictive models gave values as follows: ADHD, inattentive type, 78 percent (P>0.05); ADHD, combined type, 75 percent (P<0.05); anxiety disorders, 71%; and depressive disorders, 76%. Conclusions: This represents a promising new approach to screening tools for ADHD.

UR - http://www.scopus.com/inward/record.url?scp=84994032338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994032338&partnerID=8YFLogxK

U2 - 10.1089/g4h.2013.0058

DO - 10.1089/g4h.2013.0058

M3 - Article

VL - 2

SP - 291

EP - 298

JO - Games for health journal

JF - Games for health journal

SN - 2161-783X

IS - 5

ER -