Development of an Objective Autism Risk Index Using Remote Eye Tracking

Thomas W. Frazier, Eric W. Klingemier, Mary Beukemann, Leslie Speer, Leslie Markowitz, Sumit Parikh, Steven Wexberg, Kimberly Giuliano, Elaine E. Schulte, Carol Delahunty, Veena Ahuja, Charis Eng, Michael J. Manos, Antonio Y. Hardan, Eric A. Youngstrom, Mark S. Strauss

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Objective Abnormal eye gaze is a hallmark characteristic of autism spectrum disorder (ASD), and numerous studies have identified abnormal attention patterns in ASD. The primary aim of the present study was to create an objective, eye tracking-based autism risk index. Method In initial and replication studies, children were recruited after referral for comprehensive multidisciplinary evaluation of ASD and subsequently grouped by clinical consensus diagnosis (ASD n = 25/15, non-ASD n = 20/19 for initial/replication samples). Remote eye tracking was blinded to diagnosis and included multiple stimuli. Dwell times were recorded to each a priori-defined region of interest (ROI) and averaged across ROIs to create an autism risk index. Receiver operating characteristic curve analyses examined classification accuracy. Correlations with clinical measures evaluated whether the autism risk index was associated with autism symptom severity independent of language ability. Results In both samples, the autism risk index had high diagnostic accuracy (area under the curve [AUC] = 0.91 and 0.85, 95% CIs = 0.81-0.98 and 0.71-0.96), was strongly associated with Autism Diagnostic Observation Schedule-Second Edition (ADOS-2) severity scores (r = 0.58 and 0.59, p <.001), and not significantly correlated with language ability (r ≤| -0.28|, p >.095). Conclusion The autism risk index may be a useful quantitative and objective measure of risk for autism in at-risk settings. Future research in larger samples is needed to cross-validate these findings. If validated and scaled for clinical use, this measure could inform clinical judgment regarding ASD diagnosis and track symptom improvements.

Original languageEnglish (US)
Pages (from-to)301-309
Number of pages9
JournalJournal of the American Academy of Child and Adolescent Psychiatry
Volume55
Issue number4
DOIs
StatePublished - Apr 1 2016
Externally publishedYes

Fingerprint

Autistic Disorder
Aptitude
ROC Curve
Area Under Curve
Appointments and Schedules
Language
Referral and Consultation
Observation
Autism Spectrum Disorder

Keywords

  • autism spectrum disorder
  • autism symptoms
  • objective measure
  • remote eye tracking
  • risk

ASJC Scopus subject areas

  • Developmental and Educational Psychology
  • Psychiatry and Mental health

Cite this

Frazier, T. W., Klingemier, E. W., Beukemann, M., Speer, L., Markowitz, L., Parikh, S., ... Strauss, M. S. (2016). Development of an Objective Autism Risk Index Using Remote Eye Tracking. Journal of the American Academy of Child and Adolescent Psychiatry, 55(4), 301-309. https://doi.org/10.1016/j.jaac.2016.01.011

Development of an Objective Autism Risk Index Using Remote Eye Tracking. / Frazier, Thomas W.; Klingemier, Eric W.; Beukemann, Mary; Speer, Leslie; Markowitz, Leslie; Parikh, Sumit; Wexberg, Steven; Giuliano, Kimberly; Schulte, Elaine E.; Delahunty, Carol; Ahuja, Veena; Eng, Charis; Manos, Michael J.; Hardan, Antonio Y.; Youngstrom, Eric A.; Strauss, Mark S.

In: Journal of the American Academy of Child and Adolescent Psychiatry, Vol. 55, No. 4, 01.04.2016, p. 301-309.

Research output: Contribution to journalArticle

Frazier, TW, Klingemier, EW, Beukemann, M, Speer, L, Markowitz, L, Parikh, S, Wexberg, S, Giuliano, K, Schulte, EE, Delahunty, C, Ahuja, V, Eng, C, Manos, MJ, Hardan, AY, Youngstrom, EA & Strauss, MS 2016, 'Development of an Objective Autism Risk Index Using Remote Eye Tracking', Journal of the American Academy of Child and Adolescent Psychiatry, vol. 55, no. 4, pp. 301-309. https://doi.org/10.1016/j.jaac.2016.01.011
Frazier, Thomas W. ; Klingemier, Eric W. ; Beukemann, Mary ; Speer, Leslie ; Markowitz, Leslie ; Parikh, Sumit ; Wexberg, Steven ; Giuliano, Kimberly ; Schulte, Elaine E. ; Delahunty, Carol ; Ahuja, Veena ; Eng, Charis ; Manos, Michael J. ; Hardan, Antonio Y. ; Youngstrom, Eric A. ; Strauss, Mark S. / Development of an Objective Autism Risk Index Using Remote Eye Tracking. In: Journal of the American Academy of Child and Adolescent Psychiatry. 2016 ; Vol. 55, No. 4. pp. 301-309.
@article{d3e13405f8db4ea288ee92f254e3d2b5,
title = "Development of an Objective Autism Risk Index Using Remote Eye Tracking",
abstract = "Objective Abnormal eye gaze is a hallmark characteristic of autism spectrum disorder (ASD), and numerous studies have identified abnormal attention patterns in ASD. The primary aim of the present study was to create an objective, eye tracking-based autism risk index. Method In initial and replication studies, children were recruited after referral for comprehensive multidisciplinary evaluation of ASD and subsequently grouped by clinical consensus diagnosis (ASD n = 25/15, non-ASD n = 20/19 for initial/replication samples). Remote eye tracking was blinded to diagnosis and included multiple stimuli. Dwell times were recorded to each a priori-defined region of interest (ROI) and averaged across ROIs to create an autism risk index. Receiver operating characteristic curve analyses examined classification accuracy. Correlations with clinical measures evaluated whether the autism risk index was associated with autism symptom severity independent of language ability. Results In both samples, the autism risk index had high diagnostic accuracy (area under the curve [AUC] = 0.91 and 0.85, 95{\%} CIs = 0.81-0.98 and 0.71-0.96), was strongly associated with Autism Diagnostic Observation Schedule-Second Edition (ADOS-2) severity scores (r = 0.58 and 0.59, p <.001), and not significantly correlated with language ability (r ≤| -0.28|, p >.095). Conclusion The autism risk index may be a useful quantitative and objective measure of risk for autism in at-risk settings. Future research in larger samples is needed to cross-validate these findings. If validated and scaled for clinical use, this measure could inform clinical judgment regarding ASD diagnosis and track symptom improvements.",
keywords = "autism spectrum disorder, autism symptoms, objective measure, remote eye tracking, risk",
author = "Frazier, {Thomas W.} and Klingemier, {Eric W.} and Mary Beukemann and Leslie Speer and Leslie Markowitz and Sumit Parikh and Steven Wexberg and Kimberly Giuliano and Schulte, {Elaine E.} and Carol Delahunty and Veena Ahuja and Charis Eng and Manos, {Michael J.} and Hardan, {Antonio Y.} and Youngstrom, {Eric A.} and Strauss, {Mark S.}",
year = "2016",
month = "4",
day = "1",
doi = "10.1016/j.jaac.2016.01.011",
language = "English (US)",
volume = "55",
pages = "301--309",
journal = "Journal of the American Academy of Child and Adolescent Psychiatry",
issn = "0890-8567",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Development of an Objective Autism Risk Index Using Remote Eye Tracking

AU - Frazier, Thomas W.

AU - Klingemier, Eric W.

AU - Beukemann, Mary

AU - Speer, Leslie

AU - Markowitz, Leslie

AU - Parikh, Sumit

AU - Wexberg, Steven

AU - Giuliano, Kimberly

AU - Schulte, Elaine E.

AU - Delahunty, Carol

AU - Ahuja, Veena

AU - Eng, Charis

AU - Manos, Michael J.

AU - Hardan, Antonio Y.

AU - Youngstrom, Eric A.

AU - Strauss, Mark S.

PY - 2016/4/1

Y1 - 2016/4/1

N2 - Objective Abnormal eye gaze is a hallmark characteristic of autism spectrum disorder (ASD), and numerous studies have identified abnormal attention patterns in ASD. The primary aim of the present study was to create an objective, eye tracking-based autism risk index. Method In initial and replication studies, children were recruited after referral for comprehensive multidisciplinary evaluation of ASD and subsequently grouped by clinical consensus diagnosis (ASD n = 25/15, non-ASD n = 20/19 for initial/replication samples). Remote eye tracking was blinded to diagnosis and included multiple stimuli. Dwell times were recorded to each a priori-defined region of interest (ROI) and averaged across ROIs to create an autism risk index. Receiver operating characteristic curve analyses examined classification accuracy. Correlations with clinical measures evaluated whether the autism risk index was associated with autism symptom severity independent of language ability. Results In both samples, the autism risk index had high diagnostic accuracy (area under the curve [AUC] = 0.91 and 0.85, 95% CIs = 0.81-0.98 and 0.71-0.96), was strongly associated with Autism Diagnostic Observation Schedule-Second Edition (ADOS-2) severity scores (r = 0.58 and 0.59, p <.001), and not significantly correlated with language ability (r ≤| -0.28|, p >.095). Conclusion The autism risk index may be a useful quantitative and objective measure of risk for autism in at-risk settings. Future research in larger samples is needed to cross-validate these findings. If validated and scaled for clinical use, this measure could inform clinical judgment regarding ASD diagnosis and track symptom improvements.

AB - Objective Abnormal eye gaze is a hallmark characteristic of autism spectrum disorder (ASD), and numerous studies have identified abnormal attention patterns in ASD. The primary aim of the present study was to create an objective, eye tracking-based autism risk index. Method In initial and replication studies, children were recruited after referral for comprehensive multidisciplinary evaluation of ASD and subsequently grouped by clinical consensus diagnosis (ASD n = 25/15, non-ASD n = 20/19 for initial/replication samples). Remote eye tracking was blinded to diagnosis and included multiple stimuli. Dwell times were recorded to each a priori-defined region of interest (ROI) and averaged across ROIs to create an autism risk index. Receiver operating characteristic curve analyses examined classification accuracy. Correlations with clinical measures evaluated whether the autism risk index was associated with autism symptom severity independent of language ability. Results In both samples, the autism risk index had high diagnostic accuracy (area under the curve [AUC] = 0.91 and 0.85, 95% CIs = 0.81-0.98 and 0.71-0.96), was strongly associated with Autism Diagnostic Observation Schedule-Second Edition (ADOS-2) severity scores (r = 0.58 and 0.59, p <.001), and not significantly correlated with language ability (r ≤| -0.28|, p >.095). Conclusion The autism risk index may be a useful quantitative and objective measure of risk for autism in at-risk settings. Future research in larger samples is needed to cross-validate these findings. If validated and scaled for clinical use, this measure could inform clinical judgment regarding ASD diagnosis and track symptom improvements.

KW - autism spectrum disorder

KW - autism symptoms

KW - objective measure

KW - remote eye tracking

KW - risk

UR - http://www.scopus.com/inward/record.url?scp=84959387761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959387761&partnerID=8YFLogxK

U2 - 10.1016/j.jaac.2016.01.011

DO - 10.1016/j.jaac.2016.01.011

M3 - Article

VL - 55

SP - 301

EP - 309

JO - Journal of the American Academy of Child and Adolescent Psychiatry

JF - Journal of the American Academy of Child and Adolescent Psychiatry

SN - 0890-8567

IS - 4

ER -