Identification of smile events using automated facial expression recognition during the Autism Diagnostic Observation Schedule (ADOS-2): a proof-of-principle study

IntroductionThe diagnosis of autism spectrum disorder (ASD) is resource-intensive and associated with long waiting times. Digital screenings using facial expression recognition (FER) are a promising approach to accelerate the diagnostic process while increasing its sensitivity and specificity. The a...

Full description

Saved in:
Bibliographic Details
Main Authors: Maria Dotzer, Ulrike Kachel, Jan Huhsmann, Hendrik Huscher, Nils Raveling, Klaus Kugelmann, Stefanie Blank, Isabel Neitzel, Michael Buschermöhle, Georg G. von Polier, Daniel Radeloff
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Psychiatry
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1497583/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849322978672640000
author Maria Dotzer
Ulrike Kachel
Jan Huhsmann
Hendrik Huscher
Nils Raveling
Klaus Kugelmann
Stefanie Blank
Isabel Neitzel
Michael Buschermöhle
Georg G. von Polier
Daniel Radeloff
author_facet Maria Dotzer
Ulrike Kachel
Jan Huhsmann
Hendrik Huscher
Nils Raveling
Klaus Kugelmann
Stefanie Blank
Isabel Neitzel
Michael Buschermöhle
Georg G. von Polier
Daniel Radeloff
author_sort Maria Dotzer
collection DOAJ
description IntroductionThe diagnosis of autism spectrum disorder (ASD) is resource-intensive and associated with long waiting times. Digital screenings using facial expression recognition (FER) are a promising approach to accelerate the diagnostic process while increasing its sensitivity and specificity. The aim of this study is to examine whether the identification of smile events using FER in an autism diagnosis utilisation population is reliable.MethodsFrom video recordings of children undergoing the Autism Diagnostic Observation Schedule (ADOS-2) due to suspected ASD, sequences showing smile and non-smile events were identified. It is being investigated whether the FER reliably recognizes smile events and corresponds to a human rating.ResultsThe FER based on the facial action unit mouthSmile accurately identifies smile events with a sensitivity of 96.43% and a specificity of 96.08%. A very high agreement with human raters (κ = 0.918) was achieved.DiscussionThis study demonstrates that smile events can in principle be identified using FER in a clinical utilisation population of children with suspected autism. Further studies are required to generalise the results.
format Article
id doaj-art-4ce82d43321a45128c4ed5f2c8e9ae39
institution Kabale University
issn 1664-0640
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Psychiatry
spelling doaj-art-4ce82d43321a45128c4ed5f2c8e9ae392025-08-20T03:49:12ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402025-05-011610.3389/fpsyt.2025.14975831497583Identification of smile events using automated facial expression recognition during the Autism Diagnostic Observation Schedule (ADOS-2): a proof-of-principle studyMaria Dotzer0Ulrike Kachel1Jan Huhsmann2Hendrik Huscher3Nils Raveling4Klaus Kugelmann5Stefanie Blank6Isabel Neitzel7Michael Buschermöhle8Georg G. von Polier9Daniel Radeloff10Department of Child and Adolescent Psychiatry, Psychotherapy and Psychosomatics, University Hospital Leipzig, Leipzig, GermanyDepartment of Child and Adolescent Psychiatry, Psychotherapy and Psychosomatics, University Hospital Leipzig, Leipzig, GermanyKIZMO GmbH - Clinical Innovation Center for Medical Technology, Oldenburg, GermanyKIZMO GmbH - Clinical Innovation Center for Medical Technology, Oldenburg, GermanyKIZMO GmbH - Clinical Innovation Center for Medical Technology, Oldenburg, GermanySpeechCare GmbH, Leverkusen, GermanyBranch for Hearing, Speech and Audio Technology HSA, Fraunhofer Institute for Digital Media Technology IDMT, Oldenburg, GermanyResearch Unit of Language and Communication, Department of Rehabilitation Sciences, TU Dortmund University, Dortmund, GermanyKIZMO GmbH - Clinical Innovation Center for Medical Technology, Oldenburg, GermanyDepartment of Child and Adolescent Psychiatry, Psychotherapy and Psychosomatics, University Hospital Leipzig, Leipzig, GermanyDepartment of Child and Adolescent Psychiatry, Psychotherapy and Psychosomatics, University Hospital Leipzig, Leipzig, GermanyIntroductionThe diagnosis of autism spectrum disorder (ASD) is resource-intensive and associated with long waiting times. Digital screenings using facial expression recognition (FER) are a promising approach to accelerate the diagnostic process while increasing its sensitivity and specificity. The aim of this study is to examine whether the identification of smile events using FER in an autism diagnosis utilisation population is reliable.MethodsFrom video recordings of children undergoing the Autism Diagnostic Observation Schedule (ADOS-2) due to suspected ASD, sequences showing smile and non-smile events were identified. It is being investigated whether the FER reliably recognizes smile events and corresponds to a human rating.ResultsThe FER based on the facial action unit mouthSmile accurately identifies smile events with a sensitivity of 96.43% and a specificity of 96.08%. A very high agreement with human raters (κ = 0.918) was achieved.DiscussionThis study demonstrates that smile events can in principle be identified using FER in a clinical utilisation population of children with suspected autism. Further studies are required to generalise the results.https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1497583/fullfacial expression recognitionADOSautism diagnosisdigital diagnosisROCsmile recognition
spellingShingle Maria Dotzer
Ulrike Kachel
Jan Huhsmann
Hendrik Huscher
Nils Raveling
Klaus Kugelmann
Stefanie Blank
Isabel Neitzel
Michael Buschermöhle
Georg G. von Polier
Daniel Radeloff
Identification of smile events using automated facial expression recognition during the Autism Diagnostic Observation Schedule (ADOS-2): a proof-of-principle study
Frontiers in Psychiatry
facial expression recognition
ADOS
autism diagnosis
digital diagnosis
ROC
smile recognition
title Identification of smile events using automated facial expression recognition during the Autism Diagnostic Observation Schedule (ADOS-2): a proof-of-principle study
title_full Identification of smile events using automated facial expression recognition during the Autism Diagnostic Observation Schedule (ADOS-2): a proof-of-principle study
title_fullStr Identification of smile events using automated facial expression recognition during the Autism Diagnostic Observation Schedule (ADOS-2): a proof-of-principle study
title_full_unstemmed Identification of smile events using automated facial expression recognition during the Autism Diagnostic Observation Schedule (ADOS-2): a proof-of-principle study
title_short Identification of smile events using automated facial expression recognition during the Autism Diagnostic Observation Schedule (ADOS-2): a proof-of-principle study
title_sort identification of smile events using automated facial expression recognition during the autism diagnostic observation schedule ados 2 a proof of principle study
topic facial expression recognition
ADOS
autism diagnosis
digital diagnosis
ROC
smile recognition
url https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1497583/full
work_keys_str_mv AT mariadotzer identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT ulrikekachel identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT janhuhsmann identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT hendrikhuscher identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT nilsraveling identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT klauskugelmann identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT stefanieblank identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT isabelneitzel identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT michaelbuschermohle identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT georggvonpolier identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy
AT danielradeloff identificationofsmileeventsusingautomatedfacialexpressionrecognitionduringtheautismdiagnosticobservationscheduleados2aproofofprinciplestudy