EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Video-audio neural network ensemble for comprehensive screening of autism spectrum disorder in young children

Shreyasvi Natraj iD, Nada Kojovic, Thomas Maillart, Marie Schaer

PLOS ONE · 03.10.2024 · 19 (10) · e0308388

DOI: 10.1371/journal.pone.0308388 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 03.10.2024. Verfasst von Shreyasvi Natraj und 3 weiteren Autor:innen. Beteiligte Einrichtung: Psychiatry Department, Faculty of Medicine, University of Geneva, Geneva, Switzerland. Hauptthemen laut MEDLINE: Autism Spectrum Disorder, Neural Networks, Computer. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sinergia Grant for Digital Phenotyping of Autism Spectrum Disorders in Children, National Centre of Competence in Research (NCCR) Synapsy, Swiss National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A timely diagnosis of autism is paramount to allow early therapeutic intervention in preschoolers. Deep Learning tools have been increasingly used to identify specific autistic symptoms. But they also offer opportunities for broad automated detection of autism at an early age. Here, we leverage a multi-modal approach by combining two neural networks trained on video and audio features of semi-standardized social interactions in a sample of 160 children aged 1 to 5 years old. Our ensemble model performs with an accuracy of 82.5% (F1 score: 0.816, Precision: 0.775, Recall: 0.861) for screening Autism Spectrum Disorders (ASD). Additional combinations of our model were developed to achieve higher specificity (92.5%, i.e., few false negatives) or sensitivity (90%, i.e. few false positives). Finally, we found a relationship between the neural network modalities and specific audio versus video ASD characteristics, bringing evidence that our neural network implementation was effective in taking into account different features that are currently standardized under the gold standard ASD assessment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Autism Spectrum DisorderNeural Networks, ComputerHumansChild, PreschoolMaleFemaleInfantVideo RecordingDeep LearningMass Screening

Autor:innen und Institutionen

  • Psychiatry Department, Faculty of Medicine, University of Geneva, Geneva, Switzerland.
  • Geneva School of Economics and Management, University of Geneva, Geneva, Switzerland.

ORCID-Profile: Shreyasvi Natraj

Förderung

  • Sinergia Grant for Digital Phenotyping of Autism Spectrum Disorders in Children
  • National Centre of Competence in Research (NCCR) Synapsy
  • Swiss National Science Foundation
  • Private Foundation of the HUG
  • UNIGE COINF2018 equipment grant
  • The Fondation Pôle Autisme

Zitieren

APA

Natraj, S., Kojovic, N., Maillart, T., & Schaer, M. (2024). Video-audio neural network ensemble for comprehensive screening of autism spectrum disorder in young children. PLOS ONE, 19(10), e0308388. https://doi.org/10.1371/journal.pone.0308388

Vancouver

Natraj S, Kojovic N, Maillart T, Schaer M. Video-audio neural network ensemble for comprehensive screening of autism spectrum disorder in young children. PLOS ONE. 2024;19(10):e0308388. doi:10.1371/journal.pone.0308388

BibTeX
@article{Natraj2024,
  author = {Natraj, Shreyasvi and Kojovic, Nada and Maillart, Thomas and Schaer, Marie},
  title = {Video-audio neural network ensemble for comprehensive screening of autism spectrum disorder in young children},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {10},
  pages = {e0308388},
  doi = {10.1371/journal.pone.0308388}
}
Kostenlos starten →