{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Natraj S"],"funding":["Swiss National Science Foundation","The Fondation Pôle Autisme","Private Foundation of the HUG","UNIGE COINF2018 equipment grant","National Centre of Competence in Research (NCCR) Synapsy","Sinergia Grant for Digital Phenotyping of Autism Spectrum Disorders in Children"],"pagination":["e0308388"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11449333"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["19(10)"],"pubmed_abstract":["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."],"journal":["PloS one"],"pubmed_title":["Video-audio neural network ensemble for comprehensive screening of autism spectrum disorder in young children."],"pmcid":["PMC11449333"],"funding_grant_id":["#163859 and #190084","51NF40_185897","202235"],"pubmed_authors":["Natraj S","Kojovic N","Maillart T","Schaer M"],"additional_accession":[]},"is_claimable":false,"name":"Video-audio neural network ensemble for comprehensive screening of autism spectrum disorder in young children.","description":"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.","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024","modification":"2025-04-04T02:36:14.277Z","creation":"2025-04-04T02:36:14.277Z"},"accession":"S-EPMC11449333","cross_references":{"pubmed":["39361665"],"doi":["10.1371/journal.pone.0308388"]}}