A Fusion-Based Machine Learning Approach for Autism Detection in Young Children Using Magnetoencephalography Signals / Katsumi WATANABE ; Joydeep BHATTACHARYA ; Goutam SAHA in Journal of Autism and Developmental Disorders, 53-12 (December 2023)  

Public ISBD [article]  inJournal of Autism and Developmental Disorders > 53-12 (December 2023) . - p.4830-4848 Titre : A Fusion-Based Machine Learning Approach for Autism Detection in Young Children Using Magnetoencephalography Signals Type de document : Texte imprimé et/ou numérique Auteurs : Katsumi WATANABE, Auteur ; Joydeep BHATTACHARYA, Auteur ; Goutam SAHA, Auteur Article en page(s) : p.4830-4848 Langues : Anglais (eng) Index. décimale : PER Périodiques Résumé : In this study, we aimed to find biomarkers of autism in young children. We recorded magnetoencephalography (MEG) in thirty children (4-7 years) with autism and thirty age, gender-matched controls while they were watching cartoons. We focused on characterizing neural oscillations by amplitude (power spectral density, PSD) and phase (preferred phase angle, PPA). Machine learning based classifier showed a higher classification accuracy (88%) for PPA features than PSD features (82%). Further, by a novel fusion method combining PSD and PPA features, we achieved an average classification accuracy of 94% and 98% for feature-level and score-level fusion, respectively. These findings reveal discriminatory patterns of neural oscillations of autism in young children and provide novel insight into autism pathophysiology. En ligne : https://doi.org/10.1007/s10803-022-05767-w Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=515 [article] A Fusion-Based Machine Learning Approach for Autism Detection in Young Children Using Magnetoencephalography Signals [Texte imprimé et/ou numérique] / Katsumi WATANABE, Auteur ; Joydeep BHATTACHARYA, Auteur ; Goutam SAHA, Auteur . - p.4830-4848. Langues : Anglais (eng) in Journal of Autism and Developmental Disorders > 53-12 (December 2023) . - p.4830-4848 Index. décimale : PER Périodiques Résumé : In this study, we aimed to find biomarkers of autism in young children. We recorded magnetoencephalography (MEG) in thirty children (4-7 years) with autism and thirty age, gender-matched controls while they were watching cartoons. We focused on characterizing neural oscillations by amplitude (power spectral density, PSD) and phase (preferred phase angle, PPA). Machine learning based classifier showed a higher classification accuracy (88%) for PPA features than PSD features (82%). Further, by a novel fusion method combining PSD and PPA features, we achieved an average classification accuracy of 94% and 98% for feature-level and score-level fusion, respectively. These findings reveal discriminatory patterns of neural oscillations of autism in young children and provide novel insight into autism pathophysiology. En ligne : https://doi.org/10.1007/s10803-022-05767-w Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=515

---

1 (1 - 1 / 1)