Combining voice and language features improves automated autism detection / Heather MACFARLANE in Autism Research, 15-7 (July 2022)  

Public ISBD [article]  inAutism Research > 15-7 (July 2022) . - p.1288-1300 Titre : Combining voice and language features improves automated autism detection Type de document : Texte imprimé et/ou numérique Auteurs : Heather MACFARLANE, Auteur ; Alexandra C. SALEM, Auteur ; Liu CHEN, Auteur ; Meysam ASGARI, Auteur ; Eric FOMBONNE, Auteur Article en page(s) : p.1288-1300 Langues : Anglais (eng) Mots-clés : autism  automated measures  communication  disfluency  natural language processing  pragmatic language  prosody  voice Index. décimale : PER Périodiques Résumé : Variability in expressive and receptive language, difficulty with pragmatic language, and prosodic difficulties are all features of autism spectrum disorder (ASD). Quantifying language and voice characteristics is an important step for measuring outcomes for autistic people, yet clinical measurement is cumbersome and costly. Using natural language processing (NLP) methods and a harmonic model of speech, we analyzed language transcripts and audio recordings to automatically classify individuals as ASD or non-ASD. One-hundred fifty-eight participants (88 ASD, 70 non-ASD) ages 7 to 17 were evaluated with the autism diagnostic observation schedule (ADOS-2), module 3. The ADOS-2 was transcribed following modified SALT guidelines. Seven automated language measures (ALMs) and 10 automated voice measures (AVMs) for each participant were generated from the transcripts and audio of one ADOS-2 task. The measures were analyzed using support vector machine (SVM; a binary classifier) and receiver operating characteristic (ROC). The AVM model resulted in an ROC area under the curve (AUC) of 0.7800, the ALM model an AUC of 0.8748, and the combined model a significantly improved AUC of 0.9205. The ALM model better detected ASD participants who were younger and had lower language skills and shorter activity time. ASD participants detected by the AVM model had better language profiles than those detected by the language model. In combination, automated measurement of language and voice characteristics successfully differentiated children with and without autism. This methodology could help design robust outcome measures for future research. LAY SUMMARY: People with autism often struggle with communication differences which traditional clinical measures and language tests cannot fully capture. Using language transcripts and audio recordings from 158 children ages 7 to 17, we showed that automated, objective language and voice measurements successfully predict the child's diagnosis. This methodology could help design improved outcome measures for research. En ligne : http://dx.doi.org/10.1002/aur.2733 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=477 [article] Combining voice and language features improves automated autism detection [Texte imprimé et/ou numérique] / Heather MACFARLANE, Auteur ; Alexandra C. SALEM, Auteur ; Liu CHEN, Auteur ; Meysam ASGARI, Auteur ; Eric FOMBONNE, Auteur . - p.1288-1300. Langues : Anglais (eng) in Autism Research > 15-7 (July 2022) . - p.1288-1300 Mots-clés : autism  automated measures  communication  disfluency  natural language processing  pragmatic language  prosody  voice Index. décimale : PER Périodiques Résumé : Variability in expressive and receptive language, difficulty with pragmatic language, and prosodic difficulties are all features of autism spectrum disorder (ASD). Quantifying language and voice characteristics is an important step for measuring outcomes for autistic people, yet clinical measurement is cumbersome and costly. Using natural language processing (NLP) methods and a harmonic model of speech, we analyzed language transcripts and audio recordings to automatically classify individuals as ASD or non-ASD. One-hundred fifty-eight participants (88 ASD, 70 non-ASD) ages 7 to 17 were evaluated with the autism diagnostic observation schedule (ADOS-2), module 3. The ADOS-2 was transcribed following modified SALT guidelines. Seven automated language measures (ALMs) and 10 automated voice measures (AVMs) for each participant were generated from the transcripts and audio of one ADOS-2 task. The measures were analyzed using support vector machine (SVM; a binary classifier) and receiver operating characteristic (ROC). The AVM model resulted in an ROC area under the curve (AUC) of 0.7800, the ALM model an AUC of 0.8748, and the combined model a significantly improved AUC of 0.9205. The ALM model better detected ASD participants who were younger and had lower language skills and shorter activity time. ASD participants detected by the AVM model had better language profiles than those detected by the language model. In combination, automated measurement of language and voice characteristics successfully differentiated children with and without autism. This methodology could help design robust outcome measures for future research. LAY SUMMARY: People with autism often struggle with communication differences which traditional clinical measures and language tests cannot fully capture. Using language transcripts and audio recordings from 158 children ages 7 to 17, we showed that automated, objective language and voice measurements successfully predict the child's diagnosis. This methodology could help design improved outcome measures for research. En ligne : http://dx.doi.org/10.1002/aur.2733 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=477

Higher or lower? Interpersonal behavioral and neural synchronization of movement imitation in autistic children / Wenjun ZHANG ; Liu CHEN ; Xiaorui DENG ; Kaiyun LI ; Fengxun LIN ; Fanlu JIA ; Shuhua SU ; Wanzhi TANG in Autism Research, 17-9 (September 2024)  

Public ISBD [article]  inAutism Research > 17-9 (September 2024) . - p.1876-1901 Titre : Higher or lower? Interpersonal behavioral and neural synchronization of movement imitation in autistic children Type de document : Texte imprimé et/ou numérique Auteurs : Wenjun ZHANG, Auteur ; Liu CHEN, Auteur ; Xiaorui DENG, Auteur ; Kaiyun LI, Auteur ; Fengxun LIN, Auteur ; Fanlu JIA, Auteur ; Shuhua SU, Auteur ; Wanzhi TANG, Auteur Article en page(s) : p.1876-1901 Langues : Anglais (eng) Mots-clés : Autism  movement imitation  interpersonal neural synchronization  functional near-infrared spectroscopy hyperscanning  an intra- and interindividual imitation mechanism model Index. décimale : PER Périodiques Résumé : Abstract How well autistic children can imitate movements and how their brain activity synchronizes with the person they are imitating have been understudied. The current study adopted functional near-infrared spectroscopy (fNIRS) hyperscanning and employed a task involving real interactions involving meaningful and meaningless movement imitation to explore the fundamental nature of imitation as a dynamic and interactive process. Experiment 1 explored meaningful and meaningless gesture imitation. The results revealed that autistic children exhibited lower imitation accuracy and behavioral synchrony than non-autistic children when imitating both meaningful and meaningless gestures. Specifically, compared to non-autistic children, autistic children displayed significantly higher interpersonal neural synchronization (INS) in the right inferior parietal lobule (r-IPL) (channel 12) when imitating meaningful gestures but lower INS when imitating meaningless gestures. Experiment 2 further investigated the imitation of four types of meaningless movements (orofacial movements, transitive movements, limb movements, and gestures). The results revealed that across all four movement types, autistic children exhibited significantly lower imitation accuracy, behavioral synchrony, and INS in the r-IPL (channel 12) than non-autistic children. This study is the first to identify INS as a biomarker of movement imitation difficulties in autistic individuals. Furthermore, an intra- and interindividual imitation mechanism model was proposed to explain the underlying causes of movement imitation difficulties in autistic individuals. En ligne : https://doi.org/10.1002/aur.3205 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=535 [article] Higher or lower? Interpersonal behavioral and neural synchronization of movement imitation in autistic children [Texte imprimé et/ou numérique] / Wenjun ZHANG, Auteur ; Liu CHEN, Auteur ; Xiaorui DENG, Auteur ; Kaiyun LI, Auteur ; Fengxun LIN, Auteur ; Fanlu JIA, Auteur ; Shuhua SU, Auteur ; Wanzhi TANG, Auteur . - p.1876-1901. Langues : Anglais (eng) in Autism Research > 17-9 (September 2024) . - p.1876-1901 Mots-clés : Autism  movement imitation  interpersonal neural synchronization  functional near-infrared spectroscopy hyperscanning  an intra- and interindividual imitation mechanism model Index. décimale : PER Périodiques Résumé : Abstract How well autistic children can imitate movements and how their brain activity synchronizes with the person they are imitating have been understudied. The current study adopted functional near-infrared spectroscopy (fNIRS) hyperscanning and employed a task involving real interactions involving meaningful and meaningless movement imitation to explore the fundamental nature of imitation as a dynamic and interactive process. Experiment 1 explored meaningful and meaningless gesture imitation. The results revealed that autistic children exhibited lower imitation accuracy and behavioral synchrony than non-autistic children when imitating both meaningful and meaningless gestures. Specifically, compared to non-autistic children, autistic children displayed significantly higher interpersonal neural synchronization (INS) in the right inferior parietal lobule (r-IPL) (channel 12) when imitating meaningful gestures but lower INS when imitating meaningless gestures. Experiment 2 further investigated the imitation of four types of meaningless movements (orofacial movements, transitive movements, limb movements, and gestures). The results revealed that across all four movement types, autistic children exhibited significantly lower imitation accuracy, behavioral synchrony, and INS in the r-IPL (channel 12) than non-autistic children. This study is the first to identify INS as a biomarker of movement imitation difficulties in autistic individuals. Furthermore, an intra- and interindividual imitation mechanism model was proposed to explain the underlying causes of movement imitation difficulties in autistic individuals. En ligne : https://doi.org/10.1002/aur.3205 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=535

---

1 (1 - 2 / 2)