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 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] / 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 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] / 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

The intentional and spontaneous social motor synchrony of pre-school autistic children: Evidence from fNIRS hyperscanning and machine learning / Kaiyun LI in Journal of Child Psychology and Psychiatry, 67-6 (June 2026)  

Public ISBD [article]  inJournal of Child Psychology and Psychiatry > 67-6 (June 2026) . - p.881-895 Titre : The intentional and spontaneous social motor synchrony of pre-school autistic children: Evidence from fNIRS hyperscanning and machine learning Type de document : texte imprimé Auteurs : Kaiyun LI, Auteur ; Caiyan ZHENG, Auteur ; Yue YANG, Auteur ; Bang DU, Auteur ; Yaou ZHAO, Auteur ; Yuehui CHEN, Auteur ; Junqi LIU, Auteur ; Jiaxin CAI, Auteur ; Wenjing CHENG, Auteur ; Kezhen LV, Auteur ; Liu CHEN, Auteur ; Fanlu JIA, Auteur ; Shuhua SU, Auteur ; Wanzhi TANG, Auteur Article en page(s) : p.881-895 Langues : Anglais (eng) Mots-clés : Autistic children  social motor synchrony  interpersonal neural synchrony  fNIRS hyperscanning  machine learning Index. décimale : PER Périodiques Résumé : Background Social motor synchrony is critical for successful social interaction. It remains unclear whether autistic children exhibit distinct differences in intentional versus spontaneous social motor synchrony, as well as what underlying interpersonal neural synchrony (INS) mechanisms drive these potential differences. Method Fifty-four children (28 autistic) completed intentional (a delayed and synchronous imitation tasks in EX1) and spontaneous (a rhythmic hand-clapping task in EX2) tasks with an adult. Brain signals were collected by a portable multichannel fNIRS device and classified by GaussianNB machine learning approach. Results Compared with non-autistic children, autistic children showed: (1) significantly lower behavioral synchrony across both two experiments; (2) reduced activation in the right temporoparietal junction (r-TPJ, CH18) during Ex1, with no significant group differences in activation observed across all 20 fNIRS channels during Ex2; (3) significantly lower INS values in task-specific brain regions, that left inferior parietal lobule (l-IPL, CH3) in the delayed imitation condition in EX1; left inferior frontal gyrus (l-IFG, CH2), l-IPL (CH9), and r-TPJ (CH18) in the synchronous imitation condition in Ex1, and in the IPL (CH8, CH10-14) and r-TPJ (CH18) in Ex2. The GaussianNB model successfully discriminated between autistic and non-autistic children using task-related INS values, with classification accuracy varying by task condition, reaching 55.56% in the delayed imitation condition of EX1, 57.41% in the time-lag analysis condition of EX1, 64.81% in the synchronous imitation condition of EX1, and 74.07% in Ex2. Notably, the SHAP toolkit identified key channels driving group distinction?and these channels fully overlapped with the statistically significant INS channels identified in the analyses. Conclusions Autistic children exhibit differences in both intentional and spontaneous social motor synchrony, and these differences are linked to reduced INS in key social cognitive brain regions (IFG, IPL, TPJ). This research advances understanding of social functioning variations in autistic individuals and provides a foundational foundation for developing INS-based diagnostic tools. En ligne : https://doi.org/10.1111/jcpp.70079 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=587 [article] The intentional and spontaneous social motor synchrony of pre-school autistic children: Evidence from fNIRS hyperscanning and machine learning [texte imprimé] / Kaiyun LI, Auteur ; Caiyan ZHENG, Auteur ; Yue YANG, Auteur ; Bang DU, Auteur ; Yaou ZHAO, Auteur ; Yuehui CHEN, Auteur ; Junqi LIU, Auteur ; Jiaxin CAI, Auteur ; Wenjing CHENG, Auteur ; Kezhen LV, Auteur ; Liu CHEN, Auteur ; Fanlu JIA, Auteur ; Shuhua SU, Auteur ; Wanzhi TANG, Auteur . - p.881-895. Langues : Anglais (eng) in Journal of Child Psychology and Psychiatry > 67-6 (June 2026) . - p.881-895 Mots-clés : Autistic children  social motor synchrony  interpersonal neural synchrony  fNIRS hyperscanning  machine learning Index. décimale : PER Périodiques Résumé : Background Social motor synchrony is critical for successful social interaction. It remains unclear whether autistic children exhibit distinct differences in intentional versus spontaneous social motor synchrony, as well as what underlying interpersonal neural synchrony (INS) mechanisms drive these potential differences. Method Fifty-four children (28 autistic) completed intentional (a delayed and synchronous imitation tasks in EX1) and spontaneous (a rhythmic hand-clapping task in EX2) tasks with an adult. Brain signals were collected by a portable multichannel fNIRS device and classified by GaussianNB machine learning approach. Results Compared with non-autistic children, autistic children showed: (1) significantly lower behavioral synchrony across both two experiments; (2) reduced activation in the right temporoparietal junction (r-TPJ, CH18) during Ex1, with no significant group differences in activation observed across all 20 fNIRS channels during Ex2; (3) significantly lower INS values in task-specific brain regions, that left inferior parietal lobule (l-IPL, CH3) in the delayed imitation condition in EX1; left inferior frontal gyrus (l-IFG, CH2), l-IPL (CH9), and r-TPJ (CH18) in the synchronous imitation condition in Ex1, and in the IPL (CH8, CH10-14) and r-TPJ (CH18) in Ex2. The GaussianNB model successfully discriminated between autistic and non-autistic children using task-related INS values, with classification accuracy varying by task condition, reaching 55.56% in the delayed imitation condition of EX1, 57.41% in the time-lag analysis condition of EX1, 64.81% in the synchronous imitation condition of EX1, and 74.07% in Ex2. Notably, the SHAP toolkit identified key channels driving group distinction?and these channels fully overlapped with the statistically significant INS channels identified in the analyses. Conclusions Autistic children exhibit differences in both intentional and spontaneous social motor synchrony, and these differences are linked to reduced INS in key social cognitive brain regions (IFG, IPL, TPJ). This research advances understanding of social functioning variations in autistic individuals and provides a foundational foundation for developing INS-based diagnostic tools. En ligne : https://doi.org/10.1111/jcpp.70079 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=587

---

1 (1 - 3 / 3) Par page : 25 50 100 200