Beyond Gaze: Affective Synchrony and Sensory-Linked Interactional Profiles as Early Markers of Autism Risk / Lan LIN in Autism Research, 19-4 (April 2026)  

Public ISBD [article]  inAutism Research > 19-4 (April 2026) . - e70209 Titre : Beyond Gaze: Affective Synchrony and Sensory-Linked Interactional Profiles as Early Markers of Autism Risk Type de document : texte imprimé Auteurs : Lan LIN, Auteur ; Qian LI, Auteur ; Zenghe YUE, Auteur ; Yaxin DAI, Auteur ; Haozhen CHEN, Auteur ; Yuheng CHEN, Auteur ; Jinyi ZHU, Auteur ; Yazhu HAN, Auteur ; Shengjian YIN, Auteur ; Luyang GUAN, Auteur ; Xiaoyan KE, Auteur Article en page(s) : e70209 Langues : Anglais (eng) Mots-clés : autism spectrum disorder  early identification  high-risk infants  interpersonal affect synchrony  mutual gaze  parent–child interaction  sensory processing Index. décimale : PER Périodiques Résumé : ABSTRACT Identifying early markers for autism spectrum disorder (ASD) is a clinical priority. This study investigated interpersonal affect synchrony (IAS) as a measure of interactional quality in a longitudinal cohort of 90 high-risk infants. We aimed to disentangle its contribution from mutual gaze and identify data-driven social interaction profiles linked to sensory traits. Parent-infant interactions were recorded at 6?18?months; IAS was quantified using Cross-Recurrence Quantification Analysis, and ASD outcomes were determined at 18?24?months. Infants later diagnosed with ASD (n?=?25) showed significantly lower IAS (F(1,84)?=?5.89, p FDR?=?0.023) and synchrony stability (F(1,84)?=?5.37, p FDR?=?0.023) than non-diagnosed infants (n?=?65), yet the groups did not differ in mutual gaze (p?=?0.200). Logistic regression analysis further showed that IAS (OR?=?0.561, p FDR?=?0.038) and synchrony stability (OR?=?0.013, p FDR?=?0.038) both significantly predict clinical outcome. K-means clustering revealed three profiles: ?High Gaze-High Synchrony,? ?Mid Gaze-Low Synchrony,? and ?Low Gaze-High Synchrony.? The ?Mid Gaze-Low Synchrony? profile was significantly associated with a later ASD diagnosis (p adj?=?0.031), while the ?Low Gaze-High Synchrony? profile was linked to higher sensation-seeking traits (p adj?=?0.028). The quality of parent-infant affective connection is a more robust early marker for ASD than the quantity of mutual gaze. These findings reveal critical heterogeneity, identifying a high-risk ?gaze without engagement? pattern and a potential adaptive pathway to synchrony, underscoring the need for individualized strategies in early screening and intervention. En ligne : https://doi.org/10.1002/aur.70209 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=585 [article] Beyond Gaze: Affective Synchrony and Sensory-Linked Interactional Profiles as Early Markers of Autism Risk [texte imprimé] / Lan LIN, Auteur ; Qian LI, Auteur ; Zenghe YUE, Auteur ; Yaxin DAI, Auteur ; Haozhen CHEN, Auteur ; Yuheng CHEN, Auteur ; Jinyi ZHU, Auteur ; Yazhu HAN, Auteur ; Shengjian YIN, Auteur ; Luyang GUAN, Auteur ; Xiaoyan KE, Auteur . - e70209. Langues : Anglais (eng) in Autism Research > 19-4 (April 2026) . - e70209 Mots-clés : autism spectrum disorder  early identification  high-risk infants  interpersonal affect synchrony  mutual gaze  parent–child interaction  sensory processing Index. décimale : PER Périodiques Résumé : ABSTRACT Identifying early markers for autism spectrum disorder (ASD) is a clinical priority. This study investigated interpersonal affect synchrony (IAS) as a measure of interactional quality in a longitudinal cohort of 90 high-risk infants. We aimed to disentangle its contribution from mutual gaze and identify data-driven social interaction profiles linked to sensory traits. Parent-infant interactions were recorded at 6?18?months; IAS was quantified using Cross-Recurrence Quantification Analysis, and ASD outcomes were determined at 18?24?months. Infants later diagnosed with ASD (n?=?25) showed significantly lower IAS (F(1,84)?=?5.89, p FDR?=?0.023) and synchrony stability (F(1,84)?=?5.37, p FDR?=?0.023) than non-diagnosed infants (n?=?65), yet the groups did not differ in mutual gaze (p?=?0.200). Logistic regression analysis further showed that IAS (OR?=?0.561, p FDR?=?0.038) and synchrony stability (OR?=?0.013, p FDR?=?0.038) both significantly predict clinical outcome. K-means clustering revealed three profiles: ?High Gaze-High Synchrony,? ?Mid Gaze-Low Synchrony,? and ?Low Gaze-High Synchrony.? The ?Mid Gaze-Low Synchrony? profile was significantly associated with a later ASD diagnosis (p adj?=?0.031), while the ?Low Gaze-High Synchrony? profile was linked to higher sensation-seeking traits (p adj?=?0.028). The quality of parent-infant affective connection is a more robust early marker for ASD than the quantity of mutual gaze. These findings reveal critical heterogeneity, identifying a high-risk ?gaze without engagement? pattern and a potential adaptive pathway to synchrony, underscoring the need for individualized strategies in early screening and intervention. En ligne : https://doi.org/10.1002/aur.70209 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=585

Machine Learning-Based Early Prediction Model for Autism Spectrum Disorder in Infants Using Acoustic Feature / Shengjian YIN in Autism Research, 19-3 (March 2026)  

Public ISBD [article]  inAutism Research > 19-3 (March 2026) . - e70179 Titre : Machine Learning-Based Early Prediction Model for Autism Spectrum Disorder in Infants Using Acoustic Feature Type de document : texte imprimé Auteurs : Shengjian YIN, Auteur ; Zhijia LI, Auteur ; Luyang GUAN, Auteur ; Zenghe YUE, Auteur ; Jincen WANG, Auteur ; Jinyi ZHU, Auteur ; Yazhu HAN, Auteur ; Qian LI, Auteur ; Lan LIN, Auteur ; Yaxin DAI, Auteur ; Haozhen CHEN, Auteur ; Yuheng CHEN, Auteur ; Yun LI, Auteur ; Xiaoyan KE, Auteur Article en page(s) : e70179 Langues : Anglais (eng) Mots-clés : acoustic features  autism spectrum disorder  machine learning  model  support vector machine Index. décimale : PER Périodiques Résumé : ABSTRACT This study aimed to create a machine learning-based predictive model for early detection of autism spectrum disorder (ASD) in infants using acoustic features. Conducted as a prospective cohort at Nanjing Medical University from 2019 to 2024, infants aged 9?18?months from an ASD sibling cohort participated. Behavioral and vocalization data were gathered during the Still-Face Paradigm, with ASD diagnoses confirmed at 36?months through ADOS and ADI-R assessments. Researchers extracted 4368 acoustic features from the recordings and applied LASSO regression for dimensionality reduction, identifying 39 key features. A support vector machine (SVM) classifier was then developed, tested with four kernel functions?linear, radial basis function, polynomial, and sigmoid?via tenfold cross-validation. The final sample included 88 infants, 28 of whom were diagnosed with ASD. The sigmoid kernel yielded the best results, achieving a 92.86% sensitivity, 93.33% specificity, and a 93.18% accuracy. Notably, spectral and energy-related features were significantly higher in ASD infants (p? En ligne : https://doi.org/10.1002/aur.70179 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=583 [article] Machine Learning-Based Early Prediction Model for Autism Spectrum Disorder in Infants Using Acoustic Feature [texte imprimé] / Shengjian YIN, Auteur ; Zhijia LI, Auteur ; Luyang GUAN, Auteur ; Zenghe YUE, Auteur ; Jincen WANG, Auteur ; Jinyi ZHU, Auteur ; Yazhu HAN, Auteur ; Qian LI, Auteur ; Lan LIN, Auteur ; Yaxin DAI, Auteur ; Haozhen CHEN, Auteur ; Yuheng CHEN, Auteur ; Yun LI, Auteur ; Xiaoyan KE, Auteur . - e70179. Langues : Anglais (eng) in Autism Research > 19-3 (March 2026) . - e70179 Mots-clés : acoustic features  autism spectrum disorder  machine learning  model  support vector machine Index. décimale : PER Périodiques Résumé : ABSTRACT This study aimed to create a machine learning-based predictive model for early detection of autism spectrum disorder (ASD) in infants using acoustic features. Conducted as a prospective cohort at Nanjing Medical University from 2019 to 2024, infants aged 9?18?months from an ASD sibling cohort participated. Behavioral and vocalization data were gathered during the Still-Face Paradigm, with ASD diagnoses confirmed at 36?months through ADOS and ADI-R assessments. Researchers extracted 4368 acoustic features from the recordings and applied LASSO regression for dimensionality reduction, identifying 39 key features. A support vector machine (SVM) classifier was then developed, tested with four kernel functions?linear, radial basis function, polynomial, and sigmoid?via tenfold cross-validation. The final sample included 88 infants, 28 of whom were diagnosed with ASD. The sigmoid kernel yielded the best results, achieving a 92.86% sensitivity, 93.33% specificity, and a 93.18% accuracy. Notably, spectral and energy-related features were significantly higher in ASD infants (p? En ligne : https://doi.org/10.1002/aur.70179 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=583

---

1 (1 - 2 / 2) Par page : 25 50 100 200