How to fast - track the early identification of pre-school autistic children? By comparing diverse machine learning methods with resting - state fNIRS features / Yaou ZHAO in Research in Autism, 138 (October 2026)  

Public ISBD [article]  inResearch in Autism > 138 (October 2026) . - p.203021 Titre : How to fast - track the early identification of pre-school autistic children? By comparing diverse machine learning methods with resting - state fNIRS features Type de document : texte imprimé Auteurs : Yaou ZHAO, Auteur ; Kaiyun LI, Auteur ; Yuehui CHEN, Auteur ; Bang DU, Auteur ; Liu CHEN, Auteur ; Mingxue WANG, Auteur ; Ziyang QI, Auteur ; Yi CAO, Auteur ; Ruizhi HAN, Auteur ; Xiaotong LI, Auteur ; Wuyue WANG, Auteur ; Qingfang MENG, Auteur ; Fanlu JIA, Auteur ; Jiayi ZHANG, Auteur ; Xinyu LIU, Auteur ; Juan FU, Auteur Article en page(s) : p.203021 Langues : Anglais (eng) Mots-clés : Autism  Rs-fNIRS  Machine learning  Feature selection  The change in the Binary Entropy Index. décimale : PER Périodiques Résumé : Functional near-infrared spectroscopy (fNIRS) combined with machine learning (ML) has been increasingly applied to distinguish autism spectrum disorder (ASD) based on resting-state (rs) hemodynamic fluctuations. This study constructed rs-fNIRS datasets comprised of multi-2-minute oxy-hemoglobin (HbO), deoxy-hemoglobin (Hb), and total hemoglobin (HbT) signals (two- or four-times collection for each child) from 50 fNIRS channels. Four evolutionary computation channel selection algorithms (GA, DE, PSO, PBIL) and 12 classifiers (KNN, RC, NB, DT, ET, LSVM, RBF-SVM, RF, ADA, XGB, E-KNN, E-SVM) were firstly employed to test 12 features (mean, std, kurtosis, skewness, BinEn, ApEN, Δmean, Δstd, Δkurtosis, Δskewness, ΔBinEn, ΔApEN) of the HbO,Hb and HbT. The 3 s time series curve closely aligns with the 2-minute original data, and ΔBinEn being the optimal discriminative feature. The combination of E-SVM and E-KNN ensemble classifiers with the PBIL algorithm achieved the best performance across HbO, Hb, and HbT data. Validation experiments demonstrated the method's robustness, with an average classification accuracy exceeding 90% and identified key contribution channels (CH1, CH11, CH20, CH24, CH27, CH33, CH42). These findings revealed that rs-fNIRS-ML can serve as an efficient clinical tool for early ASD diagnosis in preschoolers. En ligne : https://dx.doi.org/https://doi.org/10.1016/j.reia.2026.203021 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=594 [article] How to fast - track the early identification of pre-school autistic children? By comparing diverse machine learning methods with resting - state fNIRS features [texte imprimé] / Yaou ZHAO, Auteur ; Kaiyun LI, Auteur ; Yuehui CHEN, Auteur ; Bang DU, Auteur ; Liu CHEN, Auteur ; Mingxue WANG, Auteur ; Ziyang QI, Auteur ; Yi CAO, Auteur ; Ruizhi HAN, Auteur ; Xiaotong LI, Auteur ; Wuyue WANG, Auteur ; Qingfang MENG, Auteur ; Fanlu JIA, Auteur ; Jiayi ZHANG, Auteur ; Xinyu LIU, Auteur ; Juan FU, Auteur . - p.203021. Langues : Anglais (eng) in Research in Autism > 138 (October 2026) . - p.203021 Mots-clés : Autism  Rs-fNIRS  Machine learning  Feature selection  The change in the Binary Entropy Index. décimale : PER Périodiques Résumé : Functional near-infrared spectroscopy (fNIRS) combined with machine learning (ML) has been increasingly applied to distinguish autism spectrum disorder (ASD) based on resting-state (rs) hemodynamic fluctuations. This study constructed rs-fNIRS datasets comprised of multi-2-minute oxy-hemoglobin (HbO), deoxy-hemoglobin (Hb), and total hemoglobin (HbT) signals (two- or four-times collection for each child) from 50 fNIRS channels. Four evolutionary computation channel selection algorithms (GA, DE, PSO, PBIL) and 12 classifiers (KNN, RC, NB, DT, ET, LSVM, RBF-SVM, RF, ADA, XGB, E-KNN, E-SVM) were firstly employed to test 12 features (mean, std, kurtosis, skewness, BinEn, ApEN, Δmean, Δstd, Δkurtosis, Δskewness, ΔBinEn, ΔApEN) of the HbO,Hb and HbT. The 3 s time series curve closely aligns with the 2-minute original data, and ΔBinEn being the optimal discriminative feature. The combination of E-SVM and E-KNN ensemble classifiers with the PBIL algorithm achieved the best performance across HbO, Hb, and HbT data. Validation experiments demonstrated the method's robustness, with an average classification accuracy exceeding 90% and identified key contribution channels (CH1, CH11, CH20, CH24, CH27, CH33, CH42). These findings revealed that rs-fNIRS-ML can serve as an efficient clinical tool for early ASD diagnosis in preschoolers. En ligne : https://dx.doi.org/https://doi.org/10.1016/j.reia.2026.203021 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=594

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