EEG spectral characteristics and asymmetry in pre-school children with autism in awake and sleep stages / Sowmyashree Mayur KAKU ; Anoop JOSEPH ; Manjula William JAMES ; Gosala R.K. SARMA ; Ashok MYSORE ; Shyam Sundar RAJAGOPALAN in Research in Autism, 121-122 (March-April 2025)  

Public ISBD [article]  inResearch in Autism > 121-122 (March-April 2025) . - 202538 Titre : EEG spectral characteristics and asymmetry in pre-school children with autism in awake and sleep stages Type de document : texte imprimé Auteurs : Sowmyashree Mayur KAKU, Auteur ; Anoop JOSEPH, Auteur ; Manjula William JAMES, Auteur ; Gosala R.K. SARMA, Auteur ; Ashok MYSORE, Auteur ; Shyam Sundar RAJAGOPALAN, Auteur Article en page(s) : 202538 Langues : Anglais (eng) Mots-clés : Autism  Preschool  Electroencephalogram  EEG  NREM  Sleep stage  Asymmetry  Power spectral density  Band power Index. décimale : PER Périodiques Résumé : Background Autism spectrum disorder (ASD) is a complex-heterogeneous neurodevelopmental disorder manifesting as abnormalities in social communication and repetitive behaviors, generally observed from early childhood. These syndromic behaviors have neurophysiological basis which stems from altered activations of cortical structures in the pathways of functional neural networks and regulatory mechanisms. Frequency bands of Electroencephalography (EEG) have functional and topographical significance expressed through computed parameters like band power and asymmetry index. Previous studies have mapped these parameters to ASD symptoms, limited to select cortical locations, bands and restricted study conditions in either passive awake or selected sleep stage. Methods Spontaneous EEG recorded from two clinically diagnosed groups of preschoolers, ASD and non-ASD in awake and 3 stages of Non-Rapid Eye Movement (NREM) sleep (N1-N3) was decomposed into 8 frequency bands spanning 0.5-24 Hz. Band powers were computed for 60 channels and hemispheric asymmetry index (AI) for 12 regions covering the entire scalp. Results We found awake alpha with N1 slow and fast theta powers significantly lower for ASD. N1 fast beta power was higher in ASD. Sleep AI exhibited significant dominance with both groups displaying congruent orientation in N1 and contralateral in N2 and N3. ASD showed lower AI in N1 and N3 with higher AI in N2. Conclusion Cyclical states of awake and sleep often tend to project their mental processes from one onto another making a use case for our pervasive approach. This pilot study highlights the need to include EEG spectral parameters into the heterogeneous relationship of awake/sleep states mentation, neuropsychology and ASD symptoms. En ligne : https://doi.org/10.1016/j.reia.2025.202538 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=555 [article] EEG spectral characteristics and asymmetry in pre-school children with autism in awake and sleep stages [texte imprimé] / Sowmyashree Mayur KAKU, Auteur ; Anoop JOSEPH, Auteur ; Manjula William JAMES, Auteur ; Gosala R.K. SARMA, Auteur ; Ashok MYSORE, Auteur ; Shyam Sundar RAJAGOPALAN, Auteur . - 202538. Langues : Anglais (eng) in Research in Autism > 121-122 (March-April 2025) . - 202538 Mots-clés : Autism  Preschool  Electroencephalogram  EEG  NREM  Sleep stage  Asymmetry  Power spectral density  Band power Index. décimale : PER Périodiques Résumé : Background Autism spectrum disorder (ASD) is a complex-heterogeneous neurodevelopmental disorder manifesting as abnormalities in social communication and repetitive behaviors, generally observed from early childhood. These syndromic behaviors have neurophysiological basis which stems from altered activations of cortical structures in the pathways of functional neural networks and regulatory mechanisms. Frequency bands of Electroencephalography (EEG) have functional and topographical significance expressed through computed parameters like band power and asymmetry index. Previous studies have mapped these parameters to ASD symptoms, limited to select cortical locations, bands and restricted study conditions in either passive awake or selected sleep stage. Methods Spontaneous EEG recorded from two clinically diagnosed groups of preschoolers, ASD and non-ASD in awake and 3 stages of Non-Rapid Eye Movement (NREM) sleep (N1-N3) was decomposed into 8 frequency bands spanning 0.5-24 Hz. Band powers were computed for 60 channels and hemispheric asymmetry index (AI) for 12 regions covering the entire scalp. Results We found awake alpha with N1 slow and fast theta powers significantly lower for ASD. N1 fast beta power was higher in ASD. Sleep AI exhibited significant dominance with both groups displaying congruent orientation in N1 and contralateral in N2 and N3. ASD showed lower AI in N1 and N3 with higher AI in N2. Conclusion Cyclical states of awake and sleep often tend to project their mental processes from one onto another making a use case for our pervasive approach. This pilot study highlights the need to include EEG spectral parameters into the heterogeneous relationship of awake/sleep states mentation, neuropsychology and ASD symptoms. En ligne : https://doi.org/10.1016/j.reia.2025.202538 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=555

Predicting neurodevelopmental disorders using machine learning models and electronic health records - status of the field / Shyam Sundar RAJAGOPALAN in Journal of Neurodevelopmental Disorders, 16 (2024)  

Public ISBD [article]  inJournal of Neurodevelopmental Disorders > 16 (2024) Titre : Predicting neurodevelopmental disorders using machine learning models and electronic health records - status of the field Type de document : texte imprimé Auteurs : Shyam Sundar RAJAGOPALAN, Auteur ; Kristiina TAMMIMIES, Auteur Langues : Anglais (eng) Mots-clés : Humans  Machine Learning  Electronic Health Records  Neurodevelopmental Disorders/diagnosis/epidemiology  Attention Deficit Disorder with Hyperactivity/diagnosis/epidemiology  Autism Spectrum Disorder/diagnosis/epidemiology  Electronic Health Record  Machine Learning  Neurodevelopmental Disorder  Population Register  for publication Not applicable. Competing interests The authors declare that  there are no competing interests. Index. décimale : PER Périodiques Résumé : Machine learning (ML) is increasingly used to identify patterns that could predict neurodevelopmental disorders (NDDs), such as autism spectrum disorder (ASD) and attention-deficit hyperactivity disorder (ADHD). One key source of multilevel data for ML prediction models includes population-based registers and electronic health records. These can contain rich information on individual and familial medical histories and socio-demographics. This review summarizes studies published between 2010-2022 that used ML algorithms to develop predictive models for NDDs using population-based registers and electronic health records. A literature search identified 1191 articles, of which 32 were retained. Of these, 47% developed ASD prediction models and 25% ADHD models. Classical ML methods were used in 82% of studies and in particular tree-based prediction models performed well. The sensitivity of the models was lower than 75% for most studies, while the area under the curve (AUC) was greater than 75%. The most important predictors were patient and familial medical history and sociodemographic factors. Using private in-house datasets makes comparing and validating model generalizability across studies difficult. The ML model development and reporting guidelines were adopted only in a few recently reported studies. More work is needed to harness the power of data for detecting NDDs early. En ligne : https://dx.doi.org/10.1186/s11689-024-09579-0 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=576 [article] Predicting neurodevelopmental disorders using machine learning models and electronic health records - status of the field [texte imprimé] / Shyam Sundar RAJAGOPALAN, Auteur ; Kristiina TAMMIMIES, Auteur. Langues : Anglais (eng) in Journal of Neurodevelopmental Disorders > 16 (2024) Mots-clés : Humans  Machine Learning  Electronic Health Records  Neurodevelopmental Disorders/diagnosis/epidemiology  Attention Deficit Disorder with Hyperactivity/diagnosis/epidemiology  Autism Spectrum Disorder/diagnosis/epidemiology  Electronic Health Record  Machine Learning  Neurodevelopmental Disorder  Population Register  for publication Not applicable. Competing interests The authors declare that  there are no competing interests. Index. décimale : PER Périodiques Résumé : Machine learning (ML) is increasingly used to identify patterns that could predict neurodevelopmental disorders (NDDs), such as autism spectrum disorder (ASD) and attention-deficit hyperactivity disorder (ADHD). One key source of multilevel data for ML prediction models includes population-based registers and electronic health records. These can contain rich information on individual and familial medical histories and socio-demographics. This review summarizes studies published between 2010-2022 that used ML algorithms to develop predictive models for NDDs using population-based registers and electronic health records. A literature search identified 1191 articles, of which 32 were retained. Of these, 47% developed ASD prediction models and 25% ADHD models. Classical ML methods were used in 82% of studies and in particular tree-based prediction models performed well. The sensitivity of the models was lower than 75% for most studies, while the area under the curve (AUC) was greater than 75%. The most important predictors were patient and familial medical history and sociodemographic factors. Using private in-house datasets makes comparing and validating model generalizability across studies difficult. The ML model development and reporting guidelines were adopted only in a few recently reported studies. More work is needed to harness the power of data for detecting NDDs early. En ligne : https://dx.doi.org/10.1186/s11689-024-09579-0 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=576

---

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