Identifying the neurodevelopmental and psychiatric signatures of genomic disorders associated with intellectual disability: a machine learning approach / Adam CUNNINGHAM ; Sergio Marco SALAS ; Matthew BRACHER-SMITH ; Samuel CHAWNER ; Jan STOCHL ; Tamsin FORD ; F. Lucy RAYMOND ; Valentina ESCOTT PRICE ; Marianne B.M. VAN DEN BREE in Molecular Autism, 14 (2023)  

Public ISBD [article]  inMolecular Autism > 14 (2023) . - 19 p. Titre : Identifying the neurodevelopmental and psychiatric signatures of genomic disorders associated with intellectual disability: a machine learning approach Type de document : texte imprimé Auteurs : Adam CUNNINGHAM, Auteur ; Sergio Marco SALAS, Auteur ; Matthew BRACHER-SMITH, Auteur ; Samuel CHAWNER, Auteur ; Jan STOCHL, Auteur ; Tamsin FORD, Auteur ; F. Lucy RAYMOND, Auteur ; Valentina ESCOTT PRICE, Auteur ; Marianne B.M. VAN DEN BREE, Auteur Article en page(s) : 19 p. Langues : Anglais (eng) Index. décimale : PER Périodiques Résumé : BACKGROUND: Genomic conditions can be associated with developmental delay, intellectual disability, autism spectrum disorder, and physical and mental health symptoms. They are individually rare and highly variable in presentation, which limits the use of standard clinical guidelines for diagnosis and treatment. A simple screening tool to identify young people with genomic conditions associated with neurodevelopmental disorders (ND-GCs) who could benefit from further support would be of considerable value. We used machine learning approaches to address this question. METHOD: A total of 493 individuals were included: 389 with a ND-GC, mean age=9.01, 66% male) and 104 siblings without known genomic conditions (controls, mean age=10.23, 53% male). Primary carers completed assessments of behavioural, neurodevelopmental and psychiatric symptoms and physical health and development. Machine learning techniques (penalised logistic regression, random forests, support vector machines and artificial neural networks) were used to develop classifiers of ND-GC status and identified limited sets of variables that gave the best classification performance. Exploratory graph analysis was used to understand associations within the final variable set. RESULTS: All machine learning methods identified variable sets giving high classification accuracy (AUROC between 0.883 and 0.915). We identified a subset of 30 variables best discriminating between individuals with ND-GCs and controls which formed 5 dimensions: conduct, separation anxiety, situational anxiety, communication and motor development. LIMITATIONS: This study used cross-sectional data from a cohort study which was imbalanced with respect to ND-GC status. Our model requires validation in independent datasets and with longitudinal follow-up data for validation before clinical application. CONCLUSIONS: In this study, we developed models that identified a compact set of psychiatric and physical health measures that differentiate individuals with a ND-GC from controls and highlight higher-order structure within these measures. This work is a step towards developing a screening instrument to identify young people with ND-GCs who might benefit from further specialist assessment. En ligne : http://dx.doi.org/10.1186/s13229-023-00549-2 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=513 [article] Identifying the neurodevelopmental and psychiatric signatures of genomic disorders associated with intellectual disability: a machine learning approach [texte imprimé] / Adam CUNNINGHAM, Auteur ; Sergio Marco SALAS, Auteur ; Matthew BRACHER-SMITH, Auteur ; Samuel CHAWNER, Auteur ; Jan STOCHL, Auteur ; Tamsin FORD, Auteur ; F. Lucy RAYMOND, Auteur ; Valentina ESCOTT PRICE, Auteur ; Marianne B.M. VAN DEN BREE, Auteur . - 19 p. Langues : Anglais (eng) in Molecular Autism > 14 (2023) . - 19 p. Index. décimale : PER Périodiques Résumé : BACKGROUND: Genomic conditions can be associated with developmental delay, intellectual disability, autism spectrum disorder, and physical and mental health symptoms. They are individually rare and highly variable in presentation, which limits the use of standard clinical guidelines for diagnosis and treatment. A simple screening tool to identify young people with genomic conditions associated with neurodevelopmental disorders (ND-GCs) who could benefit from further support would be of considerable value. We used machine learning approaches to address this question. METHOD: A total of 493 individuals were included: 389 with a ND-GC, mean age=9.01, 66% male) and 104 siblings without known genomic conditions (controls, mean age=10.23, 53% male). Primary carers completed assessments of behavioural, neurodevelopmental and psychiatric symptoms and physical health and development. Machine learning techniques (penalised logistic regression, random forests, support vector machines and artificial neural networks) were used to develop classifiers of ND-GC status and identified limited sets of variables that gave the best classification performance. Exploratory graph analysis was used to understand associations within the final variable set. RESULTS: All machine learning methods identified variable sets giving high classification accuracy (AUROC between 0.883 and 0.915). We identified a subset of 30 variables best discriminating between individuals with ND-GCs and controls which formed 5 dimensions: conduct, separation anxiety, situational anxiety, communication and motor development. LIMITATIONS: This study used cross-sectional data from a cohort study which was imbalanced with respect to ND-GC status. Our model requires validation in independent datasets and with longitudinal follow-up data for validation before clinical application. CONCLUSIONS: In this study, we developed models that identified a compact set of psychiatric and physical health measures that differentiate individuals with a ND-GC from controls and highlight higher-order structure within these measures. This work is a step towards developing a screening instrument to identify young people with ND-GCs who might benefit from further specialist assessment. En ligne : http://dx.doi.org/10.1186/s13229-023-00549-2 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=513

Psychopathology and cognitive performance in individuals with membrane-associated guanylate kinase mutations: a functional network phenotyping study / Kate BAKER in Journal of Neurodevelopmental Disorders, 7-1 (December 2015)  

Public ISBD [article]  inJournal of Neurodevelopmental Disorders > 7-1 (December 2015) . - p.8 Titre : Psychopathology and cognitive performance in individuals with membrane-associated guanylate kinase mutations: a functional network phenotyping study Type de document : texte imprimé Auteurs : Kate BAKER, Auteur ; Gaia SCERIF, Auteur ; Duncan E. ASTLE, Auteur ; Paul C. FLETCHER, Auteur ; F. Lucy RAYMOND, Auteur Article en page(s) : p.8 Langues : Anglais (eng) Mots-clés : Cognition  Dlg3  Genetics  Intellectual disability  Maguk  Psychiatric disorders Index. décimale : PER Périodiques Résumé : BACKGROUND: Rare pathogenic variants in membrane-associated guanylate kinase (MAGUK) genes cause intellectual disability (ID) and have recently been associated with neuropsychiatric risk in the non-ID population. However, it is not known whether risk for psychiatric symptoms amongst individuals with ID due to MAGUK gene mutations is higher than expected for the degree of general intellectual impairment, nor whether specific cognitive differences are associated with disruption to this gene functional network. METHODS: This study addresses these two questions via behavioural questionnaires and cognitive testing, applying quantitative methods previously validated in populations with ID. We compared males with X-linked ID caused by mutations in three MAGUK genes (PAK3, DLG3, OPHN1; n = 9) to males with ID caused by mutations in other X chromosome genes (n = 17). Non-parametric and parametric analyses were applied as appropriate to data. RESULTS: Groups did not differ in age, global cognitive impairment, adaptive function or epilepsy prevalence. However, individuals with MAGUK gene mutations demonstrated significantly higher psychopathology risks, comprising elevated total problem behaviours, prominent hyperactivity and elevated scores on an autism screening checklist. Despite these overt difficulties, individuals in the MAGUK group performed more accurately than expected for age and intelligence quotient (IQ) on computerised tests of visual attention, convergent with mouse models of MAGUK loss-of-function. CONCLUSIONS: Our findings support a role for MAGUK genes in influencing cognitive parameters relevant to psychiatric risk. In addition to establishing clear patterns of impairment for this group, our findings highlight the importance of careful phenotyping after genetic diagnosis, showing that gene functional network disruptions can be associated with specific psychopathological risks and cognitive differences within the context of ID. En ligne : http://dx.doi.org/10.1186/s11689-015-9105-x Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=347 [article] Psychopathology and cognitive performance in individuals with membrane-associated guanylate kinase mutations: a functional network phenotyping study [texte imprimé] / Kate BAKER, Auteur ; Gaia SCERIF, Auteur ; Duncan E. ASTLE, Auteur ; Paul C. FLETCHER, Auteur ; F. Lucy RAYMOND, Auteur . - p.8. Langues : Anglais (eng) in Journal of Neurodevelopmental Disorders > 7-1 (December 2015) . - p.8 Mots-clés : Cognition  Dlg3  Genetics  Intellectual disability  Maguk  Psychiatric disorders Index. décimale : PER Périodiques Résumé : BACKGROUND: Rare pathogenic variants in membrane-associated guanylate kinase (MAGUK) genes cause intellectual disability (ID) and have recently been associated with neuropsychiatric risk in the non-ID population. However, it is not known whether risk for psychiatric symptoms amongst individuals with ID due to MAGUK gene mutations is higher than expected for the degree of general intellectual impairment, nor whether specific cognitive differences are associated with disruption to this gene functional network. METHODS: This study addresses these two questions via behavioural questionnaires and cognitive testing, applying quantitative methods previously validated in populations with ID. We compared males with X-linked ID caused by mutations in three MAGUK genes (PAK3, DLG3, OPHN1; n = 9) to males with ID caused by mutations in other X chromosome genes (n = 17). Non-parametric and parametric analyses were applied as appropriate to data. RESULTS: Groups did not differ in age, global cognitive impairment, adaptive function or epilepsy prevalence. However, individuals with MAGUK gene mutations demonstrated significantly higher psychopathology risks, comprising elevated total problem behaviours, prominent hyperactivity and elevated scores on an autism screening checklist. Despite these overt difficulties, individuals in the MAGUK group performed more accurately than expected for age and intelligence quotient (IQ) on computerised tests of visual attention, convergent with mouse models of MAGUK loss-of-function. CONCLUSIONS: Our findings support a role for MAGUK genes in influencing cognitive parameters relevant to psychiatric risk. In addition to establishing clear patterns of impairment for this group, our findings highlight the importance of careful phenotyping after genetic diagnosis, showing that gene functional network disruptions can be associated with specific psychopathological risks and cognitive differences within the context of ID. En ligne : http://dx.doi.org/10.1186/s11689-015-9105-x Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=347

---

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