Machine-Learning prediction of comorbid substance use disorders in ADHD youth using Swedish registry data / Yanli ZHANG-JAMES in Journal of Child Psychology and Psychiatry, 61-12 (December 2020)  

Public ISBD [article]  inJournal of Child Psychology and Psychiatry > 61-12 (December 2020) . - p.1370-1379 Titre : Machine-Learning prediction of comorbid substance use disorders in ADHD youth using Swedish registry data Type de document : Texte imprimé et/ou numérique Auteurs : Yanli ZHANG-JAMES, Auteur ; Qi CHEN, Auteur ; Ralf KUJA-HALKOLA, Auteur ; Paul LICHTENSTEIN, Auteur ; Henrik LARSSON, Auteur ; Stephen V. FARAONE, Auteur Article en page(s) : p.1370-1379 Langues : Anglais (eng) Mots-clés : Machine learning  attention-deficit hyperactive disorder  comorbidity  risk factor  substance use disorder Index. décimale : PER Périodiques Résumé : BACKGROUND: Children with attention-deficit/hyperactivity disorder (ADHD) have a high risk for substance use disorders (SUDs). Early identification of at-risk youth would help allocate scarce resources for prevention programs. METHODS: Psychiatric and somatic diagnoses, family history of these disorders, measures of socioeconomic distress, and information about birth complications were obtained from the national registers in Sweden for 19,787 children with ADHD born between 1989 and 1993. We trained (a) a cross-sectional random forest (RF) model using data available by age 17 to predict SUD diagnosis between ages 18 and 19; and (b) a longitudinal recurrent neural network (RNN) model with the Long Short-Term Memory (LSTM) architecture to predict new diagnoses at each age. RESULTS: The area under the receiver operating characteristic curve (AUC) was 0.73(95%CI 0.70-0.76) for the random forest model (RF). Removing prior diagnosis from the predictors, the RF model was still able to achieve significant AUCs when predicting all SUD diagnoses (0.69, 95%CI 0.66-0.72) or new diagnoses (0.67, 95%CI: 0.64, 0.71) during age 18-19. For the model predicting new diagnoses, model calibration was good with a low Brier score of 0.086. Longitudinal LSTM model was able to predict later SUD risks at as early as 2 years age, 10 years before the earliest diagnosis. The average AUC from longitudinal models predicting new diagnoses 1, 2, 5 and 10 years in the future was 0.63. CONCLUSIONS: Population registry data can be used to predict at-risk comorbid SUDs in individuals with ADHD. Such predictions can be made many years prior to age of the onset, and their SUD risks can be monitored using longitudinal models over years during child development. Nevertheless, more work is needed to create prediction models based on electronic health records or linked population registers that are sufficiently accurate for use in the clinic. En ligne : http://dx.doi.org/10.1111/jcpp.13226 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=434 [article] Machine-Learning prediction of comorbid substance use disorders in ADHD youth using Swedish registry data [Texte imprimé et/ou numérique] / Yanli ZHANG-JAMES, Auteur ; Qi CHEN, Auteur ; Ralf KUJA-HALKOLA, Auteur ; Paul LICHTENSTEIN, Auteur ; Henrik LARSSON, Auteur ; Stephen V. FARAONE, Auteur . - p.1370-1379. Langues : Anglais (eng) in Journal of Child Psychology and Psychiatry > 61-12 (December 2020) . - p.1370-1379 Mots-clés : Machine learning  attention-deficit hyperactive disorder  comorbidity  risk factor  substance use disorder Index. décimale : PER Périodiques Résumé : BACKGROUND: Children with attention-deficit/hyperactivity disorder (ADHD) have a high risk for substance use disorders (SUDs). Early identification of at-risk youth would help allocate scarce resources for prevention programs. METHODS: Psychiatric and somatic diagnoses, family history of these disorders, measures of socioeconomic distress, and information about birth complications were obtained from the national registers in Sweden for 19,787 children with ADHD born between 1989 and 1993. We trained (a) a cross-sectional random forest (RF) model using data available by age 17 to predict SUD diagnosis between ages 18 and 19; and (b) a longitudinal recurrent neural network (RNN) model with the Long Short-Term Memory (LSTM) architecture to predict new diagnoses at each age. RESULTS: The area under the receiver operating characteristic curve (AUC) was 0.73(95%CI 0.70-0.76) for the random forest model (RF). Removing prior diagnosis from the predictors, the RF model was still able to achieve significant AUCs when predicting all SUD diagnoses (0.69, 95%CI 0.66-0.72) or new diagnoses (0.67, 95%CI: 0.64, 0.71) during age 18-19. For the model predicting new diagnoses, model calibration was good with a low Brier score of 0.086. Longitudinal LSTM model was able to predict later SUD risks at as early as 2 years age, 10 years before the earliest diagnosis. The average AUC from longitudinal models predicting new diagnoses 1, 2, 5 and 10 years in the future was 0.63. CONCLUSIONS: Population registry data can be used to predict at-risk comorbid SUDs in individuals with ADHD. Such predictions can be made many years prior to age of the onset, and their SUD risks can be monitored using longitudinal models over years during child development. Nevertheless, more work is needed to create prediction models based on electronic health records or linked population registers that are sufficiently accurate for use in the clinic. En ligne : http://dx.doi.org/10.1111/jcpp.13226 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=434

SLC9A9 Co-expression modules in autism-associated brain regions / Jameson PATAK in Autism Research, 10-3 (March 2017)  

Public ISBD [article]  inAutism Research > 10-3 (March 2017) . - p.414-429 Titre : SLC9A9 Co-expression modules in autism-associated brain regions Type de document : Texte imprimé et/ou numérique Auteurs : Jameson PATAK, Auteur ; Jonathan L. HESS, Auteur ; Yanli ZHANG-JAMES, Auteur ; Stephen J. GLATT, Auteur ; Stephen V. FARAONE, Auteur Article en page(s) : p.414-429 Langues : Anglais (eng) Mots-clés : SLC9A9  weighted gene co-expression network analysis  Autism spectrum disorder  endosomal pathway  transcriptome Index. décimale : PER Périodiques Résumé : SLC9A9 is a sodium hydrogen exchanger present in the recycling endosome and highly expressed in the brain. It is implicated in neuropsychiatric disorders, including autism spectrum disorders (ASDs). Little research concerning its gene expression patterns and biological pathways has been conducted. We sought to investigate its possible biological roles in autism-associated brain regions throughout development. We conducted a weighted gene co-expression network analysis on RNA-seq data downloaded from Brainspan. We compared prenatal and postnatal gene expression networks for three ASD-associated brain regions known to have high SLC9A9 gene expression. We also performed an ASD-associated single nucleotide polymorphism enrichment analysis and a cell signature enrichment analysis. The modules showed differences in gene constituents (membership), gene number, and connectivity throughout time. SLC9A9 was highly associated with immune system functions, metabolism, apoptosis, endocytosis, and signaling cascades. Gene list comparison with co-immunoprecipitation data was significant for multiple modules. We found a disproportionately high autism risk signal among genes constituting the prenatal hippocampal module. The modules were enriched with astrocyte and oligodendrocyte markers. SLC9A9 is potentially involved in the pathophysiology of ASDs. Our investigation confirmed proposed functions for SLC9A9, such as endocytosis and immune regulation, while also revealing potential roles in mTOR signaling and cell survival.. By providing a concise molecular map and interactions, evidence of cell type and implicated brain regions we hope this will guide future research on SLC9A9. En ligne : http://dx.doi.org/10.1002/aur.1670 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=304 [article] SLC9A9 Co-expression modules in autism-associated brain regions [Texte imprimé et/ou numérique] / Jameson PATAK, Auteur ; Jonathan L. HESS, Auteur ; Yanli ZHANG-JAMES, Auteur ; Stephen J. GLATT, Auteur ; Stephen V. FARAONE, Auteur . - p.414-429. Langues : Anglais (eng) in Autism Research > 10-3 (March 2017) . - p.414-429 Mots-clés : SLC9A9  weighted gene co-expression network analysis  Autism spectrum disorder  endosomal pathway  transcriptome Index. décimale : PER Périodiques Résumé : SLC9A9 is a sodium hydrogen exchanger present in the recycling endosome and highly expressed in the brain. It is implicated in neuropsychiatric disorders, including autism spectrum disorders (ASDs). Little research concerning its gene expression patterns and biological pathways has been conducted. We sought to investigate its possible biological roles in autism-associated brain regions throughout development. We conducted a weighted gene co-expression network analysis on RNA-seq data downloaded from Brainspan. We compared prenatal and postnatal gene expression networks for three ASD-associated brain regions known to have high SLC9A9 gene expression. We also performed an ASD-associated single nucleotide polymorphism enrichment analysis and a cell signature enrichment analysis. The modules showed differences in gene constituents (membership), gene number, and connectivity throughout time. SLC9A9 was highly associated with immune system functions, metabolism, apoptosis, endocytosis, and signaling cascades. Gene list comparison with co-immunoprecipitation data was significant for multiple modules. We found a disproportionately high autism risk signal among genes constituting the prenatal hippocampal module. The modules were enriched with astrocyte and oligodendrocyte markers. SLC9A9 is potentially involved in the pathophysiology of ASDs. Our investigation confirmed proposed functions for SLC9A9, such as endocytosis and immune regulation, while also revealing potential roles in mTOR signaling and cell survival.. By providing a concise molecular map and interactions, evidence of cell type and implicated brain regions we hope this will guide future research on SLC9A9. En ligne : http://dx.doi.org/10.1002/aur.1670 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=304

---

1 (1 - 2 / 2)