Can we accelerate autism discoveries through crowdsourcing? / Maude M. DAVID in Research in Autism Spectrum Disorders, 32 (December 2016)  

Public ISBD [article]  inResearch in Autism Spectrum Disorders > 32 (December 2016) . - p.80-83 Titre : Can we accelerate autism discoveries through crowdsourcing? Type de document : Texte imprimé et/ou numérique Auteurs : Maude M. DAVID, Auteur ; Brooke A. BABINEAU, Auteur ; Dennis P. WALL, Auteur Article en page(s) : p.80-83 Langues : Anglais (eng) Mots-clés : Autism  Autism spectrum disorder  Genome-environment interactions  Crowdsourcing Index. décimale : PER Périodiques Résumé : Abstract Autism is a dramatically expanding public health challenge. The search for genomic variants underlying the disease concomitantly accelerated over the last 5 years, leading to a general consensus that genetics can explain between 40% and 60% of the symptomatic variability seen in autism. This stresses both an urgent need to continue devoting resources to the search for genetic etiologies that define the forms of autism, and an equal need for attention to the interactive roles of the environment. While some environmental factors have been investigated, few studies have attempted to elucidate the combination and interplay between gene and environment to gain clear understanding of the mechanisms by which environmental factors interact with genetic susceptibilities in Autism Spectrum Disorder. Due to financial constraints as well as recruitment protocols limited by geography, such studies have been challenging to implement. We discuss here how crowdsourcing approaches can overcome these limitations. En ligne : http://dx.doi.org/10.1016/j.rasd.2016.09.001 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=296 [article] Can we accelerate autism discoveries through crowdsourcing? [Texte imprimé et/ou numérique] / Maude M. DAVID, Auteur ; Brooke A. BABINEAU, Auteur ; Dennis P. WALL, Auteur . - p.80-83. Langues : Anglais (eng) in Research in Autism Spectrum Disorders > 32 (December 2016) . - p.80-83 Mots-clés : Autism  Autism spectrum disorder  Genome-environment interactions  Crowdsourcing Index. décimale : PER Périodiques Résumé : Abstract Autism is a dramatically expanding public health challenge. The search for genomic variants underlying the disease concomitantly accelerated over the last 5 years, leading to a general consensus that genetics can explain between 40% and 60% of the symptomatic variability seen in autism. This stresses both an urgent need to continue devoting resources to the search for genetic etiologies that define the forms of autism, and an equal need for attention to the interactive roles of the environment. While some environmental factors have been investigated, few studies have attempted to elucidate the combination and interplay between gene and environment to gain clear understanding of the mechanisms by which environmental factors interact with genetic susceptibilities in Autism Spectrum Disorder. Due to financial constraints as well as recruitment protocols limited by geography, such studies have been challenging to implement. We discuss here how crowdsourcing approaches can overcome these limitations. En ligne : http://dx.doi.org/10.1016/j.rasd.2016.09.001 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=296

Clinical Evaluation of a Novel and Mobile Autism Risk Assessment / Marlena DUDA in Journal of Autism and Developmental Disorders, 46-6 (June 2016)  

Public ISBD [article]  inJournal of Autism and Developmental Disorders > 46-6 (June 2016) . - p.1953-1961 Titre : Clinical Evaluation of a Novel and Mobile Autism Risk Assessment Type de document : Texte imprimé et/ou numérique Auteurs : Marlena DUDA, Auteur ; Jena DANIELS, Auteur ; Dennis P. WALL, Auteur Article en page(s) : p.1953-1961 Langues : Anglais (eng) Mots-clés : Autism screening  Autism detection  Machine learning  Clinical validation Index. décimale : PER Périodiques Résumé : The Mobile Autism Risk Assessment (MARA) is a new, electronically administered, 7-question autism spectrum disorder (ASD) screen to triage those at highest risk for ASD. Children 16 months–17 years (N = 222) were screened during their first visit in a developmental-behavioral pediatric clinic. MARA scores were compared to diagnosis from the clinical encounter. Participant median age was 5.8 years, 76.1 % were male, and most participants had an intelligence/developmental quotient score >85; 69 of the participants (31 %) received a clinical diagnosis of ASD. The sensitivity of the MARA in detecting ASD was 89.9 % [95 % CI = 82.7–97]; the specificity was 79.7 % [95 % CI = 73.4–86.1]. In a high-risk clinical setting, the MARA shows promise as a screen to distinguish ASD from other developmental/behavioral disorders. En ligne : http://dx.doi.org/10.1007/s10803-016-2718-4 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=288 [article] Clinical Evaluation of a Novel and Mobile Autism Risk Assessment [Texte imprimé et/ou numérique] / Marlena DUDA, Auteur ; Jena DANIELS, Auteur ; Dennis P. WALL, Auteur . - p.1953-1961. Langues : Anglais (eng) in Journal of Autism and Developmental Disorders > 46-6 (June 2016) . - p.1953-1961 Mots-clés : Autism screening  Autism detection  Machine learning  Clinical validation Index. décimale : PER Périodiques Résumé : The Mobile Autism Risk Assessment (MARA) is a new, electronically administered, 7-question autism spectrum disorder (ASD) screen to triage those at highest risk for ASD. Children 16 months–17 years (N = 222) were screened during their first visit in a developmental-behavioral pediatric clinic. MARA scores were compared to diagnosis from the clinical encounter. Participant median age was 5.8 years, 76.1 % were male, and most participants had an intelligence/developmental quotient score >85; 69 of the participants (31 %) received a clinical diagnosis of ASD. The sensitivity of the MARA in detecting ASD was 89.9 % [95 % CI = 82.7–97]; the specificity was 79.7 % [95 % CI = 73.4–86.1]. In a high-risk clinical setting, the MARA shows promise as a screen to distinguish ASD from other developmental/behavioral disorders. En ligne : http://dx.doi.org/10.1007/s10803-016-2718-4 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=288

Sparsifying machine learning models identify stable subsets of predictive features for behavioral detection of autism / S. LEVY in Molecular Autism, 8 (2017)  

Public ISBD [article]  inMolecular Autism > 8 (2017) . - 65p. Titre : Sparsifying machine learning models identify stable subsets of predictive features for behavioral detection of autism Type de document : Texte imprimé et/ou numérique Auteurs : S. LEVY, Auteur ; M. DUDA, Auteur ; N. HABER, Auteur ; Dennis P. WALL, Auteur Article en page(s) : 65p. Langues : Anglais (eng) Mots-clés : Asd  Autism  Autism diagnosis  Autism screening  Autism spectrum disorder  Machine learning  Sparse machine learning  company focused on building digital solutions for child health.Springer Nature  remains neutral with regard to jurisdictional claims in published maps and  institutional affiliations. Index. décimale : PER Périodiques Résumé : Background: Autism spectrum disorder (ASD) diagnosis can be delayed due in part to the time required for administration of standard exams, such as the Autism Diagnostic Observation Schedule (ADOS). Shorter and potentially mobilized approaches would help to alleviate bottlenecks in the healthcare system. Previous work using machine learning suggested that a subset of the behaviors measured by ADOS can achieve clinically acceptable levels of accuracy. Here we expand on this initial work to build sparse models that have higher potential to generalize to the clinical population. Methods: We assembled a collection of score sheets for two ADOS modules, one for children with phrased speech (Module 2; 1319 ASD cases, 70 controls) and the other for children with verbal fluency (Module 3; 2870 ASD cases, 273 controls). We used sparsity/parsimony enforcing regularization techniques in a nested cross validation grid search to select features for 17 unique supervised learning models, encoding missing values as additional indicator features. We augmented our feature sets with gender and age to train minimal and interpretable classifiers capable of robust detection of ASD from non-ASD. Results: By applying 17 unique supervised learning methods across 5 classification families tuned for sparse use of features and to be within 1 standard error of the optimal model, we find reduced sets of 10 and 5 features used in a majority of models. We tested the performance of the most interpretable of these sparse models, including Logistic Regression with L2 regularization or Linear SVM with L1 regularization. We obtained an area under the ROC curve of 0.95 for ADOS Module 3 and 0.93 for ADOS Module 2 with less than or equal to 10 features. Conclusions: The resulting models provide improved stability over previous machine learning efforts to minimize the time complexity of autism detection due to regularization and a small parameter space. These robustness techniques yield classifiers that are sparse, interpretable and that have potential to generalize to alternative modes of autism screening, diagnosis and monitoring, possibly including analysis of short home videos. En ligne : http://dx.doi.org/10.1186/s13229-017-0180-6 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=330 [article] Sparsifying machine learning models identify stable subsets of predictive features for behavioral detection of autism [Texte imprimé et/ou numérique] / S. LEVY, Auteur ; M. DUDA, Auteur ; N. HABER, Auteur ; Dennis P. WALL, Auteur . - 65p. Langues : Anglais (eng) in Molecular Autism > 8 (2017) . - 65p. Mots-clés : Asd  Autism  Autism diagnosis  Autism screening  Autism spectrum disorder  Machine learning  Sparse machine learning  company focused on building digital solutions for child health.Springer Nature  remains neutral with regard to jurisdictional claims in published maps and  institutional affiliations. Index. décimale : PER Périodiques Résumé : Background: Autism spectrum disorder (ASD) diagnosis can be delayed due in part to the time required for administration of standard exams, such as the Autism Diagnostic Observation Schedule (ADOS). Shorter and potentially mobilized approaches would help to alleviate bottlenecks in the healthcare system. Previous work using machine learning suggested that a subset of the behaviors measured by ADOS can achieve clinically acceptable levels of accuracy. Here we expand on this initial work to build sparse models that have higher potential to generalize to the clinical population. Methods: We assembled a collection of score sheets for two ADOS modules, one for children with phrased speech (Module 2; 1319 ASD cases, 70 controls) and the other for children with verbal fluency (Module 3; 2870 ASD cases, 273 controls). We used sparsity/parsimony enforcing regularization techniques in a nested cross validation grid search to select features for 17 unique supervised learning models, encoding missing values as additional indicator features. We augmented our feature sets with gender and age to train minimal and interpretable classifiers capable of robust detection of ASD from non-ASD. Results: By applying 17 unique supervised learning methods across 5 classification families tuned for sparse use of features and to be within 1 standard error of the optimal model, we find reduced sets of 10 and 5 features used in a majority of models. We tested the performance of the most interpretable of these sparse models, including Logistic Regression with L2 regularization or Linear SVM with L1 regularization. We obtained an area under the ROC curve of 0.95 for ADOS Module 3 and 0.93 for ADOS Module 2 with less than or equal to 10 features. Conclusions: The resulting models provide improved stability over previous machine learning efforts to minimize the time complexity of autism detection due to regularization and a small parameter space. These robustness techniques yield classifiers that are sparse, interpretable and that have potential to generalize to alternative modes of autism screening, diagnosis and monitoring, possibly including analysis of short home videos. En ligne : http://dx.doi.org/10.1186/s13229-017-0180-6 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=330

The GapMap project: a mobile surveillance system to map diagnosed autism cases and gaps in autism services globally / J. DANIELS in Molecular Autism, 8 (2017)  

Public ISBD [article]  inMolecular Autism > 8 (2017) . - 55p. Titre : The GapMap project: a mobile surveillance system to map diagnosed autism cases and gaps in autism services globally Type de document : Texte imprimé et/ou numérique Auteurs : J. DANIELS, Auteur ; J. SCHWARTZ, Auteur ; N. ALBERT, Auteur ; M. DU, Auteur ; Dennis P. WALL, Auteur Article en page(s) : 55p. Langues : Anglais (eng) Mots-clés : Autism  Autism spectrum disorder  Crowdsourcing  Epidemiology  Prevalence  Resources Index. décimale : PER Périodiques Résumé : Although the number of autism diagnoses is on the rise, we have no evidence-based tracking of size and severity of gaps in access to autism-related resources, nor do we have methods to geographically triangulate the locations of the widest gaps in either the US or elsewhere across the globe. To combat these related issues of (1) mapping diagnosed cases of autism and (2) quantifying gaps in access to key intervention services, we have constructed a crowd-based mobile platform called "GapMap" (http://gapmap.stanford.edu) for real-time tracking of autism prevalence and autism-related resources that can be accessed from any mobile device with cellular or wireless connectivity. Now in beta, our aim is for this Android/iOS compatible mobile tool to simultaneously crowd-enroll the massive and growing community of families with autism to capture geographic, diagnostic, and resource usage information while automatically computing prevalence at granular geographical scales to yield a more complete and dynamic understanding of autism resource epidemiology. En ligne : http://dx.doi.org/10.1186/s13229-017-0163-7 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=330 [article] The GapMap project: a mobile surveillance system to map diagnosed autism cases and gaps in autism services globally [Texte imprimé et/ou numérique] / J. DANIELS, Auteur ; J. SCHWARTZ, Auteur ; N. ALBERT, Auteur ; M. DU, Auteur ; Dennis P. WALL, Auteur . - 55p. Langues : Anglais (eng) in Molecular Autism > 8 (2017) . - 55p. Mots-clés : Autism  Autism spectrum disorder  Crowdsourcing  Epidemiology  Prevalence  Resources Index. décimale : PER Périodiques Résumé : Although the number of autism diagnoses is on the rise, we have no evidence-based tracking of size and severity of gaps in access to autism-related resources, nor do we have methods to geographically triangulate the locations of the widest gaps in either the US or elsewhere across the globe. To combat these related issues of (1) mapping diagnosed cases of autism and (2) quantifying gaps in access to key intervention services, we have constructed a crowd-based mobile platform called "GapMap" (http://gapmap.stanford.edu) for real-time tracking of autism prevalence and autism-related resources that can be accessed from any mobile device with cellular or wireless connectivity. Now in beta, our aim is for this Android/iOS compatible mobile tool to simultaneously crowd-enroll the massive and growing community of families with autism to capture geographic, diagnostic, and resource usage information while automatically computing prevalence at granular geographical scales to yield a more complete and dynamic understanding of autism resource epidemiology. En ligne : http://dx.doi.org/10.1186/s13229-017-0163-7 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=330

---

1 (1 - 4 / 4)