Dataset Information

Individualized Early Prediction of Familial Risk of Dyslexia: A Study of Infant Vocabulary Development.

ABSTRACT: We examined early vocabulary development in children at familial risk (FR) of dyslexia and typically developing (TD) children between 17 and 35 months of age. We trained a support vector machine to classify TD and FR using these vocabulary data at the individual level. The Dutch version of the McArthur-Bates Communicative Development Inventory (Words and Sentences) (N-CDI) was used to measure vocabulary development. We analyzed group-level differences for both total vocabulary as well as lexical classes: common nouns, predicates, and closed class words. The generalizability of the classification model was tested using cross-validation. At the group level, for both total vocabulary and the composites, the difference between TD and FR was most pronounced at 19-20 months, with FRs having lower scores. For the individual prediction, highest cross-validation accuracy (68%) was obtained at 19-20 months, with sensitivity (correctly classified FR) being 70% and specificity (correctly classified TD) being 67%. There is a sensitive window in which the difference between FR and TD is most evident. Machine learning methods are promising techniques for separating FR and TD children at an early age, before they start reading.

SUBMITTER: Chen A

PROVIDER: S-EPMC5318442 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Individualized Early Prediction of Familial Risk of Dyslexia: A Study of Infant Vocabulary Development.

Chen Ao A Wijnen Frank F Koster Charlotte C Schnack Hugo H

Frontiers in psychology 20170221

We examined early vocabulary development in children at familial risk (FR) of dyslexia and typically developing (TD) children between 17 and 35 months of age. We trained a support vector machine to classify TD and FR using these vocabulary data at the <i>individual</i> level. The Dutch version of the McArthur-Bates Communicative Development Inventory (Words and Sentences) (N-CDI) was used to measure vocabulary development. We analyzed group-level differences for both total vocabulary as well as ...[more]

PMID: 28270778

Similar Datasets

Project description:Learning to read changes the brain language system. Phonological processing is the language domain most crucial for reading, but it is still unknown how reading acquisition modifies the neural phonological network in children who either develop dyslexia or are at risk of dyslexia. For the two first years of formal education, we followed 90 beginning readers with (n = 55) and without (n = 35) familial risk of dyslexia who became typical readers (n = 70) or developed dyslexia (n = 20). We used functional magnetic resonance imaging to identify the neural correlates of phonological awareness using an auditory rhyme judgment task. This task was applied when participants were starting formal education, and repeated 2 years later. By applying two alternative group splits, we analyzed the effects of dyslexia and the effects of familial risk of dyslexia separately. We found that the phonological brain network undergoes reorganization during the first 2 years of formal education. This process proceeds differently depending on the presence of a familial history of dyslexia and reading impairment. Typical readers without risk for dyslexia activate structures responsible for phonological processing already at the beginning of literacy. This group shows reduced brain activation over time during phonological processing, perhaps due to automatization of phonological skills. Children who develop reading impairment present a delay in the development of phonological structures such as the bilateral superior temporal gyri, left middle temporal gyrus, right insula and right frontal cortex, where we observed time and group interaction. Finally, typical readers with familial risk of dyslexia also present an atypical development of the neural phonological structures, visible both at the beginning of reading instruction and 2 years later. These children used a presumably efficient neural mechanism of phonological processing, based on the activation of the precentral and postcentral gyri, and achieved a typical level of phonological awareness.

Project description:Developing an accurate and interpretable model to predict an individual's risk for Coronavirus Disease 2019 (COVID-19) is a critical step to efficiently triage testing and other scarce preventative resources. To aid in this effort, we have developed an interpretable risk calculator that utilized de-identified electronic health records (EHR) from the University of Alabama at Birmingham Informatics for Integrating Biology and the Bedside (UAB-i2b2) COVID-19 repository under the U-BRITE framework. The generated risk scores are analogous to commonly used credit scores where higher scores indicate higher risks for COVID-19 infection. By design, these risk scores can easily be calculated in spreadsheets or even with pen and paper. To predict risk, we implemented a Credit Scorecard modeling approach on longitudinal EHR data from 7,262 patients enrolled in the UAB Health System who were evaluated and/or tested for COVID-19 between January and June 2020. In this cohort, 912 patients were positive for COVID-19. Our workflow considered the timing of symptoms and medical conditions and tested the effects by applying different variable selection techniques such as LASSO and Elastic-Net. Within the two weeks before a COVID-19 diagnosis, the most predictive features were respiratory symptoms such as cough, abnormalities of breathing, pain in the throat and chest as well as other chronic conditions including nicotine dependence and major depressive disorder. When extending the timeframe to include all medical conditions across all time, our models also uncovered several chronic conditions impacting the respiratory, cardiovascular, central nervous and urinary organ systems. The whole pipeline of data processing, risk modeling and web-based risk calculator can be applied to any EHR data following the OMOP common data format. The results can be employed to generate questionnaires to estimate COVID-19 risk for screening in building entries or to optimize hospital resources.

Project description:BackgroundThe present study investigated differences in reading and spelling outcomes in Dutch and English as a second language (ESL) in adolescents with a high familial risk of dyslexia, of whom some have developed dyslexia (HRDys) while others have not (HRnonDys), in comparison to a low familial risk control group without dyslexia (LRnonDys). This allowed us to investigate the persistence of dyslexia in the first language (L1) and the effect of dyslexia on the second language (L2), which has, in this case, a lower orthographic transparency. Furthermore, the inclusion of the HRnonDys group allowed us to investigate the continuity of the familial risk of dyslexia, as previous studies observed that the HRnonDys group often scores in between the HRDys and LRnonDys group, and whether these readers without reading deficits in Dutch, have more reading difficulties in ESL.MethodsThe data of three groups of adolescents were analyzed; 27 LRnonDys, 25 HRdys 25 HRnonDys. The mean age was 14;1 years; months, and 37 were male. All were native speakers of Dutch, attended regular secondary education (grade 7-10), and were non-native speakers of English. Using MANOVA the groups were compared on Dutch and English word reading fluency (WRF), spelling and vocabulary, Dutch pseudoword and loanword reading fluency, phonological awareness (PA), rapid automatized naming (RAN), and verbal short term and working memory. A repeated measures ANOVA was used to compare English and Dutch WRF, spelling and vocabulary directly within the three groups.ResultsThe analyses revealed that the HRDys group had a deficit in both reading and spelling in Dutch and ESL. They also performed poorer than the LRnonDys group on all other measures. Effect sizes were especially large for pseudoword reading and the reaction times during the PA task. The HRnonDys group scored generally poorer than the LRnonDys group but this difference was only significant for Dutch pseudoword reading, PA reaction times and verbal short term memory. In general the HRDys and HRnonDys group scored similar in Dutch and English, except for English WRF where the HRDys group scored slightly better than expected based on their Dutch WRF.DiscussionThere was a high persistence of dyslexia. Adolescents with dyslexia had large impairments in reading and spelling, and reading related measures, both in Dutch and ESL. Despite high inter-individual differences, an overall three-step pattern was observed. Adolescents in the HRnonDys group scored in between the HRDys and LRnonDys group, supporting the polygenetic origin of dyslexia and the continuity of the familial risk of dyslexia. The lower orthographic transparency did not have a negative effect on L2 reading, spelling and vocabulary, both in the HRnonDys and HRDys group. The latter group performed slightly better than expected in L2, which may be a result of the massive exposure to English and high motivation to use English by adolescents.

Dataset Information

Individualized Early Prediction of Familial Risk of Dyslexia: A Study of Infant Vocabulary Development.

Publications

Individualized Early Prediction of Familial Risk of Dyslexia: A Study of Infant Vocabulary Development.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets