-
Scientific Reports Dec 2020Dysgraphia, a disorder affecting the written expression of symbols and words, negatively impacts the academic results of pupils as well as their overall well-being. The...
Dysgraphia, a disorder affecting the written expression of symbols and words, negatively impacts the academic results of pupils as well as their overall well-being. The use of automated procedures can make dysgraphia testing available to larger populations, thereby facilitating early intervention for those who need it. In this paper, we employed a machine learning approach to identify handwriting deteriorated by dysgraphia. To achieve this goal, we collected a new handwriting dataset consisting of several handwriting tasks and extracted a broad range of features to capture different aspects of handwriting. These were fed to a machine learning algorithm to predict whether handwriting is affected by dysgraphia. We compared several machine learning algorithms and discovered that the best results were achieved by the adaptive boosting (AdaBoost) algorithm. The results show that machine learning can be used to detect dysgraphia with almost 80% accuracy, even when dealing with a heterogeneous set of subjects differing in age, sex and handedness.
Topics: Adolescent; Agraphia; Algorithms; Case-Control Studies; Child; Data Accuracy; Female; Handwriting; Humans; Machine Learning; Male
PubMed: 33299092
DOI: 10.1038/s41598-020-78611-9 -
PloS One 2020Handwriting is a complex skill to acquire and it requires years of training to be mastered. Children presenting dysgraphia exhibit difficulties automatizing their...
Handwriting is a complex skill to acquire and it requires years of training to be mastered. Children presenting dysgraphia exhibit difficulties automatizing their handwriting. This can bring anxiety and can negatively impact education. 280 children were recruited in schools and specialized clinics to perform the Concise Evaluation Scale for Children's Handwriting (BHK) on digital tablets. Within this dataset, we identified children with dysgraphia. Twelve digital features describing handwriting through different aspects (static, kinematic, pressure and tilt) were extracted and used to create linear models to investigate handwriting acquisition throughout education. K-means clustering was performed to define a new classification of dysgraphia. Linear models show that three features only (two kinematic and one static) showed a significant association to predict change of handwriting quality in control children. Most kinematic and statics features interacted with age. Results suggest that children with dysgraphia do not simply differ from ones without dysgraphia by quantitative differences on the BHK scale but present a different development in terms of static, kinematic, pressure and tilt features. The K-means clustering yielded 3 clusters (Ci). Children in C1 presented mild dysgraphia usually not detected in schools whereas children in C2 and C3 exhibited severe dysgraphia. Notably, C2 contained individuals displaying abnormalities in term of kinematics and pressure whilst C3 regrouped children showing mainly tilt problems. The current results open new opportunities for automatic detection of children with dysgraphia in classroom. We also believe that the training of pressure and tilt may open new therapeutic opportunities through serious games.
Topics: Agraphia; Biomechanical Phenomena; Child; Female; Handwriting; Humans; Male; Motor Skills
PubMed: 32915793
DOI: 10.1371/journal.pone.0237575 -
Children (Basel, Switzerland) Sep 2022Knowledge is limited about dysgraphia in adolescence and its association with daily motor-related daily performance and health-related quality of life (HRQOL). This...
Knowledge is limited about dysgraphia in adolescence and its association with daily motor-related daily performance and health-related quality of life (HRQOL). This study aimed to (1) compare and (2) examine correlations between handwriting measures, motor-related daily performance, and HRQOL of adolescents with and without dysgraphia and (3) examine the contribution of motor-related daily performance and handwriting measures to predict their physical HRQOL. There were eighty adolescents (13-18 yr): half with dysgraphia and half matched controls without dysgraphia per the Handwriting Proficiency Screening Questionnaire and Handwriting Legibility Scale participated. They copied a paragraph script onto a paper attached to the Computerized Penmanship Evaluation Tool digitizer and completed the World Health Organization Quality of Life Questionnaire-brief version and the Adult Developmental Coordination Disorder Checklist (ADC). We found significant between-group differences in motor-related daily performance, handwriting measures, and HRQOL and significant correlations between HRQOL and handwriting process measures and motor-coordination ability. Handwriting measures predicted 25%, and the ADC A and C subscales 45.6%, of the research group's physical QOL domain score variability. Notably, the control group's current perceptions of their motor-coordination performance (ADC-C) predicted 36.5% of the variance in physical QOL. Dysgraphia's negative effects during childhood and adolescence may reduce adolescents' HRQOL now and into adulthood.
PubMed: 36291371
DOI: 10.3390/children9101437 -
Sensors (Basel, Switzerland) May 2023Handwriting learning disabilities, such as dysgraphia, have a serious negative impact on children's academic results, daily life and overall well-being. Early detection...
Handwriting learning disabilities, such as dysgraphia, have a serious negative impact on children's academic results, daily life and overall well-being. Early detection of dysgraphia facilitates an early start of targeted intervention. Several studies have investigated dysgraphia detection using machine learning algorithms with a digital tablet. However, these studies deployed classical machine learning algorithms with manual feature extraction and selection as well as binary classification: either dysgraphia or no dysgraphia. In this work, we investigated the fine grading of handwriting capabilities by predicting the SEMS score (between 0 and 12) with deep learning. Our approach provided a root-mean-square error of less than 1 with automatic instead of manual feature extraction and selection. Furthermore, the SensoGrip smart pen SensoGrip was used, i.e., a pen equipped with sensors to capture handwriting dynamics, instead of a tablet, enabling writing evaluation in more realistic scenarios.
Topics: Child; Humans; Deep Learning; Handwriting; Agraphia; Algorithms; Machine Learning
PubMed: 37299942
DOI: 10.3390/s23115215 -
Frontiers in Neurology 2022Currently, little is known about Chinese-speaking primary progressive aphasia (PPA) patients compared to patients who speak Indo-European languages. We examined the...
INTRODUCTION
Currently, little is known about Chinese-speaking primary progressive aphasia (PPA) patients compared to patients who speak Indo-European languages. We examined the demographics and clinical manifestations, particularly reading and writing characteristics, of Chinese patients with PPA over the last two decades to establish a comprehensive profile and improve diagnosis and care.
METHODS
We reviewed the demographic features, clinical manifestations, and radiological features of Chinese-speaking PPA patients from 56 articles published since 1994. We then summarized the specific reading and writing errors of Chinese-speaking patients.
RESULTS
The average age of onset for Chinese-speaking patients was in their early 60's, and there were slightly more male patients than female patients. The core symptoms and images of Chinese-speaking patients were similar to those of patients who speak Indo-European languages. Reading and writing error patterns differed due to Chinese's distinct tone and orthography. The types of reading errors reported in Chinese-speaking patients with PPA included tonal errors, regularization errors, visually related errors, semantic errors, phonological errors, unrelated errors, and non-response. Among these errors, regularization errors were the most common in semantic variant PPA, and tonal errors were specific to Chinese. Writing errors mainly consisted of non-character errors (stroke, radical/component, visual, pictograph, dyskinetic errors, and spatial errors), phonologically plausible errors, orthographically similar errors, semantic errors, compound word errors, sequence errors, unrelated errors, and non-response.
CONCLUSION
This paper provides the latest comprehensive demographic information and unique presentations on the reading and writing of Chinese-speaking patients with PPA. More detailed studies are needed to address the frequency of errors in reading and writing and their anatomical substrates.
PubMed: 36561305
DOI: 10.3389/fneur.2022.1025660 -
Data in Brief Jun 2024This report presents a dataset of offline handwriting samples among Malaysian schoolchildren with potential dysgraphia. The images contained Malay sentences written by...
This report presents a dataset of offline handwriting samples among Malaysian schoolchildren with potential dysgraphia. The images contained Malay sentences written by primary school students and children under intervention by the Malaysia Dyslexia Association (PDM). Students were expected to copy and write the sentences provided on the paper form that was used to gather data. Students were required to write three sets of sentences. The paper was digitalized by scanning it and converting it into digital form. Furthermore, the images were pre-processed using image processing techniques by converting the images into binary format and interchanging the foreground and background colors. The images were then classified into two categories, namely potential dysgraphia and low potential dysgraphia. The dataset comprised a total of 249 handwriting images, obtained from a sample of 83 participants who were selected in the data collection process, with 114 for potential dysgraphia and 135 for low potential dysgraphia. Both categories of handwriting images were prepared in black and white images.
PubMed: 38868380
DOI: 10.1016/j.dib.2024.110534 -
Frontiers in Psychiatry 2023Language-based learning disabilities (LBLD) refers to a spectrum of neurodevelopmental-associated disorders that are characterized by cognitive and behavioral...
INTRODUCTION
Language-based learning disabilities (LBLD) refers to a spectrum of neurodevelopmental-associated disorders that are characterized by cognitive and behavioral differences in comprehending, processing and utilizing spoken and/or written language. The focus of this work was on identifying early predictors of three main specific LBLD including dyslexia, dyscalculia, and dysgraphia.
METHODS
The Web of Science (WoS) was searched for literature related to (neurocognitive, neurophysiological, and neuroimaging) measurements used to identify early predictors of LBLD from 1991 to 25 October 2021. A retrospective bibliometric analysis was performed to analyze collaboration among countries, institutions, authors, publishing journals, reference co-citation patterns, keyword co-occurrence, keyword clustering, and burst keywords using Biblioanalytics software.
RESULTS
In total, 921 publications related to the identification of LBLD using (neurocognitive, neurophysiological, and neuroimaging) modalities were included. The data analysis shows a slow growth in research on the topic in the 90s and early 2000 and growing trend in recent years. The most prolific and cited journal is Neuroimage, followed by Neuropsychologia. The United States and Finland's Universities Jyvaskyla and Helsinki are the leading country and institution in this field, respectively. "Neuroimaging," "brain," "fMRI," "cognitive predictor," "comorbidity," "cortical thickness" were identified as hotspots and trends of (neurocognitive, neurophysiological, and neuroimaging) modalities in the identification of LBLD.
DISCUSSION
Early predictors of LBLDs would be useful as targets for specific prevention and intervention programs to be implemented at very young ages, which could have a significant clinical impact. A novel finding of neuroimaging predictors combined with neurocognitive and neuropsychological batteries may have implications for future research.
PubMed: 38111620
DOI: 10.3389/fpsyt.2023.1229580 -
Medicina (Kaunas, Lithuania) Aug 2023: Specific Learning Disorder (SLD) is a complex neurobiological disorder characterized by a persistent difficult in reading (dyslexia), written expression (dysgraphia),...
: Specific Learning Disorder (SLD) is a complex neurobiological disorder characterized by a persistent difficult in reading (dyslexia), written expression (dysgraphia), and mathematics (dyscalculia). The hereditary and genetic component is one of the underlying causes of SLD, but the relationship between genes and the environment should be considered. Several genetic studies were performed in different populations to identify causative genes. : Here, we show the analysis of 9 multiplex families with at least 2 individuals diagnosed with SLD per family, with a total of 37 persons, 21 of whom are young subjects with SLD, by means of Next-Generation Sequencing (NGS) to identify possible causative mutations in a panel of 15 candidate genes: , , , , , , , , , , , , , , and . We detected, in eight families out nine, SNP variants in the , , , and genes, even if in silico analysis did not show any causative effect on this behavioral condition. In all cases, the mutation was transmitted by one of the two parents, thus excluding the case of de novo mutation. Moreover, the parent carrying the allelic variant transmitted to the children, in six out of seven families, reports language difficulties. : Although the present results cannot be considered conclusive due to the limited sample size, the identification of genetic variants in the above genes can provide input for further research on the same, as well as on other genes/mutations, to better understand the genetic basis of this disorder, and from this perspective, to better understand also the neuropsychological and social aspects connected to this disorder, which affects an increasing number of young people.
Topics: Child; Humans; Adolescent; Specific Learning Disorder; Nerve Tissue Proteins; Receptors, Immunologic; Alleles; High-Throughput Nucleotide Sequencing; Microtubule-Associated Proteins
PubMed: 37629793
DOI: 10.3390/medicina59081503 -
Brain Sciences Sep 2022Neurofeedback (NF) is a type of biofeedback in which an individual's brain activity is measured and presented to them to support self-regulation of ongoing brain... (Review)
Review
Neurofeedback (NF) is a type of biofeedback in which an individual's brain activity is measured and presented to them to support self-regulation of ongoing brain oscillations and achieve specific behavioral and neurophysiological outcomes. NF training induces changes in neurophysiological circuits that are associated with behavioral changes. Recent evidence suggests that the NF technique can be used to train electrical brain activity and facilitate learning among children with learning disorders. Toward this aim, this review first presents a generalized model for NF systems, and then studies involving NF training for children with disorders such as dyslexia, attention-deficit/hyperactivity disorder (ADHD), and other specific learning disorders such as dyscalculia and dysgraphia are reviewed. The discussion elaborates on the potential for translational applications of NF in educational and learning settings with details. This review also addresses some issues concerning the role of NF in education, and it concludes with some solutions and future directions. In order to provide the best learning environment for children with ADHD and other learning disorders, it is critical to better understand the role of NF in educational settings. The review provides the potential challenges of the current systems to aid in highlighting the issues undermining the efficacy of current systems and identifying solutions to address them. The review focuses on the use of NF technology in education for the development of adaptive teaching methods and the best learning environment for children with learning disabilities.
PubMed: 36138974
DOI: 10.3390/brainsci12091238 -
Movement Disorders Clinical Practice May 2023
PubMed: 37205257
DOI: 10.1002/mdc3.13721