Screening for Reading Difficulties: Comparing Eye Tracking Outcomes to Neuropsychological Assessments

Ekstrand, Anna Carin Gran; Benfatto, Mattias Nilsson; Seimyr, Gustaf Öqvist

doi:10.3389/feduc.2021.643232

Cited by 11 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…I forskning i laesning og laeseudvikling er øjenbevaegelser veletablerede indikatorer for kognitiv processering (Rayner, 2012, Holmqvist, et al, 2011. I takt med at eye-tracking er modnet som teknologi, og der er udviklet pålidelige ikke-begraensende og brugervenlige instrumenter til at optage øjenbevaegelser, er interessen også steget for at anvende øjenbevaegelser i laeseevaluering (Gran Ekstrand et al, 2021, Benfatto et al, 2016, Klerke et al, 2018, Bingel et al 2018. Forventningen er, at eye-tracking-teknologien kan give nye muligheder i evalueringen af laesning.…”

Section: Indledningunclassified

Måling af flydende læsning med øjenbevægelser i skolen

Klerke,

Fuglsang Engmose

2024

View full text Add to dashboard Cite

Eye-tracking-teknologien er blevet tilgængelig for måling af elevers læsning i skolen. I en skolehverdag skal eye-tracking-data kunne omsættes til pålidelige mål med praktisk relevans, fx til undervisningsevaluering. Dette studie præsenterer øjenbevægelsesmålet fokusord, der er udviklet til at opmærke nedbrud i elevers flydende læsning og dermed et forsøg på at oversætte eye-tracking-data til læsefaglig indsigt. Studiet er designet til at validere målets pålidelighed som læse-/ stave-indikator og endvidere målemetodens robusthed. 84 elever fra fem 4.-klasser deltog, hvoraf data fra 68 elever indgår. Udover elevernes eksisterende resultater i læse-/stavetest, optog vi deres øjenbevægelser under selvstændig højtlæsning. Vi finder stærke korrelationer mellem øjenbevægelser og læse-/stavetestresultater, som indikerer målemetodens robusthed. Videre korrelerer fokusord med klassiske øjenbevægelsesmål, hvilket er tegn på samstemmende validitet. Endelig forklarer fokusordene unik variation i elevernes læseforståelseseffektivitet og stavefærdighed ud over, hvad det stærkest korrelerede klassiske mål, fikseringstid, forklarer. Resultaterne understøtter, at fokusordsprocent er robust og tæt forbundet med læse- og stavefærdigheder.

show abstract

Section: Indledningunclassified

Måling af flydende læsning med øjenbevægelser i skolen

Klerke,

Fuglsang Engmose

2024

View full text Add to dashboard Cite

show abstract

“…Autism Spectrum enhance accuracy, and also facilitate comprehension of the techniques and algorithms employed for various types of data. Multiple studies have been conducted on ASD [22][23][24][25][26][27][28], ADHD [29][30][31], ID [9,10,32], SLD [33,34], CD [35], and NDs [4,19,20,31,[36][37][38], providing evidence that ML algorithms can enhance diagnostic strategies for NDs. Further, more research efforts that seek to investigate ML approaches for early detection and diagnosis of NDs in real-life situations are crucial for ensuring timely intervention and optimizing lifelong outcomes [17,19,20,[39][40][41].…”

Section: Introductionmentioning

confidence: 99%

Constructing Features for Screening Neurodevelopmental Disorders Using Grammatical Evolution

Toki,

Tatsis,

Pange

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Developmental domains refer to different areas of a child’s growth and maturation, including physical, language, cognitive, and social–emotional skills. Understanding these domains helps parents, caregivers, and professionals track a child’s progress and identify potential areas of concern. Nevertheless, due to the high level of heterogeneity and overlap, neurodevelopmental disorders may go undiagnosed in children for a crucial period. Detecting neurodevelopmental disorders at an early stage is fundamental. Digital tools like artificial intelligence can help clinicians with the early detection process. To achieve this, a new method has been proposed that creates artificial features from the original ones derived from the SmartSpeech project, using a feature construction procedure guided by the Grammatical Evolution technique. The new features from a machine learning model are used to predict neurodevelopmental disorders. Comparative experiments demonstrated that using the feature creation method outperformed other machine learning methods for predicting neurodevelopmental disorders. In many cases, the reduction in the test error reaches up to 65% to the next better one.

show abstract

“…Eye tracking is used to study a variety of topics within several areas of research, such as medicine, education and psychology (Henderson et al, 2015;Mcdonald et al, 2015;Ekstrand et al, 2021). Its' temporal and spatial sensitivity makes it particularly suitable for investigations into the reading process (Carter and Luke, 2020).…”

Section: Introductionmentioning

confidence: 99%

Eye movements are stable predictors of word reading ability in young readers

et al. 2023

View full text Add to dashboard Cite

During the first years of formal instruction in reading, there are developmental changes to the characteristics of children’s eye movements that correspond to their progress. Generally, these changes are driven by improved text processing and a shift from reliance on sub-lexical to lexical processes. Currently, however, little is known about to what extent early eye movements during reading in ecological contexts account for variations in later word reading ability. In this paper we investigate this association in 164 children in first grade and 206 children in second grade. We recorded their eye movements during normal text passage reading in an unrestricted eye tracking set-up. We analyzed to what extent they account for variation in word reading ability 1 year post-recording, and make comparisons to concurrent predictions. Regression analysis revealed that eye movements accounted for approximately 60% of the variance in concurrent word reading ability and approximately 48% 1 year later. Mean fixation duration explained unique variance in reading ability and largely drives the correlation. Proportion of regressions was not a significant longitudinal predictor among the youngest readers. The difference between the concurrent and longitudinal predictions was greatest in the younger children, which was in line with our expectation. Findings are discussed in relation to current models of word reading. Our results suggest that eye movements are stable predictors of word reading ability. Ultimately, knowledge of what can be gleaned from early readers’ natural eye movements about later word reading ability could help inform assessments of reading development in the educational setting, where the presence of digital assessment tools is growing.

show abstract

Screening for Reading Difficulties: Comparing Eye Tracking Outcomes to Neuropsychological Assessments

Cited by 11 publications

References 43 publications

Måling af flydende læsning med øjenbevægelser i skolen

Måling af flydende læsning med øjenbevægelser i skolen

Constructing Features for Screening Neurodevelopmental Disorders Using Grammatical Evolution

Eye movements are stable predictors of word reading ability in young readers

Contact Info

Product

Resources

About