{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T06:04:21Z","timestamp":1792821861565,"version":"4.5.0"},"reference-count":63,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T00:00:00Z","timestamp":1700611200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009409","name":"Russian Science Support Foundation","doi-asserted-by":"publisher","award":["14.641.31.0004"],"award-info":[{"award-number":["14.641.31.0004"]}],"id":[{"id":"10.13039\/100009409","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>This paper represents our research results in the pursuit of the following objectives: (i) to introduce a novel multi-sources data set to tackle the shortcomings of the previous data sets, (ii) to propose a robust artificial intelligence-based solution to identify dyslexia in primary school pupils, (iii) to investigate our psycholinguistic knowledge by studying the importance of the features in identifying dyslexia by our best AI model. In order to achieve the first objective, we collected and annotated a new set of eye-movement-during-reading data. Furthermore, we collected demographic data, including the measure of non-verbal intelligence, to form our three data sources. Our data set is the largest eye-movement data set globally. Unlike the previously introduced binary-class data sets, it contains (A) three class labels and (B) reading speed. Concerning the second objective, we formulated the task of dyslexia prediction as regression and classification problems and scrutinized the performance of 12 classifications and eight regressions approaches. We exploited the Bayesian optimization method to fine-tune the hyperparameters of the models: and reported the average and the standard deviation of our evaluation metrics in a stratified ten-fold cross-validation. Our studies showed that multi-layer perceptron, random forest, gradient boosting, and k-nearest neighbor form the group having the most acceptable results. Moreover, we showed that although separately using each data source did not lead to accurate results, their combination led to a reliable solution. We also determined the importance of the features of our best classifier: our findings showed that the IQ, gender, and age are the top three important features; we also showed that fixation along the y-axis is more important than other fixation data. Dyslexia detection, eye fixation, eye movement, demographic, classification, regression, artificial intelligence.<\/jats:p>","DOI":"10.1371\/journal.pone.0292047","type":"journal-article","created":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T13:24:05Z","timestamp":1700659445000},"page":"e0292047","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":27,"title":["Identifying dyslexia in school pupils from eye movement and demographic data using artificial intelligence"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6226-4990","authenticated-orcid":true,"given":"Soroosh","family":"Shalileh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitry","family":"Ignatov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anastasiya","family":"Lopukhina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olga","family":"Dragoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"pone.0292047.ref001","article-title":"Dyslexia: Perspectives, challenges and treatment options","author":"M Frazier","year":"2016","journal-title":"Nova Biomedical"},{"issue":"4","key":"pone.0292047.ref002","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1002\/dys.384","article-title":"A thirteen-year follow-up study of young Norwegian adults with dyslexia in childhood: reading development and educational levels","volume":"15","author":"AM Undheim","year":"2009","journal-title":"Dyslexia"},{"key":"pone.0292047.ref003","doi-asserted-by":"crossref","DOI":"10.4324\/9780203432600","volume-title":"Living with dyslexia: The social and emotional consequences of specific learning difficulties\/disabilities","author":"B Riddick","year":"2012"},{"issue":"2","key":"pone.0292047.ref004","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1111\/j.1467-9604.2010.01442.x","article-title":"The impact of dyslexia on pupils\u2019 self-esteem","volume":"25","author":"J Glazzard","year":"2010","journal-title":"Support for learning"},{"issue":"1","key":"pone.0292047.ref005","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1111\/j.1460-6984.2011.00081.x","article-title":"Interventions for children\u2019s language and literacy difficulties","volume":"47","author":"MJ Snowling","year":"2012","journal-title":"International Journal of Language & Communication Disorders"},{"issue":"1","key":"pone.0292047.ref006","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1046\/j.0021-9630.2003.00305.x","article-title":"Specific reading disability (dyslexia): What have we learned in the past four decades?","volume":"45","author":"FR Vellutino","year":"2004","journal-title":"Journal of child psychology and psychiatry"},{"issue":"4","key":"pone.0292047.ref007","doi-asserted-by":"crossref","DOI":"10.11648\/j.sjedu.20190704.11","article-title":"An overview of dyslexia: definition, characteristics, assessment, identification, and intervention","volume":"7","author":"J Roitsch","year":"2019","journal-title":"Science Journal of Education"},{"key":"pone.0292047.ref008","doi-asserted-by":"crossref","first-page":"36879","DOI":"10.1109\/ACCESS.2021.3062709","article-title":"Advance machine learning methods for Dyslexia biomarker detection: a review of implementation details and challenges","volume":"9","author":"OL Usman","year":"2021","journal-title":"IEEE Access"},{"issue":"3","key":"pone.0292047.ref009","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.icte.2020.05.006","article-title":"Developmental dyslexia detection using machine learning techniques: A survey","volume":"6","author":"S Kaisar","year":"2020","journal-title":"ICT Express"},{"issue":"3","key":"pone.0292047.ref010","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"C Cortes","year":"1995","journal-title":"Machine learning"},{"issue":"1","key":"pone.0292047.ref011","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine learning"},{"issue":"10","key":"pone.0292047.ref012","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.3390\/brainsci11101337","article-title":"Predicting dyslexia and reading speed in adolescents from eye movements in reading and non-reading tasks: A machine learning approach","volume":"11","author":"AE El Hmimdi","journal-title":"Brain Sciences"},{"key":"pone.0292047.ref013","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1007\/s00417-006-0490-4","article-title":"Evidence for frequent divergence impairment in French dyslexic children: deficit of convergence relaxation or of divergence per se?","volume":"245","author":"Z Kapoula","year":"2006","journal-title":"Graefe\u2019s Archive for Clinical and Experimental Ophthalmology"},{"key":"pone.0292047.ref014","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/s00417-007-0723-1","article-title":"Poor binocular coordination of saccades in dyslexic children","volume":"246","author":"MP. Bucci","year":"2008","journal-title":"Graefe\u2019s archive for clinical and experimental ophthalmology"},{"key":"pone.0292047.ref015","doi-asserted-by":"crossref","first-page":"100087","DOI":"10.1016\/j.array.2021.100087","article-title":"Detection of developmental dyslexia with machine learning using eye movement data","volume":"12","author":"Peter Raatikainen","year":"2021","journal-title":"Array"},{"issue":"9","key":"pone.0292047.ref016","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.3390\/children9091337","article-title":"Novel Ensemble Model Recommendation Approach for the Detection of Dyslexia","volume":"9","author":"AS AlGhamdi","year":"2022","journal-title":"Children"},{"issue":"12","key":"pone.0292047.ref017","doi-asserted-by":"crossref","first-page":"e0241687","DOI":"10.1371\/journal.pone.0241687","article-title":"Predicting risk of dyslexia with an online gamified test","volume":"15","author":"L Rello","year":"2020","journal-title":"Plos one"},{"key":"pone.0292047.ref018","article-title":"Integrating oversampling and ensemble-based machine learning techniques for an imbalanced dataset in dyslexia screening tests","author":"S Kaisar","year":"2022","journal-title":"ICT Express"},{"key":"pone.0292047.ref019","first-page":"1","article-title":"Identifying Chinese Children with Dyslexia Using Machine Learning with Character Dictation","author":"S Man Kit Lee","year":"2022","journal-title":"Scientific Studies of Reading"},{"key":"pone.0292047.ref020","doi-asserted-by":"crossref","unstructured":"Vajs I., Kovi\u0107 V., Papi\u0107 T., Savi\u0107 AM. and Jankovi\u0107 MM. Dyslexia detection in children using eye tracking data based on VGG16 network. In: 2022 30th European Signal Processing Conference (EUSIPCO). IEEE; 2022. p. 1601\u20131605.","DOI":"10.23919\/EUSIPCO55093.2022.9909817"},{"key":"pone.0292047.ref021","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556. 2014."},{"issue":"5","key":"pone.0292047.ref022","doi-asserted-by":"crossref","first-page":"539","DOI":"10.3390\/brainsci11050539","article-title":"The relation between physiological parameters and colour modifications in text background and overlay during reading in children with and without dyslexia","volume":"11","author":"T. Jakovljevi\u0107","year":"2021","journal-title":"Brain sciences"},{"issue":"13","key":"pone.0292047.ref023","doi-asserted-by":"crossref","first-page":"4900","DOI":"10.3390\/s22134900","article-title":"Spatiotemporal eye-tracking feature set for improved recognition of dyslexic reading patterns in children","volume":"22","author":"I Vajs","year":"2022","journal-title":"Sensors"},{"issue":"3","key":"pone.0292047.ref024","doi-asserted-by":"crossref","first-page":"405","DOI":"10.3390\/brainsci13030405","article-title":"Accessible Dyslexia Detection with Real-Time Reading Feedback through Robust Interpretable Eye-Tracking Features","volume":"13","author":"I Vajs","year":"2023","journal-title":"Brain Sciences"},{"key":"pone.0292047.ref025","volume-title":"Workshop on Linguistic and Neurocognitive Resources (LiNCr2020)","author":"S Alexeeva","year":"2020"},{"issue":"3","key":"pone.0292047.ref026","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1134\/S0362119719030083","article-title":"Development of the psychophysiological mechanisms in the comprehension of printed texts: eye tracking during text reading in healthy and dyslexic children aged 9\u201311 and 12\u201314 years","volume":"45","author":"A Kornev","year":"2019","journal-title":"Human Physiology"},{"key":"pone.0292047.ref027","first-page":"1","article-title":"Global reading processes in children with high risk of dyslexia: a scanpath analysis","author":"O Parshina","year":"2022","journal-title":"Annals of Dyslexia"},{"issue":"12","key":"pone.0292047.ref028","doi-asserted-by":"crossref","first-page":"e0165508","DOI":"10.1371\/journal.pone.0165508","article-title":"Screening for dyslexia using eye tracking during reading","volume":"11","author":"M Nilsson Benfatto","year":"2016","journal-title":"PloS one"},{"issue":"8","key":"pone.0292047.ref029","doi-asserted-by":"crossref","first-page":"e0182597","DOI":"10.1371\/journal.pone.0182597","article-title":"RADAR: A novel fast-screening method for reading difficulties with special focus on dyslexia","volume":"12","author":"I Smyrnakis","year":"2017","journal-title":"PloS one"},{"key":"pone.0292047.ref030","doi-asserted-by":"crossref","unstructured":"Rello L, Ballesteros M. Detecting readers with dyslexia using machine learning with eye tracking measures. In: Proceedings of the 12th International Web for All Conference; 2015. p. 1\u20138.","DOI":"10.1145\/2745555.2746644"},{"issue":"3","key":"pone.0292047.ref031","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1109\/34.75512","article-title":"Small sample size effects in statistical pattern recognition: Recommendations for practitioners","volume":"13","author":"SJ Raudys","year":"1991","journal-title":"IEEE Transactions on pattern analysis and machine intelligence"},{"key":"pone.0292047.ref032","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.neuroimage.2017.06.061","article-title":"Cross-validation failure: Small sample sizes lead to large error bars","volume":"180","author":"G Varoquaux","year":"2018","journal-title":"Neuroimage"},{"key":"pone.0292047.ref033","doi-asserted-by":"crossref","first-page":"47643","DOI":"10.1109\/ACCESS.2022.3169512","article-title":"Stop oversampling for class imbalance learning: A review","volume":"10","author":"AS Tarawneh","year":"2022","journal-title":"IEEE Access"},{"issue":"2","key":"pone.0292047.ref034","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.jml.2011.02.004","article-title":"What is the scanpath signature of syntactic reanalysis?","volume":"65","author":"T Von der Malsburg","year":"2011","journal-title":"Journal of Memory and Language"},{"issue":"1","key":"pone.0292047.ref035","doi-asserted-by":"crossref","first-page":"18","DOI":"10.3758\/s13414-020-02185-x","article-title":"Reading proficiency predicts the extent of the right, but not left, perceptual span in older readers","volume":"83","author":"A Veldre","year":"2021","journal-title":"Attention, Perception, & Psychophysics"},{"issue":"2","key":"pone.0292047.ref036","first-page":"219","article-title":"Silent reading in Russian primary schoolchildren: An eye tracking study","volume":"14","author":"A Korneev","year":"2017","journal-title":"Psychology Journal of Higher School of Economics"},{"issue":"3","key":"pone.0292047.ref037","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.3758\/s13428-018-1051-6","article-title":"Russian Sentence Corpus: Benchmark measures of eye movements in reading in Russian","volume":"51","author":"AK Laurinavichyute","year":"2019","journal-title":"Behavior research methods"},{"issue":"4","key":"pone.0292047.ref038","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1016\/j.chb.2005.12.013","article-title":"Utilizing eye movements: Overcoming inaccuracy while tracking the focus of attention during reading","volume":"22","author":"A Hyrskykari","year":"2006","journal-title":"Computers in human behavior"},{"issue":"4","key":"pone.0292047.ref039","doi-asserted-by":"crossref","first-page":"1374","DOI":"10.3758\/s13428-018-1050-7","article-title":"A novel evaluation of two related and two independent algorithms for eye movement classification during reading","volume":"50","author":"L Friedman","year":"2018","journal-title":"Behavior Research Methods"},{"key":"pone.0292047.ref040","unstructured":"Kornev A, Ishimova O. . St Petersburg, Russia: Politechnicheski Universitet. 2010."},{"key":"pone.0292047.ref041","doi-asserted-by":"crossref","first-page":"223","DOI":"10.53841\/bpstest.2003.spm","volume-title":"Raven Progressive Matrices","author":"J Raven","year":"2003"},{"issue":"1","key":"pone.0292047.ref042","first-page":"4","article-title":"Assessing the validity of the standardized assessment of reading skills in Russian and verifying the relevance of available normative data","volume":"6","author":"SV Dorofeeva","year":"2019","journal-title":"The Russian Journal of Cognitive Science"},{"key":"pone.0292047.ref043","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.neucom.2020.07.061","article-title":"On hyperparameter optimization of machine learning algorithms: Theory and practice","volume":"415","author":"L Yang","year":"2020","journal-title":"Neurocomputing"},{"issue":"117-129","key":"pone.0292047.ref044","first-page":"2","article-title":"The application of Bayesian methods for seeking the extremum","volume":"2","author":"J Mockus","year":"1978","journal-title":"Towards global optimization"},{"key":"pone.0292047.ref045","unstructured":"Louppe G, Kuma M, Nahrstaedt H. Bayesian optimization with skopt;. Available from: https:\/\/scikit-optimize.github.io\/stable\/auto_examples\/bayesian-optimization.html#sphx-glr-auto-examples-bayesian-optimization-py."},{"key":"pone.0292047.ref046","unstructured":"O\u2019Malley T, Bursztein E, Long J, Chollet F, Jin H, Invernizzi L, et al. KerasTuner; 2019. https:\/\/github.com\/keras-team\/keras-tuner."},{"key":"pone.0292047.ref047","volume-title":"Probabilistic machine learning: an introduction","author":"KP Murphy","year":"2022"},{"key":"pone.0292047.ref048","volume-title":"Algorithms for optimization","author":"MJ Kochenderfer","year":"2019"},{"issue":"1","key":"pone.0292047.ref049","first-page":"503","article-title":"On the limited memory BFGS method for large scale optimization","volume":"45","author":"DC Liu","year":"1989","journal-title":"Mathematical programming"},{"issue":"3","key":"pone.0292047.ref050","doi-asserted-by":"crossref","first-page":"349","DOI":"10.4310\/SII.2009.v2.n3.a8","article-title":"Multi-class adaboost","volume":"2","author":"T Hastie","year":"2009","journal-title":"Statistics and its Interface"},{"key":"pone.0292047.ref051","first-page":"1189","article-title":"Greedy function approximation: a gradient boosting machine","author":"JH Friedman","year":"2001","journal-title":"Annals of statistics"},{"issue":"9","key":"pone.0292047.ref052","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1145\/361002.361007","article-title":"Multidimensional binary search trees used for associative searching","volume":"18","author":"JL Bentley","year":"1975","journal-title":"Communications of the ACM"},{"issue":"3","key":"pone.0292047.ref053","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"J Platt","year":"1999","journal-title":"Advances in large margin classifiers"},{"issue":"3","key":"pone.0292047.ref054","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: a library for support vector machines","volume":"2","author":"CC Chang","year":"2011","journal-title":"ACM transactions on intelligent systems and technology (TIST)"},{"key":"pone.0292047.ref055","first-page":"4765","volume-title":"Advances in Neural Information Processing Systems","author":"SM Lundberg","year":"2017"},{"issue":"3","key":"pone.0292047.ref056","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","article-title":"Explaining prediction models and individual predictions with feature contributions","volume":"41","author":"E Strumbelj","year":"2014","journal-title":"Knowl Inf Syst"},{"key":"pone.0292047.ref057","doi-asserted-by":"crossref","unstructured":"Ignatov, D.I. and Kwuida, L., 2020. Interpretable concept-based classification with shapley values. In Ontologies and Concepts in Mind and Machine: 25th International Conference on Conceptual Structures, ICCS 2020, Bolzano, Italy, September 18\u201320, 2020, Proceedings 25 (pp. 90-102). Springer International Publishing.","DOI":"10.1007\/978-3-030-57855-8_7"},{"issue":"5895","key":"pone.0292047.ref058","doi-asserted-by":"crossref","first-page":"1502","DOI":"10.1126\/science.1160028","article-title":"Unsupervised natural experience rapidly alters invariant object representation in visual cortex","volume":"321","author":"N Li","year":"2008","journal-title":"science"},{"key":"pone.0292047.ref059","doi-asserted-by":"crossref","DOI":"10.1002\/9781118575574","volume-title":"Multivariate density estimation: theory, practice, and visualization","author":"DW Scott","year":"2015"},{"key":"pone.0292047.ref060","first-page":"7828","article-title":"Training normalizing flows with the information bottleneck for competitive generative classification","volume":"33","author":"L Ardizzone","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0292047.ref061","doi-asserted-by":"crossref","unstructured":"Shalileh S. Improving Maximum Likelihood Estimation Using Marginalization and Black-Box Variational Inference. In: International Conference on Intelligent Data Engineering and Automated Learning. Springer; 2021. p. 204\u2013212.","DOI":"10.1007\/978-3-030-91608-4_21"},{"issue":"72","key":"pone.0292047.ref062","first-page":"1","article-title":"(1 + \u03f5)-class Classification: an Anomaly Detection Method for Highly Imbalanced or Incomplete Data Sets","volume":"21","author":"M Borisyak","year":"2020","journal-title":"Journal of Machine Learning Research"},{"issue":"7","key":"pone.0292047.ref063","doi-asserted-by":"crossref","first-page":"e0254377","DOI":"10.1371\/journal.pone.0254377","article-title":"Least-squares community extraction in feature-rich networks using similarity data","volume":"16","author":"S Shalileh","year":"2021","journal-title":"Plos one"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0292047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T13:25:09Z","timestamp":1700659509000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0292047"}},"subtitle":[],"editor":[{"given":"Mohammad Amin","family":"Fraiwan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,11,22]]},"references-count":63,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2023,11,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0292047","relation":{"has-review":[{"id-type":"doi","id":"10.14293\/S2199-1006.1.SOR-UNCAT.A10664902.v1.RRETPB","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,22]]}}}