Dyslexia Diagnostics Based on Eye Movements and Artificial Intelligence Methods: A Review

161

Abstract

The review considers methods of dyslexia diagnostics based on eye movement data and implemented on the basis of artificial intelligence. A number of studies have shown that eye movements in people with dyslexia may differ from those of people with normal reading abilities. Since 2015, studies have begun to appear in which the eye movements of observers with and without dyslexia were analyzed using various artificial intelligence methods. To date, there are a number of papers using both simple and more complex models (with neural networks and deep learning). This review discusses what accuracy of diagnosis has been achieved by researchers, for which groups of subjects and for which languages the current results have been shown, what types of algorithms have been used, and other practical aspects of conducting such diagnosis. According to the data analyzed, dyslexia diagnostics by eye movements and artificial intelligence methods is very promising and may have a significant impact on early diagnosing of reading problems.

General Information

Keywords: eye-tracking, eye movements, dyslexia, artificial intelligence, diagnostics methods

Journal rubric: Theoretical Research

Article type: scientific article

DOI: https://doi.org/10.17759/cpse.2023120301

Funding. This work is the result of a research project implemented as part of the Basic Research Program at the National Research University Higher School of Economics (HSE University). The work of M. Gracheva was partially supported within the state task of the IITP RAS (R&D registration number 122041100148-0 from March 13, 2023).

Received: 03.07.2023

Accepted:

For citation: Gracheva M.A., Shalileh S. Dyslexia Diagnostics Based on Eye Movements and Artificial Intelligence Methods: A Review [Elektronnyi resurs]. Klinicheskaia i spetsial'naia psikhologiia = Clinical Psychology and Special Education, 2023. Vol. 12, no. 3, pp. 1–29. DOI: 10.17759/cpse.2023120301. (In Russ., аbstr. in Engl.)

References

  1. Akhutina T.V., Inshakova O.B. Neiropsikhologicheskaya diagnostika, obsledovanie pis'ma i chteniya mladshikh shkol'nikov [Neuropsychological diagnostics, examination of writing and reading of younger students]. Moscow: V. Sekachev, 2016. 180 p. (In Russ.).
  2. Barabanshchikov V.A., Zhegallo A.V. Aitreking: Metody registratsii dvizhenii glaz v psikhologicheskikh issledovaniyakh i praktike [Eyetracking: Methods of eye movements registration in psychological research and practice]. Moscow: Kogito-Tsentr, 2014. 128 p. (In Russ.).
  3. Bezrukikh M.M. Trudnosti obucheniya v nachal'noi shkole. Prichiny, diagnostika, kompleksnaya pomoshch' [Learning difficulties in elementary school. Causes, diagnosis, complex help]. Moscow: Eksmo, 2009. 464 p. (In Russ.).
  4. Glozman Zh.M., Potanina A.YU., Soboleva A.E. Neiropsikhologicheskaya diagnostika v doshkol'nom vozraste [Neuropsychological diagnostics in preschool age], 2nd ed. Saint-Petersburg: Piter, 2008. 80 p. (In Russ.).
  5. Gol'dina S.M., Laurinavichyute A.K., Lopukhina A.A. et al. Osobennosti dvizhenii glaz pri chtenii u detei s disleksiei. Proceedings of the First National congress on cognitive research, artificial intelligence and neuroinformatics, Moscow, October 10–16, 2020. Vol. 1. Moscow: Natsional'nyi issledovatel'skii yadernyi universitet "MIFI", 2021, pp. 497–500. (In Russ.).
  6. Goodfellow I., Courville A., Bengio Y. Glubokoe obuchenie [Deep learning]. Moscow: DMK-Press, 2018. 652 p. (In Russ.).
  7. Dorofeeva S.V. Rechevoi defitsit i disleksiya: ehksperimental'noe issledovanie russkogovoryashchikh detei [Speech deficit and dyslexia: An experimental study of Russian-speaking children]. PhD (Psychology) Thesis. Moscow, 2020. 68 p. (In Russ.).
  8. Dorofeeva S.V., Reshetnikova V.A., Zyryanov A.S. et al. Batareya testov dlya vyyavleniya osobennostei fonologicheskoi obrabotki u russkoyazychnykh detei: dannye normy i gruppy detei s disleksiei [A battery of tests to identify the features of phonological processing in Russian-speaking children: data from the norm and the group of children with dyslexia]. In A.K. Krylov, V.D. Solov'ev (eds.), Proceedings of the 8th International conference on cognitive sciences, Svetlogorsk, October 18–21,2018. Moscow: Publ. of Institute of Psychology RAS, 2018, pp. 331–333. (In Russ.).
  9. Kornev A.N. Osnovy logopatologii detskogo vozrasta: klinicheskie i psikhologicheskie aspekty [Fundamentals of childhood speech therapy: Clinical and psychological aspects]. Saint-Petersburg: Rech', 2006. 380 p. (In Russ.).
  10. Kornev A.N., Oganov S.R., Gal'perina E.I. Formirovanie psikhofiziologicheskikh mekhanizmov ponimaniya pis'mennykh tekstov: registratsiya dvizhenii vzora pri chtenii u detei s disleksiei 9–11 i 12–13 let i zdorovykh sverstniko v [Development of the psychophysiological mechanisms in the comprehension of printed texts: eye tracking during text reading in healthy and dyslexic children aged 9–11 and 12–13 years]. Fiziologiya cheloveka= Human Physiology, 2019, vol. 45, no. 3, pp. 24–30. DOI: 10.1134/S0131164619030081 (In Russ., abstr. in Engl.).
  11. Lalaeva R.I. Narusheniya chteniya i puti ikh korrektsii u mladshikh shkol'nikov. Uchebnoe posobie [Reading disorders and ways of their correction in younger students. Tutorial]. Saint-Petersburg: Soyuz, 2002. 224 p. (In Russ.).
  12. Mirkin B.G. Vvedenie v analiz dannykh: uchebnik i praktikum [Introduction to data analysis: Textbook and practice]. Moscow: Yurait, 2023. 174 p. (In Russ.).
  13. Oganov S.R., Kornev A.N. Kak glaz skaniruet tekst pri chtenii: osobennosti fiksatsii na tekste u detei s disleksiei [How the eye scans the text when reading: features of fixations on the text in children with dyslexia]. Meditsina: teoriya i praktika = Medicine: theory and practice, 2019. Vol. 4, no 5, pp. 400–401. (In Russ.).
  14. Oganov S.R., Kornev A.N. Okulomotornye referenty deyatel'nosti chteniya u detei s disleksiei 9–11 let [Oculomotor referents of reading activity in children with dyslexia aged 9–11]. Fiziologiya cheloveka = Human Physiology, 2023. Vol. 49, no. 3, pp. 34–41. DOI: 10.31857/S0131164622600872 (In Russ., abstr. in Engl.).
  15. Rusetskaya M.N. Narusheniya chteniya u mladshikh shkol'nikov: Analiz rechevykh i zritel'nykh prichin [Reading disorders in younger students: Analysis of speech and visual causes]. Saint-Petersburg: KARO, 2007. 192 p. (In Russ.).
  16. Rychkova S.I., Likhvantseva V.G. Zritel'nye narusheniya u patsientov s disleksiei (obzor literatury) [Visual disorders in patients with dyslexia (literature review)]. The EYE GLAZ, 2022. Vol. 24, no. 2, pp. 47–54. DOI: 10.33791/2222-4408-2022-2-47-54. (In Russ., abstr. in Engl.).
  17. Yarbus A.L. Rol' dvizhenii glaz v protsesse zreniya [Eye movements in vision]. Moscow: Nauka, 1965. 166 p. (In Russ.).
  18. Albon E., Adi Y., Hyde C. The effectiveness and cost-effectiveness of coloured filters for reading disability: a systematic review. Birmingham: University of Birmingham, 2008. 121 p.
  19. Al-Edaily A., Al-Wabil A., Al-Ohali Y. Dyslexia Explorer: A screening system for learning difficulties in the Arabic language using eye tracking. In Proceedings of Human Factors in Computing and Informatics: First International Conference, SouthCHI 2013, Maribor, Slovenia, July 1-3, 2013, 2013, pp. 831–834. DOI: 10.1007/978-3-642-39062-3_63
  20. Asvestopoulou T., Manousaki V., Psistakis A. et al. DysLexML: Screening tool for dyslexia using machine learning. 2019. URL: http://arxiv.org/abs/1903.06274 (Accessed: 10.10.2023).
  21. Australian Dyslexia Association. Dyslexia in Australia. URL: https://dyslexiaassociation.org.au/dyslexia-in-australia/ (Accessed: 10.10.2023).
  22. Benfatto M.N., Seimyr G.Ö., Ygge J. et al. Screening for dyslexia using eye tracking during reading. PLoS ONE. 2016. Vol. 11, no. 12, article e165508. DOI: 10.1371/journal.pone.0165508
  23. Biscaldi M., Fischer B., Hartnegg K. Voluntary saccadic control in dyslexia. Perception. 2000. Vol. 29, no. 5, pp. 509–521. DOI: 10.1068/p2666a
  24. Bucci M.P., Brémond-Gignac D., Kapoula Z. Poor binocular coordination of saccades in dyslexic children. Graefe's Archive for Clinical and Experimental Ophthalmology. 2008. Vol. 246, pp. 417–428. DOI: 10.1007/s00417-007-0723-1
  25. Cortes C., Vapnik V. Support-vector networks. Machine Learning, 1995. Vol. 20, pp. 273–297. DOI: 10.1007%2FBF00994018
  26. Cover T., Hart P. Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 1967. Vol. 13, no. 1, pp. 21–27. DOI: 10.1109/TIT.1967.1053964
  27. De Luca M., Borrelli M., Judica A. et al. Reading words and pseudowords: An eye movement study of developmental dyslexia. Brain and Language, 2002. Vol. 80, pp. 617–626. DOI: 10.1006/brln.2001.2637
  28. Deans P., O’Laughlin L., Brubaker B. et al. Use of eye movement tracking in the differential diagnosis of attention deficit hyperactivity disorder (ADHD) and reading disability. Psychology, 2010. Vol. 1 (4), pp. 238–246. DOI: 10.4236/psych.2010.14032
  29. El Hmimdi A.E., Ward L.M., Palpanas T. et al. Predicting dyslexia and reading speed in adolescents from eye movements in reading and non-reading tasks: A machine learning approach. Brain Sciences, 2021. Vol. 11 (10), article 1337. DOI: 10.3390/brainsci11101337
  30. Fischer B., Hartnegg K. Stability of gaze control in dyslexia. Strabismus, 2000. Vol. 8 (2), pp. 119–122. DOI: 10.1076/0927-3972(200006)821-2FT119
  31. Franzen L., Stark Z., Johnson A.P. Individuals with dyslexia use a different visual sampling strategy to read text. Scientific Reports, 2021. Vol. 11, article 6449. DOI: 10.1038/s41598-021-84945-9
  32. Henderson L.M., Taylor R.H., Barrett B. et al. Treating reading difficulties with colour. BMJ, 2014. Vol. 349, article g5160. DOI: 10.1136/bmj.g5160
  33. Ho T.K. Random decision forests. Proceedings of 3rd international Conference on Document Analysis and Recognition. IEEE, 1995. Vol. 1, pp. 278–282. DOI: 10.1109/ICDAR.1995.598994
  34. Høien T., Lundberg I. Dyslexia: From theory to intervention. Part of the Neuropsychology & Cognition book series, vol. 18. Springer, 2000. 230 p. DOI: 10.1007/978-94-017-1329-0
  35. Hyönä J., Olson R.K. Eye fixation patterns among dyslexic and normal readers: Effects of word length and word frequency. Journal of Experimental Psychology: Learning, Memory, and Cognition, 1995. Vol. 21 (6), pp. 1430–1440. DOI: 10.1037/0278-7393.21.6.1430
  36. Jainta S., Kapoula Z. Dyslexic children are confronted with unstable binocular fixation while reading. PLoS ONE, 2011. Vol. 6 (4), article e18694. DOI: 10.1371/journal.pone.0018694
  37. Jakovljević T., Janković M.M., Savić A.M. et al. The relation between physiological parameters and colour modifications in text background and overlay during reading in children with and without dyslexia. Brain sciences, 2021. Vol. 11 (5), article 539. DOI: 10.3390/brainsci11050539
  38. Jothi Prabha A., Bhargavi R. Eye movement feature set and predictive model for dyslexia: Feature set and predictive model for dyslexia. International Journal of Cognitive Informatics and Natural Intelligence, 2021. Vol. 15 (4), pp. 1–22. DOI: 10.4018/IJCINI.20211001.oa28
  39. Jothi Prabha A., Bhargavi R. Prediction of dyslexia from eye movements using machine learning. IETE Journal of Research, 2019. Vol. 68 (2), pp. 814–823. DOI: 03772063.2019.1622461
  40. Jothi Prabha A., Bhargavi R. Predictive model for dyslexia from fixations and saccadic eye movement events. Computer Methods and Programs in Biomedicine, 2020. Vol. 195, article 105538. DOI: 10.1016/j.cmpb.2020.105538
  41. Jothi Prabha A., Bhargavi R., Rani B.D. Prediction of dyslexia severity levels from fixation and saccadic eye movement using machine learning. Biomedical Signal Processing and Control, 2023. Vol. 79, article. 104094. DOI: 10.1016/j.bspc.2022.104094
  42. Kaisar S. Developmental dyslexia detection using machine learning techniques: A survey. ICT Express. 2020, vol. 6, no. 3, pp. 181–184. DOI: 10.1016/j.icte.2020.05.006
  43. Levy-Schoen A. Flexible and/or rigid control of oculomotor scanning behavior. In D.F. Fisher, R.A. Monty, J.W. Senders (eds.), Eye Movements: Cognition and Visual Perception. Hillsdale (NJ): Lawrence Erlbaum, 1981, pp. 299–314. DOI: 10.4324/9781315437415
  44. Lustig J. Identifying dyslectic gaze pattern. Comparison of methods for identifying dyslectic readers based on eye movement patterns. PhD Thesis. KTH royal institute of technology. 2016. URL: https://www.diva-portal.org/smash/record.jsf?pid=diva2%3A955646&dswid=-7506 (Accessed: 21.10.2023)
  45. McCullagh P. Generalized linear models. New York: Routledge. 1989. 532 p. DOI: 10.1201/9780203753736
  46. Nerušil B., Polec J., Škunda J. et al. Eye tracking based dyslexia detection using a holistic approach. Scientific Reports, 2021. Vol. 11, article 15687. DOI: 10.1038/s41598-021-95275-1
  47. Olson R.K., Kliegl R., Davidson B.J. Dyslexic and normal readers’ eye movements. Journal of Experimental Psychology: Human Perception and Performance, 1983. Vol. 9, no. 5, pp. 816–825. DOI: 10.1037/0096-1523.9.5.816
  48. Parshina O., Lopukhina A., Goldina S. et al. Global reading processes in children with high risk of dyslexia: A scanpath analysis. Annals of Dyslexia, 2022. Vol. 72, pp. 403–425. DOI: 10.1007/s11881-021-00251-z
  49. Pavlidis G.T. Do eye movements hold the key to dyslexia? Neuropsychologia, 1981. Vol. 19, no. 1, pp. 57–64. DOI: 10.1016/0028-3932(81)90044-0
  50. Peterson R.L., Pennington B.F. Developmental dyslexia. Lancet, 2012. Vol. 379, pp. 1997–2007. DOI: 10.1016/S0140-6736(12)60198-6
  51. Peterson R.L., Pennington B.F. Developmental dyslexia. Annual Review of Clinical Psychology, 2015. Vol. 11, pp. 283–307. DOI: 10.1146/annurev-clinpsy-032814-112842
  52. Pirozzolo F.J., Rayner K. The neural control of eye movements in acquired and developmental reading disorders. Studies in Neurolinguistics, 1979. Vol. 4, pp. 97–123. DOI: 10.1016/B978-0-12-746304-9.50009-4
  53. Raatikainen P., Hautala J., Loberg O. et al. Detection of developmental dyslexia with machine learning using eye movement data. Array, 2021. Vol. 12, article 100087. DOI: 10.1016/j.array.2021.100087
  54. Rayner K. Eye movements and the perceptual span in beginning and skilled readers. Journal of Experimental Child Psychology. 1986. Vol. 41 (2), pp. 211–236. DOI: 10.1016/0022-0965(86)90037-8
  55. Rayner K. Eye movements in reading and information processing: 20 years of research. Psychological Bulletin, 1998. Vol. 124 (3), pp. 372–422. DOI: 10.1037/0033-2909.124.3.372
  56. Rayner K. Eye movements, perceptual span, and reading disability. Annals of Dyslexia. 1983. Vol. 33, pp. 163–173. DOI: 10.1007/BF02648003
  57. Rayner K. The role of eye movements in learning to read and reading disability. Remedial and Special Education. 1985. Vol. 6, pp. 53–60. DOI: 10.1177/074193258500600609
  58. Razuk M., Barela J.A., Peyre H. et al. Eye movements and postural control in dyslexic children performing different visual tasks. PLoS ONE, 2018. Vol. 13, article e0198001. DOI: 10.1371/journal.pone.0198001
  59. 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, article 16. DOI: 10.1145/2745555.2746644
  60. Smyrnakis I., Andreadakis V., Selimis V. et al. RADAR: A novel fast-screening method for reading difficulties with special focus on dyslexia. Plos ONE, 2017. Vol. 12 (8), article e0182597. DOI: 10.1371/journal.pone.0182597
  61. Tiadi A., Gérard C.L., Peyre H. et al. Immaturity of visual fixations in dyslexic children. Frontiers in Human Neuroscience, 2016. Vol. 10, article 58. DOI: 10.3389/fnhum.2016.00058
  62. Tinker M.A. Recent studies of eye movements in reading. Psychological Bulletin, 1958. Vol. 55, no. 4, pp. 215–231. DOI: 10.1037/h0041228
  63. Tinker M.A. The study of eye movements in reading. Psychological Bulletin, 1946. Vol. 43, no. 2, pp. 93–120. DOI: 10.1037/h0063378
  64. Usman O.L., Muniyandi R.C., Omar K. et al. Advance machine learning methods for dyslexia biomarker detection: A review of implementation details and challenges. IEEE Access, 2021. Vol. 9, pp. 36879–36897. DOI: 10.1109/ACCESS.2021.3062709
  65. Vajs I., Kovic V., Papic T. et al. Dyslexia detection in children using eye tracking data based on VGG16 network. In Proceedings of European Signal Processing Conference (EUSIPCO), 2022, pp. 1601–1605. DOI: 10.23919/EUSIPCO55093.2022.9909817
  66. Vajs I., Ković V., Papić T. et al. Spatiotemporal eye-tracking feature set for improved recognition of dyslexic reading patterns in children. Sensors, 2022. Vol. 22 (13), article 4900. DOI: 10.3390/s22134900 
  67. Vajs I.A., Kvascev G.S., Papic T.M. et al. Eye-tracking image encoding: Autoencoders for the crossing of language boundaries in developmental dyslexia detection. IEEE Access, 2023. Vol. 11, pp. 3024–3033. DOI: 10.1109/ACCESS.2023.3234438
  68. Vajs I., Papić T., Ković V. et al. Accessible dyslexia detection with real-time reading feedback through robust interpretable eye-tracking features. Brain Sciences, 2023. Vol. 13 (3), article 405. DOI: 10.3390/brainsci13030405
  69. Vellutino F.R., Fletcher J.M., Snowling M.J. et al. Specific reading disability (dyslexia): What have we learned in the past four decades? Journal of Child Psychology and Psychiatry, 2004. Vol. 45 (1), pp. 2–40. DOI: 10.1046/j.0021-9630.2003.00305.x
  70. Ward L.M., Kapoula Z. Differential diagnosis of vergence and saccade disorders in dyslexia. Scientific Reports, 2020. Vol. 10, article 22116. DOI: 10.1038/s41598-020-79089-1
  71. Wu Y.J., Yang W.H., Wang Q.X. et al. Eye-movement patterns of Chinese children with developmental dyslexia during the Stroop test. Biomedical and Environmental Sciences, 2018. Vol. 31 (9), pp. 677–685. DOI: 10.3967/bes2018.092

Information About the Authors

Maria A. Gracheva, PhD in Biology, Senior Researcher of Vision Systems Lab, Institute for Information Transmission Problems (Kharkevich Institute), Junior Researcher of Vision Modelling Laboratory, HSE University, Moscow, Russia, Moscow, Russia, ORCID: https://orcid.org/0000-0003-0196-148X, e-mail: mg.iitp@gmail.com

Soroosh Shalileh, PhD in Engineering, Head of Vision Modelling Laboratory, HSE University, Moscow, Russia, ORCID: https://orcid.org/0000-0001-6226-4990, e-mail: sr.shalileh@gmail.com

Metrics

Views

Total: 357
Previous month: 36
Current month: 23

Downloads

Total: 161
Previous month: 24
Current month: 27