Dyscalculia Detection Using Machine Learning

  • Alka Subramanyam
  • Sonakshi Jyrwa
  • Juhi M. Bansinghani
  • Sarthak J. Dadhakar
  • Trena V. Dhingra
  • Umesh R. RamchandaniEmail author
  • Sharmila Sengupta
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11941)


A great amount of research is going on in the detection of learning disabilities, but the detection of Dyscalculia remains a tedious and time-consuming task even today. Various tests are conducted to detect if the patient has Dyscalculia and each test has to be evaluated manually as the scores alone are not sufficient to determine it. In some cases, Curriculum-Based Tests [CBTs] or Wide Range Achievement Tests [WRAT] or both need to be conducted after analysis of the results of the Woodcock-Johnson Tests. As a collaborative project between the Department of Psychiatry B.Y.L. Nair Ch. Hospital and Department of Computer Engineering, Vivekanand Education Society’s Institute of Technology a system is developed to help improve the detection of Dyscalculia. The Woodcock-Johnson Tests of Achievements are conducted by the doctors and the results of these tests determine the learning disability.


Decision tree Dyscalculia Learning disability Machine learning Random forest Woodcock-Johnson tests of achievements 


  1. 1.
  2. 2.
  3. 3.
  4. 4.
    Neurol (2001)Google Scholar
  5. 5.
    Desmonet, J.F., Taylor, M.J., Chaix, Y.: Development dyslexia. Lancet 363, 1451–1460 (2004).
  6. 6.
    Jordan, J. A., Wylie, J., Mulhern, G.: Phonological awareness and mathematical difficulty: a longitudinal perspective (2010)CrossRefGoogle Scholar
  7. 7.
    Karande, S., Bhosrekar, K., Kulkarni, M., Thakker, A.: Health-related quality of life of children with newly diagnosed specific learning disability. J. Trop. Pediatr. 55, 160–169 (2009) CrossRefGoogle Scholar
  8. 8.
    Kaufmann, L., Von Aster, M.: The diagnosis and management of dyscalculia. Dtsch. Arztebl. Int. 109(45), 767–778 (2012).
  9. 9.
  10. 10.
    Korhonen, J.G., Linnanmaki, K., Aunio, P.: Language and mathematical performance: a comparison of lower secondary school students with different levels of mathematical skills (2011)Google Scholar
  11. 11.
    Kucian, K., Kaufmann, L.: A developmental model of number representations. Behav. Brain Sci. 32, 340–341 (2009)CrossRefGoogle Scholar
  12. 12.
    Landerl, K., Moll, K.: Comorbidity of learning disorders: prevalence and familial transmission. J. Child Psychol. Psychiatry 5, 287–294 (2010)CrossRefGoogle Scholar
  13. 13.
    Manor, O., Shalev, R.S., Joseph, A., Gross-Tsur, V.: Arithmetic skills in kindergarten children with developmental language disorders. Eur. J. Paediatr. Neurol. 5, 71–77 (2001)CrossRefGoogle Scholar
  14. 14.
    Rubinstein, O., Bedard, A.C., Tannock, R.: Methylphenidate improves general but not core numerical abilities in ADHD children with co-morbid Dyscalculia or mathematical difficulties (2008)Google Scholar
  15. 15.
    Karande, S.: Current challenges in managing specific learning disability in Indian children. J. Postgrad. Med. 54, 75 (2008)CrossRefGoogle Scholar
  16. 16.
    Shavlev, R.S., Auerbach, J., Gross-Tsur, V.: Developmental Dyscalculia behavioural and attentional aspects: a research note (1995)Google Scholar
  17. 17.
    Shaywitz, S.: Dyslexia. N. Engl. J. Med. 338, 307–312 (1998)CrossRefGoogle Scholar
  18. 18.
    Von Aster, M.G., Shalev, R.: Number development and developmental Dyscalculia. Dev. Med. Child Neurol. 49, 868–873 (2007)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Alka Subramanyam
    • 1
  • Sonakshi Jyrwa
    • 1
  • Juhi M. Bansinghani
    • 2
  • Sarthak J. Dadhakar
    • 2
  • Trena V. Dhingra
    • 2
  • Umesh R. Ramchandani
    • 2
    Email author
  • Sharmila Sengupta
    • 2
  1. 1.Department of PsychiatryB.Y.L. Nair Ch. HospitalMumbaiIndia
  2. 2.Department of Computer EngineeringVivekanand Education Society’s Institute of TechnologyMumbaiIndia

Personalised recommendations