Advertisement

Comparison of Machine Learning Methods for Effective Autism Diagnosis

  • D. Pavithra
  • A. N. Jayanthi
  • R. Nidhya
Conference paper
  • 17 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1118)

Abstract

Autism spectrum disorder is a neurological problem that will have challenges in social, emotional and behaviour skills. ASD can be diagnosed only by the age of three. The children with ASD will have developmental delay at every stage of their growth. The ASD is categorized as mild, moderate and severe. Proper diagnosis with treatment can cure ASD at the earliest. There are a number of tools for autism diagnosis such as the Autism Spectrum Quotient, Modified Checklist for Autism in Toddlers. Accuracy of the method mostly relies on the knowledge of the person who reviews the child. Accuracy can be improved by using AI technology like machine learning. Machine learning is a part of Artificial Intelligence where the system gets the ability to learn and improve itself. ML provides classifiers to diagnose autism at a high rate of accuracy. This paper focuses on comparing the existing machine learning classifiers (Naïve Bayes, SVM, k-NN and random forest) on ISAA data set for effective autism diagnosis.

Keywords

Autism spectrum disorder Machine learning Naïve Bayes SVM k-NN Random forest 

References

  1. 1.
    Thabtah, F.: Machine learning in autistic spectrum disorder behavioral research: a review and ways forward. Inf. Health Social Care 1–20 (2018)Google Scholar
  2. 2.
    Thabtah, F.: Autism Spectrum Disorder Screening: Machine Learning adaptation and DSM-5 fulfillment. Proceedings of the 1st International Conference on Medical and Health Info. (ICMHI’17), Taichung City, Taiwan, pp. 1–6 (2017)Google Scholar
  3. 3.
    Duda, M., Ma, R., Haber, N., Wall, D.P.: Use of Machine Learning for Behavioral Distinction of Autism and ADHD, Transl Psychiatry 6(2) (2016)Google Scholar
  4. 4.
    Mohammad, R., Thabtah, F., McCluskey, L.: Intelligent rule-based phishing websites classification. IET Inf. Secur. 8(3), 153–160 (2014)CrossRefGoogle Scholar
  5. 5.
    Thabtah, F.: Review on associative classification mining. Knowl. Eng. Rev. 22(1), 37–65 (2007)CrossRefGoogle Scholar
  6. 6.
    Wall, D.P., Dally. R., Luyster, R., et al.: Use of artificial intelligence to shorten the behavioral diagnosis of autism, PLoS ONE 7 (2012)Google Scholar
  7. 7.
    Pratap, A., Kanimozhiselvi, C.S., Vijayakumar, R., Pramod, K.V.: Predictive assessment of autism using unsupervised machine learning models. Int. J. Advanced Intelligence Paradigms, 6(2):113–21 (2014)Google Scholar
  8. 8.
    Kosmicki, J.A., Sochat, V., Duda, M., Wall, D.P.: Searching for a minimal set of behaviors for autism detection through feature selection-based machine learning. Transl. Psychiatry 5(2) (2015)Google Scholar
  9. 9.
    Duda, M., Ma, R., Haber, N., Wall, D.P.: Use of machine learning for behavioral distinction of autism and ADHD. Transl. Psychiatry 9(6) (2016)Google Scholar
  10. 10.
    Demirhan, A.: Performance of machine learning methods in determining the autism spectrum disorder cases. Mugla J. Scie. Technol. 4(1), 79–84 (2018)CrossRefGoogle Scholar
  11. 11.
    Deshpanden, S. N.: Indian scale for assessment of autism-test manual (2015)Google Scholar
  12. 12.
  13. 13.
    Pavithra, D., Jayanthi, A.N.: A study on machine learning algorithm in medical diagnosis 9(4), 42–46 (2018)Google Scholar
  14. 14.
  15. 15.
    Demirhan, A.: Neuroimage-based clinical prediction using machine learning tools. Int. J. Imaging Syst. Technol. 27(1), 89–97 (2017)CrossRefGoogle Scholar
  16. 16.
    https://medium.com/machine-learning-101/ chapter-5- random- forest-classifier
  17. 17.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar
  18. 18.
    Hall, M., Frank, E., Holmes, G., et al.: The WEKA data mining software: an update. SIGKDD Explo. 11(1), 10–18 (2009)CrossRefGoogle Scholar
  19. 19.
    Thabtah, F.: An accessible and efficient autism screening method for behavioural data and predictive analyses. Health Info. J. (2018)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • D. Pavithra
    • 1
  • A. N. Jayanthi
    • 1
  • R. Nidhya
    • 2
  1. 1.Department of Electronics and Communication EngineeringSri Ramakrishna Institute of TechnologyCoimbatoreIndia
  2. 2.Department of Computer Science and EngineeringMadanapalle Institute of Technology and ScienceMadanapalleIndia

Personalised recommendations