Autism Spectrum Disorder Diagnosis Assistance using Machine Learning

Authors

  • Arthur Alexandre Artoni Universidade Estadual de Londrina
  • Cinthyan Renata Sachs Camerlengo de Barbosa Universidade Estadual de Londrina
  • Marcelo Morandini Universidade de São Paulo

DOI:

https://doi.org/10.22456/2175-2745.126309

Keywords:

Austim, Machine Learning, Diagnosi

Abstract

Autism Spectrum Disorder (ASD) is a common but complex disorder to diagnose since there are no imaging or blood tests that can detect ASD. Several techniques can be used, such as diagnostic scales that contain specific questionnaires formulated by specialists that serve as a guide in the diagnostic process. In this paper, Machine Learning (ML) was applied on three public databases containing AQ-10 test results for adults, adolescents, and children; as well as other characteristics that could influence the diagnosis of ASD. Experiments were carried out on the databases to list which attributes would be truly relevant for the diagnosis of ASD using ML, which could be of great value for medical students or residents, and for physicians who are not specialists in ASD. The experiments have shown that it is possible to reduce the number of attributes to only 5 while maintaining an Accuracy above 0.9. In the other Database to maintain the same level of Accuracy, the fewer attribute numbers were 7. The Support Vector Machine stood out from the others algorithms used in this paper, obtaining superior results in all scenarios.

Downloads

Download data is not yet available.

References

GOMES, P. et al. Autism in Brazil: a systematic review of family challenges and coping strategies.Jornal de pediatria,SciELO Brasil, v. 91, n. 2, p. 111–121, 2015.

SILVA, A.; GAIATO, M. B.; REVELES, L. T.Mundo Singular: entenda o autismo. Rio de Janeiro: Fontana, 2012.

FERREIRA, R. S. Autism testing: Uma ferramenta móvel no auxílio ao pré-diagnóstico do autismo. In:Anais do XXIIConferência Internacional sobre Informática na Educação. Fortaleza, Ceará - Brasil: Nuevas Ideas en Informática Educativa,2010. v. 13, p. 178–187.

ZANON, R. B.; BACKES, B.; BOSA, C. A. Identificação dos primeiros sintomas do autismo pelos pais.Psicologia:Teoria e Pesquisa, SciELO Brasil, v. 30, n. 1, p. 25–33, 2014.

RELLINI, E. et al. Childhood Autism Rating Scale (CARS) and Autism Behavior Checklist (ABC) correspondence andconflicts with DSM-IV criteria in diagnosis of autism.Journal of autism and developmental disorders, Springer, v. 34, n. 6, p.703–708, 2004.

SCHOPLER, E. et al. Toward objective classification of childhood autism: Childhood Autism Rating Scale (CARS).Journal of autism and developmental disorders, Springer, v. 10, n. 1, p. 91–103, 1980.

KLEINMAN, J. M. et al. The modified checklist for autism in toddlers: a follow-up study investigating the early detectionof autism spectrum disorders.Journal of autism and developmental disorders, Springer, v. 38, n. 5, p. 827–839, 2008.

PENTEADO, F. A. O. et al. Software para auxílio ao diagnóstico de autismo. In:VIII Congresso de extensão universitáriada UNESP. São Paulo: Universidade Estadual Paulista Júlio de Mesquita Filho, 2015. p. 1–4.

BONE, D. et al. Applying machine learning to facilitate autism diagnostics: pitfalls and promises.Journal of autism anddevelopmental disorders, Springer, v. 45, n. 5, p. 1121–1136, 2015.

WALL, D. et al. Use of machine learning to shorten observation-based screening and diagnosis of autism.Translationalpsychiatry, Nature Publishing Group, v. 2, n. 4, p. 100, 2012.

XUE, M.; ZHU, C. A study and application on machine learning of artificial intellligence. In:International JointConference on Artificial Intelligence. Pasadena, California, USA: IEEE, 2009. p. 272–274.

THABTAH, F. Autism spectrum disorder screening: Machine learning adaptation and dsm-5 fulfillment. In:Proceedingsof the 1st International Conference on Medical and Health Informatics 2017. New York, NY, USA: ACM, 2017. p. 1–6.

ABDELJABER, F.Detecting Autistic Traits using Computational Intelligence & Machine Learning Techniques.Dissertação (Mestrado) — Department of Psychology, University of Huddersfield, January 2019.

GUEDES, N. P. S.; TADA, I. N. C. A produção científica brasileira sobre autismo na psicologia e na educação.Psicologia:teoria e pesquisa, v. 31, n. 3, p. 303–309, 2015.

LAMPREIA, A. R. S.Perceções parentais sobre a perturbação do espetro do autismo: processo de diagnóstico,interferência e recursos. Dissertação (Mestrado) — Faculdade de Psicologia, Universidade de Lisboa, 2015.

DIDEHBANI, N. et al. Virtual reality social cognition training for children with high functioning autism.Computers inHuman Behavior, Elsevier, v. 62, p. 703–711, 2016.

KANNER, L. et al. Autistic disturbances of affective contact.Nervous child, New York, v. 2, n. 3, p. 217–250, 1943.

KLIN, A. Autismo e síndrome de Asperger: uma visão geral Autism and Asperger syndrome: an overview.RevistaBrasileira de Psiquiatria, SciELO Brasil, v. 28, n. Supl I, p. S3–11, 2006.

BRITO, M. M. V. A.A contribuição do PECS no desenvolvimento da comunicação de uma aluna com perturbações doespectro do autismo. Dissertação (Mestrado) — Universidade de Trás-os-Montes e Alto Douro, Mestrado em Ciências daEducação, 2015.

SKAFIDAS, E. et al. Predicting the diagnosis of autism spectrum disorder using gene pathway analysis.Molecularpsychiatry, Nature Publishing Group, v. 19, n. 4, p. 504–510, 2014.

ASSOCIATION, A. P. et al.DSM-5: Manual diagnóstico e estatístico de transtornos mentais. Porto Alegre: Artmed,2014.

GROB, G. N. Origins of DSM: A study in appearance and reality.American Journal of Psychiatry, v. 148, n. 4, p.421–431, 1991.

PORCIUNCULA, R. Investigação precoce do transtorno do espectro autista: Sinais que alertam para a intervenção.ROTTA, NT; FILHO, CAB; BRIDI, FRS. Neurologia e aprendizagem: abordagem muldisciplinar., Porto Alegre: Artmed, p.29–54, 2016.

ROTTA, N. T.; OHLWEILER, L.; RIESGO, R. S.Transtornos da aprendizagem: abordagem neurobiológica emultidisciplinar. Porto Alegre: Artmed, 190f., 2016.

GUEDES, D. F.O uso das Tecnologias Digitais para a Alfabetização de Alunos com Transtorno do Espectro Autista:proposta de um Curso de Capacitação. Dissertação (Mestrado) — Programa de Pós-Graduação em Ensino, Cornélio Procópio,2019.

THABTAH, F.; KAMALOV, F.; RAJAB, K. A new computational intelligence approach to detect autistic features forautism screening.International Journal of Medical Informatics, Elsevier, v. 117, p. 112–124, 2018.

BARON-COHEN, S. et al. The Autism-spectrum Quotient (AQ): Evidence from Asperger Syndrome/High-FunctioningAutism, Males and Females, Scientists and Mathematicians.Journal of autism and developmental disorders, Springer, v. 31,n. 1, p. 5–17, 2001.

ALLISON, C.; AUYEUNG, B.; BARON-COHEN, S. Toward brief “red flags” for autism screening: the short autismspectrum quotient and the short quantitative checklist in 1,000 cases and 3,000 controls.Journal of the American Academy ofChild & Adolescent Psychiatry, Elsevier, v. 51, n. 2, p. 202–212, 2012.

BISHOP, C. M.Pattern recognition and machine learning. New York, NY: Springer, 2006. (Information science andstatistics).

MICHIE, D. et al. Machine Learning.Neural and Statistical Classification, Technometrics, v. 13, 1994.

ZHAO, Z. et al. Applying machine learning to identify autism with restricted kinematic features.IEEE Access, IEEE, v. 7,p. 157614–157622, 2019.

ALZUBI, R. et al. Hybrid feature selection method for autism spectrum disorder snps. In:Conference on ComputationalIntelligence in Bioinformatics and Computational Biology (CIBCB). Manchester, UK: IEEE, 2017. p. 1–7.

LIU, W. et al. Automatic diagnosis of autism based on functional magnetic resonance imaging and elastic net. In:5thInformation Technology and Mechatronics Engineering Conference (ITOEC). Chongqing, China: IEEE, 2020. p. 104–108.

ELNAKIEB, Y. A. et al. Computer aided autism diagnosis using diffusion tensor imaging.IEEE Access, IEEE, Tainan,Taiwan, v. 8, p. 191298–191308, 2020.

HUANG, F. et al. Sparse low-rank constrained adaptive structure learning using multi-template for autism spectrumdisorder diagnosis. In:16th International Symposium on Biomedical Imaging (ISBI 2019). Venice: IEEE, 2019. p. 1555–1558.

ELNAKIEB, Y. et al. Autism spectrum disorder diagnosis framework using diffusion tensor imaging. In:InternationalConference on Imaging Systems and Techniques (IST). Abu Dhabi, United Arab Emirates: IEEE, 2019. p. 1–5.

MOSTAFA, S.; TANG, L.; WU, F.-X. Diagnosis of autism spectrum disorder based on eigenvalues of brain networks.IEEE Access, IEEE, v. 7, p. 128474–128486, 2019.

HAPUTHANTHRI, D. et al. An EEG based Channel Optimized Classification Approach for Autism Spectrum Disorder.In:Moratuwa Engineering Research Conference (MERCon). Sri Lanka: IEEE, 2019. p. 123–128.

WU, C. et al. Machine Learning Based Autism Spectrum Disorder Detection from Videos. In:2020 IEEE InternationalConference on E-health Networking, Application Services (HEALTHCOM). Virtual Conference: IEEE, 2021. p. 1–6.

SIDHU, G. Locally linear embedding and fmri feature selection in psychiatric classification.IEEE Journal of TranslationalEngineering in Health and Medicine, IEEE, v. 7, p. 1–11, 2019.

HASAN, C. Z. C.; JAILANI, R.; TAHIR, N. M. ANN and SVM Classifiers in Identifying Autism Spectrum Disorder GaitBased on Three-Dimensional Ground Reaction Forces. In:TENCON 2018 - Region 10 Conference. Jeju Island, Korea: IEEE,2018. p. 2436–2440.

VIJAYALAKSHMI, K. et al. A hybrid recommender system using multiclassifier regression model for autism detection.In:2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE). VirtualConference: IEEE, 2020. p. 139–144.

AKTER, T. et al. Machine learning-based models for early stage detection of autism spectrum disorders.IEEE Access,IEEE, v. 7, p. 166509–166527, 2019.

ROOPA, B. S.; PRASAD, R. M. Concatenating framework in ASD analysis towards research progress. In:1stInternational Conference on Advanced Technologies in Intelligent Control, Environment, Computing CommunicationEngineering (ICATIECE). Bangalore, India: IEEE, 2019. p. 269–271.

HUANG, Z.-A.; LIU, R.; TAN, K. C. Multi-task learning for efficient diagnosis of asd and adhd using resting-state fmridata. In:2020 International Joint Conference on Neural Networks (IJCNN). Glasgow , United Kingdom: IEEE, 2020. p. 1–7.

ASLAM, A. R. et al. An 8.62μw Processor for Autism Spectrum Disorder Classification using Shallow Neural Network.In:3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS). Washington, DC, USA: IEEE, 2021.p. 1–4.

BEKEROM, B. Using machine learning for detection of autism spectrum disorder. In:26th Twente Student Conference onIT. Netherlands: University of Twente, 2017. p. 1–7.

OBAFEMI-AJAYI, T. et al. Facial structure analysis separates autism spectrum disorders into meaningful clinicalsubgroups.Journal of autism and developmental disorders, Springer, v. 45, n. 5, p. 1302–1317, 2015.

HAN, J.; PEI, J.; KAMBER, M.Data mining: concepts and techniques. Waltham, MA, USA: Elsevier, 2011.

GUYON, I.; ELISSEEFF, A. An introduction to variable and feature selection.Journal of machine learning research, v. 3,p. 1157–1182, 2003.

BREIMAN, L. Random Forests.Machine learning, Springer, v. 45, n. 1, p. 5–32, 2001.

ALPAYDIN, E.Introduction to machine learning. Cambridge, MA: MIT Press, 2009. 613 p.

RINGNÉR, M. What is principal component analysis?Nature biotechnology, Nature Publishing Group, v. 26, n. 3, p. 303,2008.

CUNNINGHAM, P.; DELANY, S. J. K-nearest neighbour classifiers.Multiple Classifier Systems, Springer-Verlag, v. 34,n. 8, p. 1–17, 2007.

SALZBERG, S. L. C4.5: Programs for machine learning.Machine Learning, Springer, v. 16, n. 3, p. 235–240, 1994.

CORTES, C.; VAPNIK, V. Support-vector networks.Machine Learning, [S. l.], v. 20, n. 3, p. 273–297, Sep 1995.

LORENA, A. C.; CARVALHO, A. C. de. Uma introdução às support vector machines.Revista de Informática Teórica eAplicada, v. 14, n. 2, p. 43–67, 2007.

KOHAVI, R. et al. A study of cross-validation and bootstrap for accuracy estimation and model selection. In:Proceedingsof 14th International Joint Conferences on Artificial Intelligence. Montreal, Canada: IJCAI, 1995. v. 14, n. 2, p. 1137–1145.

KIM, J.-H. Estimating classification error rate: Repeated cross-validation, repeated hold-out and bootstrap.Computationalstatistics & data analysis, Elsevier, v. 53, n. 11, p. 3735–3745, 2009.

Downloads

Published

2022-12-28

How to Cite

Artoni, A. A., Barbosa, C., & Morandini, . M. (2022). Autism Spectrum Disorder Diagnosis Assistance using Machine Learning. Revista De Informática Teórica E Aplicada, 29(3), 36–53. https://doi.org/10.22456/2175-2745.126309

Issue

Section

Regular Papers