Early Autism Diagnosis: Machine Learning Models and Their Effectiveness

Abstract

Diagnosis is of utmost importance for timely intervention and support. However, traditional diagnosis methods, which are based on subjective assessment, are delayed. This project explores the role that machine learning techniques might play in enhancing the accuracy and effectiveness of autism spectrum disorder (ASD) detection. Several state-of-the-art classification algorithms were benchmarked using a dataset from Kaggle. Logistic regression, XG Boost, random forest, decision tree, and gradient boosting were taken into consideration. Other performance measures, in terms of accuracy, F1 score, and precision, were considered. The results showed that XG Boost was the best model, because this one had the most precision and reliability of ASD prediction. The research signifies the potential of artificial intelligence and machine learning technologies for the betterment of the diagnostic process and provides a robust and timely tool for early detection of ASD. Conclusions and recommendations of the study strongly emphasize the necessity of approaches that integrate multidisciplinary and ethical considerations for responsible translation into clinical practice.

Keywords: Autism spectrum disorder (ASD), machine learning, modalities, Autism Diagnostic Observation Schedule (ADOS), XG Boost, precision, accuracy, confusion matrix, F1 score.

Keyworde: Autism spectrum disorder (ASD), machine learning, modalities, Autism Diagnostic Observation Schedule (ADOS), XG Boost, precision, accuracy, confusion matrix, F1 score

Full Text PDF

Refrences:

1. Bone D, Bishop S, Black MP, Goodwin MS, Lord C. Use of machine learning to improve autism screening and diagnostic instruments: effectiveness, efficiency, and multi-instrument fusion. J Child Psychol Psychiatry. 2016; 57 (8): 927–937.
2. Heinsfeld AS, Franco AR, Craddock RC, Buchweitz A, Meneguzzi F. Identification of autism spectrum disorder using deep learning and the ABIDE NeuroImage: Clinical. 2018; 17: 16– 23.
3. Thabtah F, Peebles D, Seker H. A machine learning autism classification based on logistic regression analysis. Health Inform Sci Syst. 2020; 8 (1): 1–9.
4. Duda M, Ma R, Haber N, Wall DP. Use of machine learning for behavioral distinction of autism and ADHD. Transl Psychiatry. 2016; 6 (2): e732.
5. Li M, Dai Z, Wang M, He L, Huang H, Zheng H. Predicting autism spectrum disorder based on multi-site MRI, clinical, and demographic data: a multisite machine learning Mol Psychiatry. 2019; 24 (10): 1599–1605.
6. Chen CP, Keown CL, Jahedi A, Muller RA. Deep learning in autism diagnosis and biomarker discovery. J Autism Dev Disord. 2015; 45 (4): 1123–1136.
7. Yechiam E, Arshavsky O, Shamay-Tsoory SG, Yaniv S, Aharon J. Adapted to explore: reinforcement learning in autistic spectrum conditions. Brain Cognit. 2010; 72 (2): 317–324.
8. Chen Q, Chen X, Zhang Y, Ma Q. Deep learning for neuroimaging-based diagnosis and rehabilitation of autism spectrum disorder: a review. Front Neurosci. 2020; 14: 1007.
9. Guang S, Pang N, Deng X, Yang L, He F, Wu L, Chen C, Yin F, Peng Synaptopathology involved in autism spectrum disorder. Front Cell Neurosci. 2018; 12: 470.
10. Abraham A, Milham MP, Di Martino A, Craddock RC, Samaras D, Thirion B, Varoquaux G. Deriving reproducible biomarkers from multi-site resting-state data: an autism-based example. NeuroImage. 2017; 147: 736–745.
11. Lundberg SM, Erion GG, Lee SI. Consistent individualized feature attribution for tree ensembles. Nat Mach Intell. 2020; 2 (5): 252–260.
12. Chen X, Huang Q, Shi L, He Y, Li Associations between gut microbiota and autism spectrum disorder: a systematic review and meta-analysis. PLoS One. 2019; 14 (9): e0222907.
13. Hyman SL, Levy SE, Myers SM; Council on Children With Disabilities, Section on Developmental and Behavioral Pediatrics. Identification, evaluation, and management of children with autism spectrum disorder. Pediatrics. 2020; 145 (1): e20193447.
14. Lord C, Cook EH, Leventhal BL, Amaral DG. Autism spectrum disorders review. Neuron. 2000; 28 (2): 355–363.
15. Hazlett HC, Gu H, Munsell BC, Kim SH, Styner M, Wolff JJ, Piven Early brain development in infants at high risk for autism spectrum disorder. Nature. 2017; 542 (7641): 348–351.
16. Khosla M, Jamison K, Ngo GH, Kuceyeski A, Sabuncu Machine learning in resting-state fMRI analysis. Magn Reson Imaging. 2019; 64: 101–121.
17. Kuwabara H, Lu J, Lim L, Irie H, Lopez PT. Machine learning approaches for predicting autism spectrum disorder diagnosis using facial imaging J Child Psychol Psychiatry. 2016; 57(8): 927–937.
18. Vabalas A, Gowen E, Poliakoff E, Casson Machine learning algorithm validation with a limited sample size. PLoS One. 2019; 14 (11): e0224365.
19. Shaw KA, Maenner MJ, Bakian AV, et Early identification of autism spectrum disorder among children aged 4 years — Early Autism and Developmental Disabilities Monitoring Network, six sites, United States, 2016. MMWR Surveill Summ. 2021; 70 (10): 1–14.
20. van’t Hof M, Tisseur C, van Berckelear-Onnes I, van Nieuwenhuyzen A, Daniels AM, Deen M, Hoek HW, Ester WA. Age at autism spectrum disorder diagnosis: a systematic review and meta- analysis from 2012 to 2019. Autism. 2021; 25 (4): 862–973.
21. Bi X, Wang Z, Yang Y, Gao Y, Xu Y. A multi-feature learning model for early autism spectrum disorder diagnosis based on structural and functional MRI. Front Neurosci. 2018; 12: 707.
22. Hyman SL, Levy SE, Myers SM; Council on Children With Disabilities, Section on Developmental and Behavioral Pediatrics. Identification, evaluation, and management of children with autism spectrum disorder. Pediatrics. 2020; 145 (1): e20193447.
23. Thabtah F. Machine learning in autism spectrum disorder behavioral research: a review and ways forward. Inform Health Soc Care. 2019; 44 (3): 278–297.
24. Kelley JE, Barrio BL, Cardon TA, Brando-Subis C, Lee S, Smith K. DSM-5 autism spectrum disorder symptomology in award-winning narrative fiction. Educ Train Autism Dev Disabil. 2018;53:115-27.
25. Frye RE, Rossignol D, Casanova MF, Brown GL, Martin V, Edelson S, et A review of traditional and novel treatments for seizures in autism spectrum disorder: Findings from a systematic review and expert panel. Front Public Health. 2013;1:31. DOI: 10.3389/fpubh.2013.00031. PMID: 24350200.
26. Pensado-López A, Veiga-Rúa S, Carracedo Á, Allegue C, Sánchez Experimental models to study autism spectrum disorders: hiPSCs, rodents and zebrafish. Genes. 2020;11:1376. DOI: 10.3390/genes11111376. PMID: 33233737.
27. Hyman SL, Levy SE, Myers SM, Kuo DZ, Apkon S, Davidson LF, et Identification, evaluation, and management of children with autism spectrum disorder. Pediatrics. 2020;145. DOI: 10.1542/peds.2019-3447. PMID: 31843864.
28. Marbaniang P, Patil I, Lokanathan M, Parse H, Catherin Sesu D, Ingavale S, et al. Nanorice-like structure of carbon-doped hexagonal boron nitride as an efficient metal-free catalyst for oxygen electroreduction. ACS Sustain Chem Eng. 2018;6:11115-22. DOI: 1021/acssuschemeng.8b02609.
29. Guang S, Pang N, Deng X, Yang L, He F, Wu L, et al. Synaptopathology involved in autism spectrum disorder. Front Cell Neurosci. 2018;12:470. DOI: 10.3389/fncel.2018.00470. PMID:
30. Scott-Van Zeeland AA, McNealy K, Wang AT, Sigman M, Bookheimer SY, Dapretto No neural evidence of statistical learning during exposure to artificial languages in children with autism spectrum disorders. Biol Psychiatry. 2010;68:345-51. DOI: 10.1016/j.biopsych.2010.01.011. PMID: 20303070.
31. Prince M, Patel V, Saxena S, Maj M, Maselko J, Phillips MR, et No health without mental health. Lancet. 2007;370:859-77. DOI: 10.1016/S0140-6736(07)61238-0. PMID: 17804063.