Abstract
Background: Autistic Spectrum Disorder (ASD) is a disorder associated with genetic and neurological components leading to difficulties in social interaction and communication. According to statistics of WHO, the number of patients diagnosed with ASD is gradually increasing. Most of the current studies focus on clinical diagnosis, data collection and brain images analysis, but do not focus on the diagnosis of ASD based on machine learning.
Objective: This study aims to classify ASD data to provide a quick, accessible and easy way to support early diagnosis of ASD. Methods: Three ASD datasets are used for children, adolescences and adults. To classify the ASD data, we used the k-Nearest Neighbours method (kNN), the Support Vector Machine method (SVM) and the Random Forests method (RF). In our experiments, the data was randomly split into training and test sets. The parts of the data were randomly selected 100 times to test the classification methods. Results: The final results were assessed by the average values. It is shown that SVM and RF are effective methods for ASD classification. In particular, the RF method classified the data with an accuracy of 100% for all above datasets. Conclusion: The early diagnosis of ASD is critical. If the number of data samples is large enough, we can achieve a high accuracy for machine learning-based ASD diagnosis. Among three classification methods, RF achieves the best performance for ASD data classification.Keywords: Autism spectrum disorder, machine learning, supervised learning, random forest, k-nearest neighbour, support vector machine.
Graphical Abstract
[1]
World Health Organization. Autism spectrum disorders [Internet]. 2017 [cited 2018 Dec 4]. Available from: . http://www.who.int/news-room/fact-sheets/detail/autism-spectrum-disorders
[2]
Hlavatá P, Kašpárek T, Linhartová P, et al. Autism, impulsivity and inhibition a review of the literature. Basal Ganglia 2018; 14: 44-53.
[http://dx.doi.org/10.1016/j.baga.2018.10.002]
[http://dx.doi.org/10.1016/j.baga.2018.10.002]
[3]
McDermott JH, Study DDD, Clayton-Smith J, Briggs TA. The TBR1-related autistic-spectrum-disorder phenotype and its clinical spectrum. Eur J Med Genet 2018; 61(5): 253-6.
[http://dx.doi.org/10.1016/j.ejmg.2017.12.009] [PMID: 29288087]
[http://dx.doi.org/10.1016/j.ejmg.2017.12.009] [PMID: 29288087]
[4]
Saresella M, Piancone F, Marventano I, et al. Multiple inflammasome complexes are activated in autistic spectrum disorders. Brain Behav Immun 2016; 57: 125-33.
[http://dx.doi.org/10.1016/j.bbi.2016.03.009] [PMID: 26979869]
[http://dx.doi.org/10.1016/j.bbi.2016.03.009] [PMID: 26979869]
[5]
Heinsfeld AS, Franco AR, Craddock RC, Buchweitz A, Meneguzzi F. Identification of autism spectrum disorder using deep learning and the ABIDE dataset. Neuroimage Clin 2017; 17: 16-23.
[http://dx.doi.org/10.1016/j.nicl.2017.08.017] [PMID: 29034163]
[http://dx.doi.org/10.1016/j.nicl.2017.08.017] [PMID: 29034163]
[6]
Thabtah F, Kamalov F, Rajab K. A new computational intelligence approach to detect autistic features for autism screening. Int J Med Inform 2018; 117: 112-24.
[http://dx.doi.org/10.1016/j.ijmedinf.2018.06.009] [PMID: 30032959]
[http://dx.doi.org/10.1016/j.ijmedinf.2018.06.009] [PMID: 30032959]
[7]
Azer SA, Bokhari RA, AlSaleh GS, et al. Experience of parents of children with autism on YouTube: are there educationally useful videos? Inform Health Soc Care 2018; 43(3): 219-33.
[8]
Franz L, Adewumi K, Chambers N, Viljoen M, Baumgartner JN, de Vries PJ. Providing early detection and early intervention for autism spectrum disorder in South Africa: stakeholder perspectives from the Western Cape province. J Child Adolesc Ment Health 2018; 30(3): 149-65.
[http://dx.doi.org/10.2989/17280583.2018.1525386] [PMID: 30403918]
[http://dx.doi.org/10.2989/17280583.2018.1525386] [PMID: 30403918]
[9]
Pagnozzi AM, Conti E, Calderoni S, Fripp J, Rose SE. A systematic review of structural MRI biomarkers in autism spectrum disorder: a machine learning perspective. Int J Dev Neurosci 2018; 71: 68-82.
[http://dx.doi.org/10.1016/j.ijdevneu.2018.08.010] [PMID: 30172895]
[http://dx.doi.org/10.1016/j.ijdevneu.2018.08.010] [PMID: 30172895]
[10]
Casanova R, Barnard RT, Gaussoin SA, et al. Using high-dimensional machine learning methods to estimate an anatomical risk factor for Alzheimer’s disease across imaging databases. Neuroimage 2018; 183: 401-11.
[http://dx.doi.org/10.1016/j.neuroimage.2018.08.040] [PMID: 30130645]
[http://dx.doi.org/10.1016/j.neuroimage.2018.08.040] [PMID: 30130645]
[11]
Parisi L. RaviChandran N, Manaog ML. Feature-driven machine learning to improve early diagnosis of Parkinson’s disease. Expert Syst Appl 2018; 110: 182-90.
[http://dx.doi.org/10.1016/j.eswa.2018.06.003]
[http://dx.doi.org/10.1016/j.eswa.2018.06.003]
[12]
Khamparia A, Saini G, Pandey B, et al. KDSAE: Chronic kidney disease classification with multimedia data learning using deep stacked autoencoder network. Multimed. Tools Appl 2019.
[13]
Priyadarshini R, Barik RK, Panigrahi C, et al. An Investigation Into the Efficacy of Deep Learning Tools for Big Data Analysis in Health Care. Int J Grid High Perform Comput 2018; 10(3): 1-13.
[http://dx.doi.org/10.4018/IJGHPC.2018070101]
[http://dx.doi.org/10.4018/IJGHPC.2018070101]
[15]
Escudero J, Ifeachor E, Zajicek JP, Green C, Shearer J, Pearson S. Machine learning-based method for personalized and cost-effective detection of Alzheimer’s disease. IEEE Trans Biomed Eng 2013; 60(1): 164-8.
[http://dx.doi.org/10.1109/TBME.2012.2212278] [PMID: 22893371]
[http://dx.doi.org/10.1109/TBME.2012.2212278] [PMID: 22893371]
[16]
Liu S, Liu S, Cai W, et al. Multimodal neuroimaging feature learning for multiclass diagnosis of Alzheimer’s disease. IEEE Trans Biomed Eng 2015; 62(4): 1132-40.
[http://dx.doi.org/10.1109/TBME.2014.2372011] [PMID: 25423647]
[http://dx.doi.org/10.1109/TBME.2014.2372011] [PMID: 25423647]
[17]
Abdar M, Zomorodi-Moghadam M, Zhou X, et al. A new nested ensemble technique for automated diagnosis of breast cancer Pattern Recognit Lett [Internet] 2018. Available from: . https://linkinghub.elsevier.com/retrieve/pii/S0167865518308766
[http://dx.doi.org/10.1016/j.patrec.2018.11.004]
[http://dx.doi.org/10.1016/j.patrec.2018.11.004]
[18]
Adem K, Kiliçarslan S, Cömert O. Classification and diagnosis of cervical cancer with softmax classification with stacked autoencoder. Expert Syst Appl 2019; 115: 557-64. [Internet
[http://dx.doi.org/10.1016/j.eswa.2018.08.050]
[http://dx.doi.org/10.1016/j.eswa.2018.08.050]
[19]
Altman NS. An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat 1992; 43(3): 175-85.
[20]
Dua D, Graff C. UCI Machine Learning Repository Available at: . http://archive.ics.uci.edu/mlIrvine
[21]
Thabtah F. Autism Spectrum Disorder screening: Machine learning
adaptation and DSM-5 fulfillment. ICMHI '17 Proceedings of the
1st International Conference on Medical and Health Informatics 2017; Taichung City, Taiwan May 20-22..
[22]
Thabtah F. ASDTests. A mobile app for ASD screening. [Internet]. 2017. [cited 2018 Dec 20]. Available from: . www.asdtests.com
[23]
Thabtah F. Machine learning in autistic spectrum disorder behavioral research: A review and ways forward. Inform Health Soc Care 2019; 44(3): 278-97.
[24]
Cortes C, Vapnik V. Support-Vector Networks. Mach Learn 1995; 20: 273-97.
[http://dx.doi.org/10.1007/BF00994018]
[http://dx.doi.org/10.1007/BF00994018]
[25]
Breiman L. Random forests. Mach Learn 2001; 45: 5-32.
[http://dx.doi.org/10.1023/A:1010933404324]
[http://dx.doi.org/10.1023/A:1010933404324]
Article Metrics
12
1