Identifying Autism Spectrum Disorder Using Optimization-Based Clustering

Authors: Sharifah Mousli, Sona Taheri, Jiayuan He

Abstract:

Autism spectrum disorder (ASD) is a complex developmental condition involving persistent difficulties with social communication, restricted interests, and repetitive behavior. The challenges associated with ASD can interfere with an affected individual’s ability to function in social, academic, and employment settings. Although there is no effective medication known to treat ASD, to our best knowledge, early intervention can significantly improve an affected individual’s overall development. Hence, an accurate diagnosis of ASD at an early phase is essential. The use of machine learning approaches improves and speeds up the diagnosis of ASD. In this paper, we focus on the application of unsupervised clustering methods in ASD, as a large volume of ASD data generated through hospitals, therapy centers, and mobile applications has no pre-existing labels. We conduct a comparative analysis using seven clustering approaches, such as K-means, agglomerative hierarchical, model-based, fuzzy-C-means, affinity propagation, self organizing maps, linear vector quantisation – as well as the recently developed optimization-based clustering (COMSEP-Clust) approach. We evaluate the performances of the clustering methods extensively on real-world ASD datasets encompassing different age groups: toddlers, children, adolescents, and adults. Our experimental results suggest that the COMSEP-Clust approach outperforms the other seven methods in recognizing ASD with well-separated clusters.

Keywords: Autism spectrum disorder, clustering, optimization, unsupervised machine learning.

References:

[1] A. P. Association et al., “American psychiatric association: Diagnostic and statistical manual of mental disorders, arlington,” 2013. (Online). Available: https://doi.org/10.1176/appi.books.9780890425596
[2] H. S. Park, S. Y. Yi, S. A. Yoon, and S.-B. Hong, “Comparison of the autism diagnostic observation schedule and childhood autism rating scale in the diagnosis of autism spectrum disorder: a preliminary study,” Journal of the Korean Academy of Child and Adolescent Psychiatry, vol. 29, no. 4, p. 172, 2018. (Online). Available: https://doi.org/10.5765/jkacap.180015
[3] C. Lord, S. Risi, L. Lambrecht, E. H. Cook, B. L. Leventhal, P. C. DiLavore, A. Pickles, and M. Rutter, “The autism diagnostic observation schedule—generic: A standard measure of social and communication deficits associated with the spectrum of autism,” Journal of autism and developmental disorders, vol. 30, pp. 205–223, 2000. (Online). Available: https://doi.org/10.1023/A:1005592401947
[4] C. Lord and C. Corsello, “Diagnostic instruments in autistic spectrum disorders.” Handbook of Autism and Pervasive Developmental Disorders, Fourth Edition, 2005. (Online). Available: https://doi.org/10.1007/978-1-4419-1698-3 908
[5] F. R. Volkmar, C. Lord, A. Bailey, R. T. Schultz, and A. Klin, “Autism and pervasive developmental disorders,” Journal of child psychology and psychiatry, vol. 45, no. 1, pp. 135–170, 2004. (Online). Available: https://doi.org/10.1046/j.0021-9630.2003.00317.x
[6] K. K. Hyde, M. N. Novack, N. LaHaye, C. Parlett-Pelleriti, R. Anden, D. R. Dixon, and E. Linstead, “Applications of supervised machine learning in autism spectrum disorder research: a review,” Review Journal of Autism and Developmental Disorders, vol. 6, pp. 128–146, 2019.
[Online]. Available: https://doi.org/10.1007/s40489-019-00158-x
[7] M. M. Rahman, O. L. Usman, R. C. Muniyandi, S. Sahran, S. Mohamed, and R. A. Razak, “A review of machine learning methods of feature selection and classification for autism spectrum disorder,” Brain sciences, vol. 10, no. 12, p. 949, 2020. (Online). Available: https://doi.org/10.3390/brainsci10120949
[8] E. Stevens, A. Atchison, L. Stevens, E. Hong, D. Granpeesheh, D. Dixon, and E. Linstead, “A cluster analysis of challenging behaviors in autism spectrum disorder,” in 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE, 2017, pp. 661–666. (Online). Available: https://doi.org/10.1109/ICMLA.2017.00-85
[9] M. Elbattah, R. Carette, G. Dequen, J.-L. Gu´erin, and F. Cilia, “Learning clusters in autism spectrum disorder: image-based clustering of eye-tracking scanpaths with deep autoencoder,” in 2019 41st Annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE, 2019, pp. 1417–1420. (Online). Available: https://doi.org/10.1109/EMBC.2019.8856904
[10] S. Silleresi, P. Pr´evost, R. Zebib, F. Bonnet-Brilhault, D. Conte, and L. Tuller, “Identifying language and cognitive profiles in children with asd via a cluster analysis exploration: Implications for the new icd-11,” Autism Research, vol. 13, no. 7, pp. 1155–1167, 2020. (Online). Available: https://doi.org/10.1002/aur.2268
[11] A. A. Abdulrazzaq, S. S. Hamid, A. T. Al-Douri, A. Mohamad, and A. M. Ibrahim, “Early detection of autism spectrum disorders (asd) with the help of data mining tools,” BioMed Research International, vol. 2022, 2022.
[(Online). Available: https://doi.org/10.1155/2022/1201129
[12] A. Pratap and C. Kanimozhiselvi, “Predictive assessment of autism using unsupervised machine learning models,” International Journal of Advanced Intelligence Paradigms, vol. 6, no. 2, pp. 113–121, 2014.
[Online]. Available: https://doi.org/10.1504/IJAIP.2014.062174
[13] C. M. Parlett-Pelleriti, E. Stevens, D. Dixon, and E. J. Linstead, “Applications of unsupervised machine learning in autism spectrum disorder research: a review,” Review Journal of Autism and Developmental Disorders, pp. 1–16, 2022. (Online). Available: https://doi.org/10.1007/s40489-021-00299-y
[14] S. Zheng, K. A. Hume, H. Able, S. L. Bishop, and B. A. Boyd, “Exploring developmental and behavioral heterogeneity among preschoolers with asd: A cluster analysis on principal components,” Autism Research, vol. 13, no. 5, pp. 796–809, 2020. (Online). Available: https://doi.org/10.1002/aur.2263
[15] M. Uljarevi´c, A. Lane, A. Kelly, and S. Leekam, “Sensory subtypes and anxiety in older children and adolescents with autism spectrum disorder,” Autism Research, vol. 9, no. 10, pp. 1073–1078, 2016. (Online). Available: https://doi.org/10.1002/aur.1602
[16] E. Stevens, D. R. Dixon, M. N. Novack, D. Granpeesheh, T. Smith, and E. Linstead, “Identification and analysis of behavioral phenotypes in autism spectrum disorder via unsupervised machine learning,” International journal of medical informatics, vol. 129, pp. 29–36, 2019. (Online). Available: https://doi.org/10.1016/j.ijmedinf.2019.05.006
[17] T. Obara, M. Ishikuro, G. Tamiya, M. Ueki, C. Yamanaka, S. Mizuno, M. Kikuya, H. Metoki, H. Matsubara, M. Nagai et al., “Potential identification of vitamin b6 responsiveness in autism spectrum disorder utilizing phenotype variables and machine learning methods,” Scientific reports, vol. 8, no. 1, pp. 1–7, 2018. (Online). Available: https://doi.org/10.1038/s41598-018-33110-w
[18] F. Thabtah, R. Spencer, N. Abdelhamid, F. Kamalov, C. Wentzel, Y. Ye, and T. Dayara, “Autism screening: an unsupervised machine learning approach,” Health Information Science and Systems, vol. 10, no. 1, p. 26, 2022. (Online). Available: https://doi.org/10.1007/s13755-022-00191-x
[19] A´ . E. Tovar, A. Rodr´ıguez-Granados, and N. Arias-Trejo, “Atypical shape bias and categorization in autism: Evidence from children and computational simulations,” Developmental Science, vol. 23, no. 2, p. e12885, 2020. (Online). Available: https://doi.org/10.1111/desc.12885
[20] C. Kanimozhiselvi and A. Pratap, “Possibilistic lvq neural network-an application to childhood autism grading,” Neural Network World, vol. 26, no. 3, p. 253, 2016. (Online). Available: https://doi.org/10.14311/NNW.2016.26.014
[21] O. Veatch, J. Veenstra-VanderWeele, M. Potter, M. Pericak-Vance, and J. Haines, “Genetically meaningful phenotypic subgroups in autism spectrum disorders,” Genes, Brain and Behavior, vol. 13, no. 3, pp. 276–285, 2014. (Online). Available: https://doi.org/10.1111/gbb.12117
[22] T. Lingren, P. Chen, J. Bochenek, F. Doshi-Velez, P. Manning-Courtney, J. Bickel, L. Wildenger Welchons, J. Reinhold, N. Bing, Y. Ni et al., “Electronic health record based algorithm to identify patients with autism spectrum disorder,” PloS one, vol. 11, no. 7, p. e0159621, 2016. (Online). Available: https://doi.org/10.1371/journal.pone.0159621
[23] T. Vargason, R. E. Frye, D. L. McGuinness, and J. Hahn, “Clustering of co-occurring conditions in autism spectrum disorder during early childhood: A retrospective analysis of medical claims data,” Autism Research, vol. 12, no. 8, pp. 1272–1285, 2019. (Online). Available: https://doi.org/10.1002/aur.2128
[24] A. Verma, L. Bang, J. E. Miller, Y. Zhang, M. T. M. Lee, Y. Zhang, M. Byrska-Bishop, D. J. Carey, M. D. Ritchie, S. A. Pendergrass et al., “Human-disease phenotype map derived from phewas across 38,682 individuals,” The American Journal of Human Genetics, vol. 104, no. 1, pp. 55–64, 2019. (Online). Available: https://doi.org/10.1016/j.ajhg.2018.11.006
[25] T. Obafemi-Ajayi, D. Lam, T. N. Takahashi, S. Kanne, and D. Wunsch, “Sorting the phenotypic heterogeneity of autism spectrum disorders: A hierarchical clustering model,” in 2015 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). IEEE, 2015, pp. 1–7. (Online). Available: https://doi.org/10.1109/CIBCB.2015.7300337
[26] A. Kushki, E. Anagnostou, C. Hammill, P. Duez, J. Brian, A. Iaboni, R. Schachar, J. Crosbie, P. Arnold, and J. P. Lerch, “Examining overlap and homogeneity in asd, adhd, and ocd: a data-driven, diagnosis-agnostic approach,” Translational Psychiatry, vol. 9, no. 1, p. 318, 2019. (Online). Available: https://doi.org/10.1038/s41398-019-0631-2
[27] A. M. Bagirov, N. Hoseini-Monjezi, and S. Taheri, “A novel optimization approach towards improving separability of clusters,” Computers & Operations Research, vol. 152, pp. 106–135, 2023. (Online). Available: https://doi.org/10.1007/978-3-030-37826-4
[28] D. Dua and C. Graff, “UCI Machine Learning Repository,” 2019. (Online). Available: http://archive.ics.uci.edu/ml
[29] F. Thabtah, “Autism spectrum disorder screening: machine learning adaptation and dsm-5 fulfillment,” in Proceedings of the 1st International Conference on Medical and health Informatics 2017, 2017, pp. 1–6. (Online). Available: https://doi.org/10.1145/3107514.3107515
[30] J. Alwidian, A. Elhassan, and R. Ghnemat, “Predicting autism spectrum disorder using machine learning technique,” International Journal of Recent Technology and Engineering, vol. 8, no. 5, pp. 4139–4143, 2020. (Online). Available: https://doi.org/10.35940/ijrte.E6016.018520
[31] F. Thabtah, “An accessible and efficient autism screening method for behavioural data and predictive analyses,” Health informatics journal, vol. 25, no. 4, pp. 1739–1755, 2019. (Online). Available: https://doi.org/10.1177/1460458218796636
[32] S. Baron-Cohen, S. Wheelwright, R. Skinner, J. Martin, and E. Clubley, “The autism-spectrum quotient (aq): Evidence from asperger syndrome/high-functioning autism, malesand females, scientists and mathematicians,” Journal of autism and developmental disorders, vol. 31, pp. 5–17, 2001. (Online). Available: https://doi.org/10.1023/a:1005653411471
[33] C. Allison, S. Baron-Cohen, S. Wheelwright, T. Charman, J. Richler, G. Pasco, and C. Brayne, “The q-chat (quantitative checklist for autism in toddlers): a normally distributed quantitative measure of autistic traits at 18–24 months of age: preliminary report,” Journal of autism and developmental disorders, vol. 38, pp. 1414–1425, 2008.
[34] J. MacQuuen, “Some methods for classification and analysis of multivariate observation,” in Proceedings of the 5th Berkley Symposium on Mathematical Statistics and Probability, 1967, pp. 281–297.
[35] F. Murtagh and P. Legendre, “Ward’s hierarchical agglomerative clustering method: which algorithms implement ward’s criterion?” Journal of classification, vol. 31, pp. 274–295, 2014. (Online). Available: https://doi.org/10.1007/s00357-014-9161-z
[36] C. Fraley, A. Raftery, L. Scrucca, T. Murphy, and M. Fop, “mclust: Normal mixture modeling for model-based clustering, classification, and density estimation,” R package version, vol. 4, no. 7, 2014.
[37] J. C. Bezdek, “Cluster validity with fuzzy sets,” Journal of Cybernetics, 1973. (Online). Available: https://doi.org/10.1080/01969727308546047
[38] B. J. Frey and D. Dueck, “Clustering by passing messages between data points,” science, vol. 315, no. 5814, pp. 972–976, 2007. (Online). Available: https://doi.org/10.1126/science.1136800
[39] T. Kohonen and T. Kohonen, “Learning vector quantization,” Self-organizing maps, pp. 175–189, 1995.
[(Online). Available: https://doi.org/10.1007/978-3-642-97610-0 6
[40] M. Maechler, “cluster: ”finding groups in data”: Cluster analysis extended rousseeuw et al.” 2022, last accessed 21 April 2023. (Online). Available: https://cran.r-project.org/web/packages/cluster/index.html
[41] R Core Team, R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing, Vienna, Austria, 2023. (Online). Available: http://www.R-project.org/
[42] C. Fraley, “mclust: Gaussian mixture modelling for model-based clustering, classification, and density estimation,” 2022, last accessed 21 April 2023. (Online). Available: https://cran.r-project.org/web/packages/mclust/index.html
[43] Z. Cebeci, “Partitioning cluster analysis using fuzzy c-means,” 2017, last accessed 21 April 2023. (Online). Available: https://cran.r-project.org/web/packages/ppclust/vignettes/fcm.html
[44] U. Bodenhofer, “Package ‘apcluster’,” 2022, last accessed 20 April 2023. (Online). Available: https://cran.r-project.org/web/packages/ apcluster/apcluster.pdf
[45] R. Wehrens and J. Kruisselbrink, “Package ‘kohonen’,” 2022, last accessed 07 June 2023. (Online). Available: https://cran.r-project.org/web/packages/kohonen/kohonen.pdf
[46] V. Nikolaidis, “Package ‘nnlib2rcpp’,” 2023, last accessed 14 June 2023. (Online). Available: https://cran.r-project.org/web/packages/nnlib2Rcpp/index.html
[47] S. Taheri, “Comsep-clust,” 2021, last accessed 21 April 2023. (Online). Available: https://github.com/SnTa2019/Clustering-via-Nonsmooth -Optimization
[48] P. J. Rousseeuw, “Silhouettes: a graphical aid to the interpretation and validation of cluster analysis,” Journal of computational and applied mathematics, vol. 20, pp. 53–65, 1987. (Online). Available: https://doi.org/10.1016/0377-0427(87)90125-7