Unlocking the Potential of Autism Detection: Integrating Traditional Feature Selection and Machine Learning Techniques
Article Sidebar
Main Article Content
Abstract
The diagnostic process for Autism Spectrum Disorder (ASD) typically involves time-consuming assessments conducted by specialized physicians. To improve the efficiency of ASD screening, intelligent solutions based on machine learning have been proposed in the literature. However, many existing ML models lack the incorporation of medical tests and demographic features, which could potentially enhance their detection capabilities by considering affected features through traditional feature selection approaches. This study aims to address the aforementioned limitation by utilizing a real dataset containing 45 features and 983 patients. To achieve this goal, a two-phase methodology is employed. The first phase involves data preparation, including handling missing data through model-based imputation, normalizing the dataset using the Min-Max method, and selecting relevant features using traditional feature selection approaches based on affected features. In the second phase, seven ML classification techniques recommended by the literature, including Decision Trees (DT), Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), AdaBoost, Gradient Boosting (GB), and Neural Network (NN), are utilized to develop ML models. These models are then trained and tested on the prepared dataset to evaluate their performance in detecting ASD. The performance of the ML models is assessed using various metrics, such as Accuracy, Recall, Precision, F1-score, AUC, Train time, and Test time. These metrics provide insights into the models' overall accuracy, sensitivity, specificity, and the trade-off between true positive and false positive rates. The results of the study highlight the effectiveness of utilizing traditional feature selection approaches based on affected features. Specifically, the GB model outperforms the other models with an accuracy of 87%, Recall of 87%, Precision of 86%, F1-score of 86%, AUC of 95%, Train time of 21.890, and Test time of 0.173. Additionally, a benchmarking analysis against five other studies reveals that the proposed methodology achieves a perfect score across three key areas. By considering affected features through traditional feature selection approaches, the developed ML models demonstrate improved performance and have the potential to enhance ASD screening and diagnosis processes.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
Deprecated: json_decode(): Passing null to parameter #1 ($json) of type string is deprecated in /home/u273879158/domains/mesopotamian.press/public_html/journals/plugins/generic/citations/CitationsPlugin.php on line 68
How to Cite
References
[1] M. Elsabbagh et al., “Global Prevalence of Autism and Other Pervasive Developmental Disorders,” Autism Res., vol. 5, no. 3, pp. 160–179, 2012, doi: 10.1002/aur.239.
[2] A. Nazeer and J. L. Calles, “Autism spectrum disorders,” Clin. Asp. Psychopharmacol. Child. Adolesc. Second Ed., vol. 28, no. 2, pp. 173–190, 2016, doi: 10.4324/9781315692289-7.
[3] M. N. A. Tawhid, S. Siuly, H. Wang, F. Whittaker, K. Wang, and Y. Zhang, “A spectrogram image based intelligent technique for automatic detection of autism spectrum disorder from EEG,” PLoS One, vol. 16, no. 6 June, p. e0253094, 2021, doi: 10.1371/journal.pone.0253094.
[4] C. J. Jordan, “Evolution of autism support and understanding via the World Wide Web,” Intellect. Dev. Disabil., vol. 48, no. 3, pp. 220–227, 2010, doi: 10.1352/1934-9556-48.3.220.
[5] S. Siuly, O. F. Alcin, V. Bajaj, A. Sengur, and Y. Zhang, “Exploring Hermite transformation in brain signal analysis for the detection of epileptic seizure,” IET Sci. Meas. Technol., vol. 13, no. 1, pp. 35–41, 2019, doi: 10.1049/iet-smt.2018.5358.
[6] S. S. Joudar, A. S. Albahri, and R. A. Hamid, “Triage and priority-based healthcare diagnosis using artificial intelligence for autism spectrum disorder and gene contribution: A systematic review,” Comput. Biol. Med., vol. 146, p. 105553, Jul. 2022, doi: 10.1016/j.compbiomed.2022.105553.
[7] M. E. Alqaysi, A. S. Albahri, and R. A. Hamid, “Diagnosis-Based Hybridization of Multimedical Tests and Sociodemographic Characteristics of Autism Spectrum Disorder Using Artificial Intelligence and Machine Learning Techniques: A Systematic Review,” Int. J. Telemed. Appl., vol. 2022, 2022, doi: 10.1155/2022/3551528.
[8] J. Groopman, “What is autism?,” New York Rev. Books, vol. 60, no. 10, p. 2011, 2013, doi: 10.4324/9781315069609-7.
[9] K. E. Joung, S. L. Rifas-Shiman, E. Oken, and C. S. Mantzoros, “Maternal midpregnancy leptin and adiponectin levels as predictors of autism spectrum disorders: A prenatal cohort study,” J. Clin. Endocrinol. Metab., vol. 106, no. 10, pp. E4118–E4127, 2021, doi: 10.1210/clinem/dgab378.
[10] L. Mottron and D. Bzdok, “Autism spectrum heterogeneity: fact or artifact?,” Mol. Psychiatry, vol. 25, no. 12, pp. 3178–3185, 2020, doi: 10.1038/s41380-020-0748-y.
[11] Y. Hendel, G. Meiri, H. Flusser, A. Michaelovski, I. Dinstein, and I. Menashe, “Factors Affecting Family Compliance with Genetic Testing of Children Diagnosed with Autism Spectrum Disorder,” J. Autism Dev. Disord., vol. 51, no. 4, pp. 1201–1209, 2021, doi: 10.1007/s10803-020-04589-y.
[12] P. Morales Hidalgo, N. Voltas Moreso, and J. Canals Sans, “Autism spectrum disorder prevalence and associated sociodemographic factors in the school population: EPINED study,” Autism, vol. 25, no. 7, pp. 1999–2011, 2021, doi: 10.1177/13623613211007717.
[13] L. A. Bendik and F. Spicer-White, “The untold perspective: Parents’ experiences of the autism spectrum disorder assessment process when the child did not receive a diagnosis,” Autism, p. 13623613211003740, 2021, doi: 10.1177/13623613211003741.
[14] J. Veenstra-Vanderweele and R. D. Blakely, “Networking in autism: Leveraging genetic, biomarker and model system findings in the search for new treatments,” Neuropsychopharmacology, vol. 37, no. 1, pp. 196–212, 2012, doi: 10.1038/npp.2011.185.
[15] J. Hunter and D. Dale, “The Matplotlib User’s Guide,” Gentoo.Modulix.Net, 2005.
[16] N. A. Halsey and S. L. Hyman, “Measles-mumps-rubella vaccine and autistic spectrum disorder: report from the New Challenges in Childhood Immunizations Conference convened in Oak Brook, Illinois, June 12-13, 2000.,” Pediatrics, vol. 107, no. 5, pp. e84–e84, 2001, doi: 10.1542/peds.107.5.e84.
[17] A. Hviid, J. V. Hansen, M. Frisch, and M. Melbye, “Measles, mumps, rubella vaccination and autism a nationwide cohort study,” Ann. Intern. Med., vol. 170, no. 8, pp. 513–520, 2019, doi: 10.7326/M18-2101.
[18] A. H. Alamoodi and et al., “Review of Artificial Neural Networks-Contribution Methods Integrated with Structural Equation Modelling and Multi-Criteria Decision Analysis for Selection Customization,” Int. Sci. J. Eng. Appl. Artif. Intell. , vol. 124, p. 106643, 2023, doi: https://doi.org/10.1016/j.engappai.2023.106643.
[19] D. L. De Luise et al., “Asd: Ml perspective for individual performance evaluation,” in Advances in Intelligent Systems and Computing, 2016, vol. 356, pp. 379–400. doi: 10.1007/978-3-319-18296-4_32.
[20] L. Alzubaidi et al., “A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications,” J. Big Data, vol. 10, no. 1, p. 46, Apr. 2023, doi: 10.1186/s40537-023-00727-2.
[21] R. M. Dawes, D. Faust, and P. E. Meehl, “Clinical versus actuarial judgment,” Science (80-. )., vol. 243, no. 4899, pp. 1668–1674, 1989, doi: 10.1126/science.2648573.
[22] J. A. Colbert and D. A. Chokshi, “Technology in medical education—Osler meets Watson,” J. Gen. Intern. Med., vol. 29, no. 12, pp. 1584–1585, 2014.
[23] S. Yeasmin, “Benefits of Artificial Intelligence in Medicine,” in 2nd International Conference on Computer Applications and Information Security, ICCAIS 2019, 2019, pp. 1–6. doi: 10.1109/CAIS.2019.8769557.
[24] A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, 2017, doi: 10.1038/nature21056.
[25] A. S. Albahri, R. A. Hamid, A. A. Zaidan, and O. S. Albahri, “Early automated prediction model for the diagnosis and detection of children with autism spectrum disorders based on effective sociodemographic and family characteristic features,” Neural Comput. Appl., Sep. 2022, doi: 10.1007/s00521-022-07822-0.
[26] A. S. Albahri et al., “A Systematic Review of Trustworthy and Explainable Artificial Intelligence in Healthcare: Assessment of Quality, Bias Risk, and Data Fusion,” Inf. Fusion, Mar. 2023, doi: 10.1016/j.inffus.2023.03.008.
[27] A. S. Albahri et al., “A Systematic Review of Using Deep Learning Technology in the Steady-State Visually Evoked Potential-Based Brain-Computer Interface Applications: Current Trends and Future Trust Methodology,” Int. J. Telemed. Appl., vol. 2023, 2023.
[28] F. Marciano et al., “Artificial Intelligence: the ‘Trait D’Union’ in Different Analysis Approaches of Autism Spectrum Disorder Studies,” Curr. Med. Chem., vol. 28, no. 32, pp. 6591–6618, 2021, doi: 10.2174/0929867328666210203205221.
[29] W. Liu, M. Li, and L. Yi, “Identifying children with autism spectrum disorder based on their face processing abnormality: A machine learning framework,” Autism Res., vol. 9, no. 8, pp. 888–898, 2016, doi: 10.1002/aur.1615.
[30] M. E. Alqaysi, A. S. Albahri, and R. A. Hamid, “Hybrid Diagnosis Models for Autism Patients Based on Medical and Sociodemographic Features Using Machine Learning and Multicriteria Decision-Making (MCDM) Techniques: An Evaluation and Benchmarking Framework,” Comput. Math. Methods Med., vol. 2022, p. 9410222, 2022, doi: 10.1155/2022/9410222.
[31] A. S. Albahri et al., “Towards physician’s experience: Development of machine learning model for the diagnosis of autism spectrum disorders based on complex T ‐spherical fuzzy‐weighted zero‐inconsistency method,” Comput. Intell., vol. 39, no. 2, pp. 225–257, Apr. 2023, doi: 10.1111/coin.12562.
[32] S. S. Joudar et al., “Artificial intelligence-based approaches for improving the diagnosis, triage, and prioritization of autism spectrum disorder: a systematic review of current trends and open issues,” Artif. Intell. Rev., pp. 1–65, Jun. 2023, doi: 10.1007/s10462-023-10536-x.
[33] K. S. Oma, P. Mondal, N. S. Khan, M. R. K. Rizvi, and M. N. Islam, “A Machine Learning Approach to Predict Autism Spectrum Disorder,” in 2nd International Conference on Electrical, Computer and Communication Engineering, ECCE 2019, 2019, pp. 1–6. doi: 10.1109/ECACE.2019.8679454.
[34] F. Thabtah and D. Peebles, “A new machine learning model based on induction of rules for autism detection,” Health Informatics J., vol. 26, no. 1, pp. 264–286, 2020, doi: 10.1177/1460458218824711.
[35] S. Raj and S. Masood, “Analysis and Detection of Autism Spectrum Disorder Using Machine Learning Techniques,” Procedia Comput. Sci., vol. 167, pp. 994–1004, 2020, doi: 10.1016/j.procs.2020.03.399.
[36] K. Akyol, “Assessing the importance of autistic attributes for autism screening,” Expert Syst., vol. 37, no. 5, 2020, doi: 10.1111/exsy.12562.
[37] M. D. Hossain, M. A. Kabir, A. Anwar, and M. Z. Islam, “Detecting autism spectrum disorder using machine learning techniques,” Heal. Inf. Sci. Syst., vol. 9, no. 1, pp. 1–13, 2021, doi: 10.1007/s13755-021-00145-9.
[38] M. Garbulowski et al., “Interpretable Machine Learning Reveals Dissimilarities Between Subtypes of Autism Spectrum Disorder,” Front. Genet., vol. 12, p. 73, 2021, doi: 10.3389/fgene.2021.618277.
[39] M. Varma et al., “Outgroup machine learning approach identifies single nucleotide variants in noncoding DNA associated with autism spectrum disorder,” in Pacific Symposium on Biocomputing, 2019, vol. 24, no. 2019, pp. 260–271. doi: 10.1142/9789813279827_0024.
[40] B. Yamagata et al., “Machine learning approach to identify a resting-state functional connectivity pattern serving as an endophenotype of autism spectrum disorder,” Brain Imaging Behav., vol. 13, no. 6, pp. 1689–1698, 2019, doi: 10.1007/s11682-018-9973-2.
[41] S. S. Joudar, A. S. Albahri, and R. A. Hamid, “Intelligent triage method for early diagnosis autism spectrum disorder (ASD) based on integrated fuzzy multi-criteria decision-making methods,” Informatics Med. Unlocked, vol. 36, p. 101131, 2023, doi: 10.1016/j.imu.2022.101131.
Retinal Fundus Images, “https://www.kaggle.com/,” 2023.https://www.kaggle.com/datasets/kssanjaynithish03/retinal-fundus-images (accessed Feb. 01, 2023).