Use of Artificial Intelligence in the Diagnostics of Autism Spectrum Disorder

Gabriele Mustika Kresnia, Arli Aditya Parikesit

Abstract

Autism Spectrum Disorder (ASD) is a neurologic development disorder; it is listed in the Diagnostic and Statistical Manual of Mental Disorders, 5th Edition (DSM-V). Early diagnosis is critical in improving the life quality of individuals affected by ASD. Several studies show that Artificial Intelligence can be used in the diagnosis of ASD through biological means such as observing patient EEG data and surveying their genome. Articles were searched in the PUBMED database, ScienceDirect and Springer Link between 2019 - 2020. Four papers were selected for review. The papers were able to devise models that can accurately predict ASD in affected individuals, though some are based on old data and/or require testing on larger datasets to determine accuracy. As ASD diagnosis usually cannot be achieved before the individual shows symptoms, AI has the potential to improve ASD diagnosis in affected individuals. Further study to confirm the models and test on larger, more recent datasets would be required to develop more accurate models and achieve even better results.

Autism Spectrum Disorder (ASD) merupakan salah satu gangguan perkembangan saraf yang tercantum pada Diagnostic and Statistical Manual of Mental Disorders, 5th Edition (DSM-V). Diagnosis dini sangat penting untuk meningkatkan kualitas hidup individu ASD. Beberapa penelitian menunjukkan bahwa Kecerdasan Buatan dapat digunakan untuk diagnosis ASD melalui metode berbasis biologis seperti mengamati data EEG pasien dan mensurvei genomnya. Review ini berbasis pencarian data antara 2019 – 2020 di database PUBMED, ScienceDirect dan Springer Link. Empat makalah kunci dipilih untuk ditinjau. Makalah-makalah tersebut mampu merancang model yang dapat memprediksi ASD secara akurat, meskipun beberapa aspek implementasinya didasarkan pada data usang dan/atau memerlukan pengujian pada kumpulan data yang lebih besar untuk menentukan akurasi. Mengingat diagnosis ASD biasanya tidak dapat dilakukan sebelum individu menunjukkan gejala sekunder, kecerdasan buatan berpotensi meningkatkan keandalan diagnosis ASD. Masih diperlukan studi lanjutan untuk mengkonfirmasi model dan pengujian pada kumpulan data yang lebih besar dan lebih baru untuk mengembangkan model yang memiliki presisi lebih baik dan hasil lebih akurat.

Full Text:

PDF

References

Murray AL, Allison C, Smith PL, Baron-Cohen S, Booth T, Auyeung B. Investigating diagnostic bias in autism spectrum conditions: An item response theory analysis of sex bias in the AQ-10. Autism Res [Internet]. 2017 May 1;10(5):790–800. Available from: https://pubmed.ncbi.nlm.nih.gov/27891820/[cited 2022 Jan 20]

Bagatell N. From Cure to Community: Transforming Notions of Autism. Ethos [Internet]. 2010 Mar 1;38(1):33–55. Available from: https://onlinelibrary.wiley.com/doi/full/10.1111/j.1548-1352.2009.01080.x[cited 2022 Jan 20]

Abdolzadegan D, Moattar MH, Ghoshuni M. A robust method for early diagnosis of autism spectrum disorder from EEG signals based on feature selection and DBSCAN method. Biocybern Biomed Eng. 2020;40(1):482–93.

Bahado-Singh RO, Vishweswaraiah S, Aydas B, Mishra NK, Yilmaz A, Guda C, et al. Artificial intelligence analysis of newborn leucocyte epigenomic markers for the prediction of autism. Brain Res. 2019;1724:146457.

Bajestani GS, Behrooz M, Khani AG, Nouri-Baygi M, Mollaei A. Diagnosis of autism spectrum disorder based on complex network features. Comput Methods Programs Biomed. 2019;177:277–83.

Gök M. A novel machine learning model to predict autism spectrum disorders risk gene. Neural Comput Appl 2018 3110 [Internet]. 2018;31(10):6711–7. Available from: https://link.springer.com/article/10.1007/s00521-018-3502-5 [cited 2022 Jan 20]

Alpaydin E. Introduction to machine learning.;682. Available from: https://mitpress.mit.edu/books/introduction-machine-learning-fourth-edition [cited 2022 Jan 20]

Kaderali L, Radde N. Inferring gene regulatory networks from expression data. Stud Comput Intell. 2008;94:33–74.

Noble WS. What is a support vector machine? Nat Biotechnol 2006 2412 [Internet]. 2006;24(12):1565–7. Available from: https://www.nature.com/articles/nbt1206-1565 [cited 2022 Jan 20]

Zhang Y. Support Vector Machine Classification Algorithm and Its Application. Commun Comput Inf Sci [Internet]. 2012;308 CCIS(PART 2):179–86. Available from: https://link.springer.com/chapter/10.1007/978-3-642-34041-3_27[cited 2022 Jan 20]

Wu Y, Ianakiev K, Govindaraju V. Improved k-nearest neighbor classification. Pattern Recognit. 2002 Oct 1;35(10):2311–8.

Bengio Y, Goodfellow I, Courville A. MIT press. Deep learning. 2017;1:1-7

Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS. Deep learning for visual understanding: A review. Neurocomputing. 2016;187:27–48.

Anurogo D, Parikesit AA. Troubled Helix – Tinjauan Multiperspektif Genetika dalam Bioetika. Cermin Dunia Kedokt [Internet]. 2021;48(3):147–53. Available from: http://103.13.36.125/index.php/CDK/article/view/1331[cited 2021 Mar 9]

Parikesit AA. Introductory Chapter: The Contribution of Bioinformatics as Blueprint Lead for Drug Design. In: Ivana Glavic, ed. Molecular Insight of Drug Design [Internet]. London: InTech; 2018. p. 7. Available from: http://www.intechopen.com/books/molecular-insight-of-drug-design/introductory-chapter-the-contribution-of-bioinformatics-as-blueprint-lead-for-drug-design[cited 2018 Aug 29]

Satya PGAN, Parikesit AA. Revolution in Detecting Tuberculosis using Radiology with Application of Deep Learning Algorithm. Cermin Dunia Kedokt [Internet]. 2021;48(4):261–3. Available from: http://www.cdkjournal.com/index.php/CDK/issue/view/98

Refbacks

  • There are currently no refbacks.