A hybrid CNN-SVM model for enhanced autism diagnosis.

Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE

Original Publication: San Francisco, CA : Public Library of Science

Support Vector Machine* ; Magnetic Resonance Imaging*/methods ; Neural Networks, Computer* ; Autistic Disorder*/diagnosis ; Autistic Disorder*/physiopathology; Humans ; Male ; Female ; Autism Spectrum Disorder/diagnosis ; Autism Spectrum Disorder/physiopathology ; Autism Spectrum Disorder/diagnostic imaging ; Brain/diagnostic imaging ; Brain/physiopathology ; Adolescent ; Child ; Adult ; Young Adult

Autism is a representative disorder of pervasive developmental disorder. It exerts influence upon an individual's behavior and performance, potentially co-occurring with other mental illnesses. Consequently, an effective diagnostic approach proves to be invaluable in both therapeutic interventions and the timely provision of medical support. Currently, most scholars' research primarily relies on neuroimaging techniques for auxiliary diagnosis and does not take into account the distinctive features of autism's social impediments. In order to address this deficiency, this paper introduces a novel convolutional neural network-support vector machine model that integrates resting state functional magnetic resonance imaging data with the social responsiveness scale metrics for the diagnostic assessment of autism. We selected 821 subjects containing the social responsiveness scale measure from the publicly available Autism Brain Imaging Data Exchange dataset, including 379 subjects with autism spectrum disorder and 442 typical controls. After preprocessing of fMRI data, we compute the static and dynamic functional connectivity for each subject. Subsequently, convolutional neural networks and attention mechanisms are utilized to extracts their respective features. The extracted features, combined with the social responsiveness scale features, are then employed as novel inputs for the support vector machine to categorize autistic patients and typical controls. The proposed model identifies salient features within the static and dynamic functional connectivity, offering a possible biological foundation for clinical diagnosis. By incorporating the behavioral assessments, the model achieves a remarkable classification accuracy of 94.30%, providing a more reliable support for auxiliary diagnosis.
Competing Interests: NO authors have competing interests.
(Copyright: © 2024 Qiu, Zhai. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Sci Rep. 2021 Jan 8;11(1):165. (PMID: 33420212)
IEEE Trans Med Imaging. 2022 Oct;41(10):2891-2902. (PMID: 35533175)
Front Neurosci. 2021 Jan 28;14:629630. (PMID: 33584183)
IEEE Trans Neural Netw Learn Syst. 2021 Jul;32(7):2847-2861. (PMID: 32692687)
Front Neuroinform. 2021 Jan 20;14:575999. (PMID: 33551784)
PLoS One. 2021 May 20;16(5):e0235946. (PMID: 34014933)
PLoS Biol. 2023 Aug 31;21(8):e3002239. (PMID: 37651504)
Magn Reson Med. 1995 Oct;34(4):537-41. (PMID: 8524021)
JCPP Adv. 2022 Oct 05;2(4):e12106. (PMID: 36741204)
J Psychiatr Brain Sci. 2022;7:. (PMID: 36425354)
Autism Res. 2013 Apr;6(2):78-90. (PMID: 23436773)
Sci Rep. 2023 Jan 20;13(1):1172. (PMID: 36670149)
IEEE J Sel Top Signal Process. 2016 Oct;10(7):1189-1203. (PMID: 28439325)
Front Neuroinform. 2022 Sep 28;16:949926. (PMID: 36246393)
Medicina (Kaunas). 2022 Aug 12;58(8):. (PMID: 36013557)
Neuroinformatics. 2016 Jul;14(3):339-51. (PMID: 27075850)
Neural Netw. 2023 Jan;158:99-110. (PMID: 36446159)
Autism Res. 2023 Feb;16(2):280-293. (PMID: 36495045)
Clin Biomech (Bristol, Avon). 2004 May;19(4):415-28. (PMID: 15109763)
Hum Brain Mapp. 2016 Nov;37(11):3957-3978. (PMID: 27329401)
PLoS One. 2013 Jul 04;8(7):e68910. (PMID: 23861951)
iScience. 2022 Dec 24;26(1):105872. (PMID: 36647383)
Front Hum Neurosci. 2015 May 19;9:249. (PMID: 26042013)
Sci Rep. 2019 Apr 5;9(1):5729. (PMID: 30952913)
Autism Res. 2022 May;15(5):778-790. (PMID: 35238171)
J Biomed Inform. 2023 Jan;137:104254. (PMID: 36509416)
Sci Rep. 2023 Feb 25;13(1):3291. (PMID: 36841898)
Sci Rep. 2019 Mar 11;9(1):4072. (PMID: 30858433)
Neuroimage. 2013 Oct 15;80:360-78. (PMID: 23707587)
Med Image Anal. 2023 Dec;90:102932. (PMID: 37657365)

Date Created: 20240514 Date Completed: 20240514 Latest Revision: 20240518

20240518

PMC11093301

10.1371/journal.pone.0302236

38743688