A personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework
Abstract Autism Spectrum Disorder (ASD) is characterized as a neurodevelopmental disorder with a heterogeneous nature, influenced by genetics and exhibiting diverse clinical presentations. In this study, we dissect Autism Spectrum Disorder (ASD) into its behavioral components, mirroring the diagnost...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-43478-z |
| _version_ | 1826970966755901440 |
|---|---|
| author | Mohamed T. Ali Ahmad Gebreil Yaser ElNakieb Ahmed Elnakib Ahmed Shalaby Ali Mahmoud Ahmed Sleman Guruprasad A. Giridharan Gregory Barnes Ayman S. Elbaz |
| author_facet | Mohamed T. Ali Ahmad Gebreil Yaser ElNakieb Ahmed Elnakib Ahmed Shalaby Ali Mahmoud Ahmed Sleman Guruprasad A. Giridharan Gregory Barnes Ayman S. Elbaz |
| author_sort | Mohamed T. Ali |
| collection | DOAJ |
| description | Abstract Autism Spectrum Disorder (ASD) is characterized as a neurodevelopmental disorder with a heterogeneous nature, influenced by genetics and exhibiting diverse clinical presentations. In this study, we dissect Autism Spectrum Disorder (ASD) into its behavioral components, mirroring the diagnostic process used in clinical settings. Morphological features are extracted from magnetic resonance imaging (MRI) scans, found in the publicly available dataset ABIDE II, identifying the most discriminative features that differentiate ASD within various behavioral domains. Then, each subject is categorized as having severe, moderate, or mild ASD, or typical neurodevelopment (TD), based on the behavioral domains of the Social Responsiveness Scale (SRS). Through this study, multiple artificial intelligence (AI) models are utilized for feature selection and classifying each ASD severity and behavioural group. A multivariate feature selection algorithm, investigating four different classifiers with linear and non-linear hypotheses, is applied iteratively while shuffling the training-validation subjects to find the set of cortical regions with statistically significant association with ASD. A set of six classifiers are optimized and trained on the selected set of features using 5-fold cross-validation for the purpose of severity classification for each behavioural group. Our AI-based model achieved an average accuracy of 96%, computed as the mean accuracy across the top-performing AI models for feature selection and severity classification across the different behavioral groups. The proposed AI model has the ability to accurately differentiate between the functionalities of specific brain regions, such as the left and right caudal middle frontal regions. We propose an AI-based model that dissects ASD into behavioral components. For each behavioral component, the AI-based model is capable of identifying the brain regions which are associated with ASD as well as utilizing those regions for diagnosis. The proposed system can increase the speed and accuracy of the diagnostic process and result in improved outcomes for individuals with ASD, highlighting the potential of AI in this area. |
| first_indexed | 2024-03-09T15:17:35Z |
| format | Article |
| id | doaj.art-6ec305bea1514f06800cd22cb5654eb1 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2025-02-18T04:57:47Z |
| publishDate | 2023-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-6ec305bea1514f06800cd22cb5654eb12024-11-17T12:30:23ZengNature PortfolioScientific Reports2045-23222023-10-0113112110.1038/s41598-023-43478-zA personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning frameworkMohamed T. Ali0Ahmad Gebreil1Yaser ElNakieb2Ahmed Elnakib3Ahmed Shalaby4Ali Mahmoud5Ahmed Sleman6Guruprasad A. Giridharan7Gregory Barnes8Ayman S. Elbaz9Bioengineering Department, University of LouisvilleBioengineering Department, University of LouisvilleBioengineering Department, University of LouisvilleElectrical and Computer Engineering, Penn State Erie-The Behrend CollegeLyda Hill Department of Bioinformatics, UT Southwestern Medical CenterBioengineering Department, University of LouisvilleBioengineering Department, University of LouisvilleBioengineering Department, University of LouisvilleDepartment of Neurology and Pediatric Research Institute, University of LouisvilleBioengineering Department, University of LouisvilleAbstract Autism Spectrum Disorder (ASD) is characterized as a neurodevelopmental disorder with a heterogeneous nature, influenced by genetics and exhibiting diverse clinical presentations. In this study, we dissect Autism Spectrum Disorder (ASD) into its behavioral components, mirroring the diagnostic process used in clinical settings. Morphological features are extracted from magnetic resonance imaging (MRI) scans, found in the publicly available dataset ABIDE II, identifying the most discriminative features that differentiate ASD within various behavioral domains. Then, each subject is categorized as having severe, moderate, or mild ASD, or typical neurodevelopment (TD), based on the behavioral domains of the Social Responsiveness Scale (SRS). Through this study, multiple artificial intelligence (AI) models are utilized for feature selection and classifying each ASD severity and behavioural group. A multivariate feature selection algorithm, investigating four different classifiers with linear and non-linear hypotheses, is applied iteratively while shuffling the training-validation subjects to find the set of cortical regions with statistically significant association with ASD. A set of six classifiers are optimized and trained on the selected set of features using 5-fold cross-validation for the purpose of severity classification for each behavioural group. Our AI-based model achieved an average accuracy of 96%, computed as the mean accuracy across the top-performing AI models for feature selection and severity classification across the different behavioral groups. The proposed AI model has the ability to accurately differentiate between the functionalities of specific brain regions, such as the left and right caudal middle frontal regions. We propose an AI-based model that dissects ASD into behavioral components. For each behavioral component, the AI-based model is capable of identifying the brain regions which are associated with ASD as well as utilizing those regions for diagnosis. The proposed system can increase the speed and accuracy of the diagnostic process and result in improved outcomes for individuals with ASD, highlighting the potential of AI in this area.https://doi.org/10.1038/s41598-023-43478-z |
| spellingShingle | Mohamed T. Ali Ahmad Gebreil Yaser ElNakieb Ahmed Elnakib Ahmed Shalaby Ali Mahmoud Ahmed Sleman Guruprasad A. Giridharan Gregory Barnes Ayman S. Elbaz A personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework Scientific Reports |
| title | A personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework |
| title_full | A personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework |
| title_fullStr | A personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework |
| title_full_unstemmed | A personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework |
| title_short | A personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework |
| title_sort | personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework |
| url | https://doi.org/10.1038/s41598-023-43478-z |
| work_keys_str_mv | AT mohamedtali apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT ahmadgebreil apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT yaserelnakieb apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT ahmedelnakib apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT ahmedshalaby apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT alimahmoud apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT ahmedsleman apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT guruprasadagiridharan apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT gregorybarnes apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT aymanselbaz apersonalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT mohamedtali personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT ahmadgebreil personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT yaserelnakieb personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT ahmedelnakib personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT ahmedshalaby personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT alimahmoud personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT ahmedsleman personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT guruprasadagiridharan personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT gregorybarnes personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework AT aymanselbaz personalizedclassificationofbehavioralseverityofautismspectrumdisorderusingacomprehensivemachinelearningframework |