Classification of Preschoolers with Low-Functioning Autism Spectrum Disorder Using Multimodal MRI Data.
Johanna-Inhyang KimSungkyu BangJin-Ju YangHeejin KwonSoomin JangSungwon RohSeok Hyeon KimMi Jung KimHyun Ju LeeJong-Min LeeBung-Nyun KimPublished in: Journal of autism and developmental disorders (2022)
Multimodal imaging studies targeting preschoolers and low-functioning autism spectrum disorder (ASD) patients are scarce. We applied machine learning classifiers to parameters from T1-weighted MRI and DTI data of 58 children with ASD (age 3-6 years) and 48 typically developing controls (TDC). Classification performance reached an accuracy, sensitivity, and specificity of 88.8%, 93.0%, and 83.8%, respectively. The most prominent features were the cortical thickness of the right inferior occipital gyrus, mean diffusivity of the middle cerebellar peduncle, and nodal efficiency of the left posterior cingulate gyrus. Machine learning-based analysis of MRI data was useful in distinguishing low-functioning ASD preschoolers from TDCs. Combination of T1 and DTI improved classification accuracy about 10%, and large-scale multi-modal MRI studies are warranted for external validation.
Keyphrases
- autism spectrum disorder
- machine learning
- contrast enhanced
- big data
- attention deficit hyperactivity disorder
- magnetic resonance imaging
- intellectual disability
- deep learning
- diffusion weighted imaging
- artificial intelligence
- electronic health record
- end stage renal disease
- magnetic resonance
- chronic kidney disease
- high resolution
- ejection fraction
- newly diagnosed
- computed tomography
- young adults
- lymph node
- squamous cell carcinoma
- multiple sclerosis
- data analysis
- functional connectivity
- white matter
- pain management
- chronic pain
- cancer therapy
- radiation therapy
- optical coherence tomography
- case control
- photodynamic therapy
- working memory
- drug delivery