Table 5.
Top 10 citing articles on AI in ASD.
| Rank | Title of citing articles | Doi | Times cited | Interpretation of the findings |
|---|---|---|---|---|
| 1 | Early brain development in infants at high risk for autism spectrum disorder (Hazlett et al., 2017) | 10.1038/nature21369 | 580 | This study used a deep learning algorithm based on brain surface information obtained by MRI in individuals aged between 6 and 12 months to predict the diagnosis of autism in high-risk children at 24 months, which showed high accuracy. The study demonstrates that early brain changes occur during the period when autistic behaviors first appear. |
| 2 | Identification of autism spectrum disorder using deep learning and the ABIDE dataset (Heinsfeld et al., 2018) | 10.1016/j.nicl.2017.08.017 | 387 | This study extracted patterns of functional connectivity that objectively identify ASD from functional brain imaging data based on the ABIDE dataset by deep learning models. The authors also identified the areas of the brain that contributed most to differentiating ASD from the anticorrelation of brain function between anterior and posterior areas of the brain. |
| 3 | EEG complexity as a biomarker for autism spectrum disorder risk (Bosl et al., 2011) | 10.1186/1741-7015-9-18 | 292 | This study used several machine learning algorithms to analyze the modified multiscale entropy computed on the basis of resting state EEG data, which may be a useful biomarker for early detection of risk for ASD in infants. |
| 4 | Genome-wide prediction and functional characterization of the genetic basis of autism spectrum disorder (Krishnan et al., 2016) | 10.1038/nn.4353 | 222 | The authors developed a machine-learning approach based on a human brain-specific gene network to show a genome-wide prediction of ASD risk genes, and they demonstrated that a large number of ASD genes converge in a few key pathways and developmental stages of the brain, as well as identified possible causative genes. |
| 5 | Functional neuroimaging of high-risk 6-month-old infants predicts a diagnosis of autism at 24 months of age (Emerson et al., 2017) | 10.1126/scitranslmed.aag2882 | 195 | This study applied a fully cross-validated machine learning algorithm based on functional brain connections of high-risk 6-month-old infants and showed a high predictive value of infants who received a diagnosis of ASD at 24 months. |
| 6 | Functional connectivity classification of autism identifies highly predictive brain features but falls short of biomarker standards (Plitt et al., 2015) | 10.1016/j.nicl.2014.12.013 | 185 | This study compared the classification accuracy of a machine learning classifier based on rs-fMRI data to a classifier based on scores on behavioral metrics for ASD, and the results suggested that individuals can be classified as having ASD from rs-fMRI scans alone but that this approach does not meet biomarker standards. |
| 7 | A small number of abnormal brain connections predicts adult autism spectrum disorder (Yahata et al., 2016) | 10.1038/ncomms11254 | 167 | This study developed a novel machine-learning algorithm that can identify a small number of functional connections separating adult ASD and typically developed individuals, and the classifier achieved high accuracy. |
| 8 | Use of machine learning to shorten observation-based screening and diagnosis of autism (Wall et al., 2012) | 10.1038/tp.2012.10 | 151 | This study used a series of machine learning algorithms based on the Autism Diagnostic Observation Schedule, and the results showed this method can shorten observation-based screening and diagnosis of autism. |
| 9 | Whole-genome deep-learning analysis identifies contribution of noncoding mutations to autism risk (Zhou et al., 2019) | 10.1038/s41588-019-0420-0 | 128 | This study applied a deep-learning-based framework in 1,790 ASD simplex families and revealed a convergent genetic landscape of coding and noncoding mutations in ASD. |
| 10 | Fuzzy Synchronization Likelihood-wavelet methodology for diagnosis of autism spectrum disorder (Ahmadlou et al., 2012) | 10.1016/j.jneumeth.2012.08.020 | 125 | This study presented a methodology using Fuzzy Synchronization Likelihood based on EEG and Neural Network classifier to diagnose ASD, which showed high accuracy. |
ABIDE, autism brain imaging data exchange; AI, artificial intelligence; ASD, autism spectrum disorder; EEG, electroencephalography; MRI, magnetic resonance imaging; rs-fMRI, resting state functional magnetic resonance imaging.