Automated diagnosis of autism: State of the art
Authors:
- Amir ValizadehAVAmir Valizadeh
- Mana MoassefiMMMana Moassefi
- Amin Nakhostin-AnsariANAmin Nakhostin-Ansari
- Soheil Heidari Some’ehSSSoheil Heidari Some’eh
- Hossein Hosseini-AslHHHossein Hosseini-Asl
- Mehrnush Saghab TorbatiMTMehrnush Saghab Torbati
- Zahra Maleki GhorbaniZGZahra Maleki Ghorbani
- Iman Menbari-OskouieIMIman Menbari-Oskouie
- Faezeh AghajaniFAFaezeh Aghajani
- Alireza MirzamohammadiAMAlireza Mirzamohammadi
- Mohammad GhafouriMGMohammad Ghafouri
Preprint
Abstract
Background: Autism spectrum disorder (ASD) represents a panel of conditions that begin during the developmental period and result in impairments of personal, social, academic, or occupational functioning. Early diagnosis is directly related to a better prognosis. Unfortunately, the diagnosis of ASD requires a long and exhausting subjective process. Objective: To review the state of the art for the automated autism diagnosis. Methods: In February 2022, we searched multiple databases and several sources of grey literature for eligible studies. We used an adapted version of the QUADAS-2 tool to assess the risk of bias in the studies. A brief report of the methods and results of each study is presented. Data were synthesized for each modality separately using the Split Component Synthesis (SCS) method. We assessed heterogeneity using the I 2 statistics and evaluated publication bias using trim and fill tests combined with ln DOR. Confidence in cumulative evidence was evaluated using the GRADE approach for diagnostic studies. Results: We included 344 studies from 186020 participants (51129 are estimated to be unique) for nine different modalities in this review, from which 232 reported sufficient data for meta-analysis. The area under the curve was in the range of 0.71-0.90 for all the modalities. The studies on EEG data provided the best accuracy, with the area under the curve ranging between 0.85 to 0.93. Conclusions: The literature is rife with bias and methodological/reporting flaws. Recommendations are provided for future research to provide better studies and fill in the current knowledge gaps.Keywords
This publication has 399 references indexed in Scilit:
- Multisite functional connectivity MRI classification of autism: ABIDE resultsFrontiers in Human Neuroscience, 2013
- Differential Deactivation during Mentalizing and Classification of Autism Based on Default Mode Network ConnectivityPLOS ONE, 2012
- Extracting Multiscale Pattern Information of fMRI Based Functional Brain Connectivity with Application on Classification of Autism Spectrum DisordersPLOS ONE, 2012
- A stable pattern of EEG spectral coherence distinguishes children with autism from neuro-typical controls - a large case control studyBMC Medicine, 2012
- Multivariate Searchlight Classification of Structural Magnetic Resonance Imaging in Children and Adolescents with AutismBiological Psychiatry, 2011
- Functional connectivity magnetic resonance imaging classification of autismBrain, 2011
- Diffusion based abnormality markers of pathology: Toward learned diagnostic prediction of ASDNeuroImage, 2011
- Atypical diffusion tensor hemispheric asymmetry in autismAutism Research, 2010
- Predictive models of autism spectrum disorder based on brain regional cortical thicknessNeuroImage, 2010
- Quantifying heterogeneity in a meta‐analysisStatistics in Medicine, 2002