Accuracy of machine learning algorithms for the diagnosis of autism spectrum disorder based on cerebral sMRI, rs-fMRI, and EEG: protocols for three systematic reviews and meta-analyses

BackgroundAutism 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. ObjectiveTo review the state of the art for the automated autism diagnosis. MethodsIn 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 I2 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. ResultsWe 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. ConclusionsThe 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.