Generalizable neuromarker for autism spectrum disorder across imaging sites and developmental stages: A multi-site study

Abstract

Autism spectrum disorder (ASD) is a lifelong condition, and its underlying biological mechanisms remain elusive. The complexity of various factors, including inter-site and development-related differences, makes it challenging to develop generalizable neuroimaging-based biomarkers for ASD. This study used a large-scale, multi-site dataset of 730 Japanese adults to develop a generalizable neuromarker for ASD across independent sites (U.S., Belgium, and Japan) and different developmental stages (children and adolescents). Our adult ASD neuromarker achieved successful generalization for the US and Belgium adults (area under the curve [AUC] = 0.70) and Japanese adults (AUC = 0.81). The neuromarker demonstrated significant generalization for children (AUC = 0.66) and adolescents (AUC = 0.71; all P<0.05, family-wise-error corrected). We identified 141 functional connections (FCs) important for discriminating individuals with ASD from TDCs. These FCs largely centered on social brain regions such as the amygdala, hippocampus, dorsomedial and ventromedial prefrontal cortices, and temporal cortices. Finally, we mapped schizophrenia (SCZ) and major depressive disorder (MDD) onto the biological axis defined by the neuromarker and explored the biological continuity of ASD with SCZ and MDD. We observed that SCZ, but not MDD, was located proximate to ASD on the biological dimension defined by the ASD neuromarker. The successful generalization in multifarious datasets and the observed relations of ASD with SCZ on the biological dimensions provide new insights for a deeper understanding of ASD.

Computational Mechanisms of Neuroimaging Biomarkers Uncovered by Multicenter Resting-State fMRI Connectivity Variation Profile

“…Extensive research has highlighted the relevance of functional connectivity (FC) in relation to individual characteristics [6][7][8][9] , task activities 10,11 , brain states 12 , anatomical structure 13 and neuronal signals [14][15][16] . Owing to its simplicity, versatility, interpretability, and sensitivity to individual variations, the FC biomarker shows great promise for objective diagnosis [17][18][19][20] , personalized treatment selection 21,22 , and neuromodulation target identification in psychiatry [23][24][25][26] .…”

“…Although altered functional connections between patient groups and healthy controls have been identified [30][31][32][33] , the individual-level classifications can be only achieved with the help of the machine-learning algortihms. In our multicenter study, we successfully developed major depressive disorder (MDD), schizophrenia (SCZ), and autism spectrum disorder (ASD) biomarkers using ensemble sparse classifiers, which generalized well across data from various centers [18][19][20] and maintained consistent performance on new data (anterograde generalization) 34 . However, its discrimination ability evaluated with completely independent datasets, with areas under the curve of 0.74, 0.82, and 0.66-0.81 for MDD, SCZ, and ASD, respectively, may not yet meet high standards.…”