Key result
Bayesian high-order brain networks identify ASD with ~73% accuracy, outperforming traditional correlation methods.
Why the study?
Correlation's correlation lacks a solid theoretical foundation for constructing high-order brain functional networks, despite empirical effectiveness in identifying neurological disorders.
Absolute Event Rate: 72.83% vs 66.3%
A novel Bayesian high-order method for estimating brain functional networks improves the identification of autism spectrum disorder compared to conventional correlation methods.
May improve ASD detection in neuroimaging; extends correlation methods but leaves open clinical validation.
Brain functional network (BFN) has become an increasingly important tool to understand the inherent organization of the brain and explore informative biomarkers of neurological disorders. Pearson’s correlation (PC) is the most widely accepted method for constructing BFNs and provides a basis for designing new BFN estimation schemes. Particularly, a recent study proposes to use two sequential PC operations, namely, correlation’s correlation (CC), for constructing the high-order BFN. Despite its empirical effectiveness in identifying neurological disorders and detecting subtle changes of connections in different subject groups, CC is defined intuitively without a solid and sustainable theoretical foundation. For understanding CC more rigorously and providing a systematic BFN learning framework, in this paper, we reformulate it in the Bayesian view with a prior of matrix-variate normal distribution. As a result, we obtain a probabilistic explanation of CC. In addition, we develop a Bayesian high-order method (BHM) to automatically and simultaneously estimate the high- and low-order BFN based on the probabilistic framework. An efficient optimization algorithm is also proposed. Finally, we evaluate BHM in identifying subjects with autism spectrum disorder (ASD) from typical controls based on the estimated BFNs. Experimental results suggest that the automatically learned high- and low-order BFNs yield a superior performance over the artificially defined BFNs via conventional CC and PC.
No takes yet. Share an insight, caveat, or question.
Jiang et al. (2022) studied Autism Spectrum Disorder (n=184). Bayesian high-order method (BHM) for brain functional network estimation vs. Traditional Pearson's correlation (PC) and correlation's correlation (CC) was evaluated on Classification accuracy for ASD identification. The automatically learned Bayesian high-order brain functional network achieved a classification accuracy of 72.83% for identifying autism spectrum disorder, outperforming traditional correlation's correlation (66.30%) and Pearson's correlation (63.59%).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: