From Dyadic to Higher-Order Interactions: Enhanced Representation of Homotopic Functional Connectivity Through Control of Intervening Variables

Background: The brain's complex functionality emerges from network interactions that go beyond dyadic connections, with higher-order interactions significantly contributing to this complexity. Homotopic functional connectivity (HoFC) is a key neurophysiological characteristic of the human brain, reflecting synchronized activity between corresponding regions in the brain's hemispheres.Materials and Methods: Using resting-state functional magnetic resonance imaging data from the Human Connectome Project, we evaluate dyadic and higher-order interactions of three functional connectivity (FC) parameterizations-bivariate correlation, partial correlation, and tangent space embedding-in their effectiveness at capturing HoFC through the inter-hemispheric analogy test.Results: Higher-order feature vectors are generated through node2vec, a random walk-based node embedding technique applied to FC networks. Our results show that higher-order feature vectors derived from partial correlation most effectively represent HoFC, while tangent space embedding performs best for dyadic interactions.Discussion: These findings validate HoFC and underscore the importance of the FC construction method in capturing intrinsic characteristics of the human brain. Impact Statement The impact of this article on the literature is multifaceted. It offers insights into which method of functional connectivity construction best captures homotopic functional connectivity (HoFC), a significant characteristic of the human brain. In addition, it addresses an important gap in the literature by demonstrating that partial correlation is the most suitable connectivity construction method for random walk node embedding techniques. Furthermore, this work marks the first validation of HoFC through machine learning feature vectors. Finally, our study provides insights to validate machine learning methods using inherent characteristics of the human brain, rather than relying solely on traditional machine learning evaluation metrics.