Towards Causality-Aware Modeling for Multimodal Brain-Muscle Interactions

TL;DR

Problem: Inferring causal interactions in nonlinear, multivariate biomedical signals with uncertainty and interventional requirements is difficult for traditional linear models and purely observational methods. Approach: The authors propose a DBN-Informed CCM framework that fuses Takens embedding-based attractor reconstruction with probabilistic temporal modeling, using a dual-weight scheme that combines geometric proximity and DBN-derived conditional probabilities to drive local predictions and quantify interventions. Contributions: A unified framework enabling uncertainty-aware causal inference with interventional analysis, a novel way to quantify causal effect magnitude via both geometric and probabilistic changes, and validation on EEG-EMG data from dystonic and healthy children showing frequency-specific motor-network reorganization. Findings: The approach yields higher predictive consistency and causal stability than baselines, with dystonia exhibiting increased delta-band and reduced beta-band connectivity and larger post-perturbation CCM shifts. Significance: The method provides a generalizable foundation for multimodal causal analysis in biomedical imaging with potential applications in real-time neural interfacing and adaptive neuromodulation.

Abstract

Robust characterization of dynamic causal interactions in multivariate biomedical signals is essential for advancing computational and algorithmic methods in biomedical imaging. Conventional approaches, such as Dynamic Bayesian Networks (DBNs), often assume linear or simple statistical dependencies, while manifold based techniques like Convergent Cross Mapping (CCM) capture nonlinear, lagged interactions but lack probabilistic quantification and interventional modeling. We introduce a DBN informed CCM framework that integrates geometric manifold reconstruction with probabilistic temporal modeling. Applied to multimodal EEG-EMG recordings from dystonic and neurotypical children, the method quantifies uncertainty, supports interventional simulation, and reveals distinct frequency specific reorganization of corticomuscular pathways in dystonia. Experimental results show marked improvements in predictive consistency and causal stability as compared to baseline approaches, demonstrating the potential of causality aware multimodal modeling for developing quantitative biomarkers and guiding targeted neuromodulatory interventions.

Figures (3)

• Figure 1: Schematic of proposed DBN-Informed CCM
• Figure 2: Number and strength of connections in healthy and dystonic subjects for different frequency bands.
• Figure 3: Pre and Post Intervention CCM values for all subjects