Analysis of the relationship between mathematical learning stress and neuroendocrine response based on causal modeling

Introduction: This study develops a methodological framework to investigate the relationship between mathematical learning stress and neuroendocrine responses through causal modeling. Traditional approaches often fail to capture the complex interplay between psychological stressors and physiological responses, limiting their ability to provide actionable insights. To address these limitations, we propose the Representation-Factorized-Optimal (RFO) model, which is specifically designed to model the intricate dynamics between stress experienced during mathematical learning and the associated neuroendocrine responses. Methods: The model integrates three core components: the Representation Consistency Enforcer (RCE), which ensures the stability and reliability of variable representations; the Factorized Relation Projector (FRP), which disentangles and projects the relationships between stress and neuroendocrine variables; and the Optimal Transport Matcher (OTM), which aligns these variables for robust causal inference. To further enhance the model's performance, we incorporate advanced techniques such as representation alignment and sparse representation learning, enabling the extraction of meaningful patterns from high-dimensional data. Results and Discussion: Experimental results demonstrate that the proposed model achieves superior accuracy and interpretability compared to existing methods, providing a more nuanced understanding of the causal mechanisms underlying the interaction between mathematical learning stress and neuroendocrine responses. These findings hold significant implications for advancing research in the interdisciplinary fields of educational psychology and neurobiology, offering a robust tool for exploring the physiological impacts of cognitive stressors.