Cross-Modal Computational Model of Brain-Heart Interactions via HRV and EEG Feature

2026-01-11

arXiv.org

AI Summary

This study investigates whether electrocardiogram (ECG) signals can serve as a reliable surrogate for electroencephalogram (EEG) in monitoring cognitive load outside controlled laboratory settings. To this end, the authors propose a cross-modal regression framework that maps ECG-derived features—specifically heart rate variability (HRV) and Catch22 time-series descriptors—to EEG band power metrics using XGBoost. To address the scarcity of real-world HRV data, they introduce PSV-SDG, a novel method for generating synthetic HRV sequences, which is shown to significantly enhance model performance. The resulting approach enables lightweight, interpretable, and robust modeling of cognitive states using only wearable ECG devices. Experimental results demonstrate that ECG-based features effectively proxy EEG-derived cognitive indicators, thereby establishing a foundation for low-cost, real-time cognitive monitoring in elderly and clinical populations.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Brain-Sensing and Analysis
• Intelligent Robots: Cognitive Robotics

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Security and Privacy: Large-scale security measurements

Abstract

The electroencephalogram (EEG) has been the gold standard for quantifying mental workload; however, due to its complexity and non-portability, it can be constraining. ECG signals, which are feasible on wearable equipment pieces such as headbands, present a promising method for cognitive state monitoring. This research explores whether electrocardiogram (ECG) signals are able to indicate mental workload consistently and act as surrogates for EEG-based cognitive indicators. This study investigates whether ECG-derived features can serve as surrogate indicators of cognitive load, a concept traditionally quantified using EEG. Using a publicly available multimodal dataset (OpenNeuro) of EEG and ECG recorded during working-memory and listening tasks, features of HRV and Catch22 descriptors are extracted from ECG, and spectral band-power with Catch22 features from EEG. A cross-modal regression framework based on XGBoost was trained to map ECG-derived HRV representations to EEG-derived cognitive features. In order to address data sparsity and model brain-heart interactions, we integrated the PSV-SDG to produce EEG-conditioned synthetic HRV time series.This addresses the challenge of inferring cognitive load solely from ECG-derived features using a combination of multimodal learning, signal processing, and synthetic data generation. These outcomes form a basis for light, interpretable machine learning models that are implemented through wearable biosensors in non-lab environments. Synthetic HRV inclusion enhances robustness, particularly in sparse data situations. Overall, this work is an initiation for building low-cost, explainable, and real-time cognitive monitoring systems for mental health, education, and human-computer interaction, with a focus on ageing and clinical populations.

Problem

• cognitive load
• ECG
• EEG
• HRV
• cross-modal

Innovation

• cross-modal regression
• HRV-EEG mapping
• synthetic HRV generation
• cognitive load estimation
• wearable biosensors