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

TL;DR

This paper investigates whether ECG signals can reliably indicate mental workload, using a cross-modal regression framework to map ECG features to EEG-based cognitive indicators, aiming for portable, real-time cognitive monitoring.

Contribution

It introduces a novel cross-modal regression approach with synthetic HRV data to infer EEG-based cognitive load from ECG signals, enhancing robustness and interpretability.

Findings

ECG-derived HRV features can predict EEG-based cognitive load.

Synthetic HRV improves model robustness in sparse data scenarios.

The approach enables portable, real-time mental workload assessment.

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.