Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Unveiling the Heart-Brain Connection: An Analysis of ECG in Cognitive Performance

Akshay Sasi, Malavika Pradeep, Nusaibah Farrukh, Rahul Venugopal, Elizabeth Sherly

TL;DR

The study addresses the need for portable cognitive-load monitoring by leveraging ECG instead of EEG. It introduces Catch22-based ECG features and a cross-modal transfer-learning framework to map ECG representations to EEG-like cognitive spaces, enabling EEG-like workload inference from wearable sensors. The results show that ECG Catch22 with XGBoost achieves near-EEG performance in memory-load classification, and cross-modal transfers reveal strong heart–brain coupling, validating ECG as a practical surrogate for EEG in real-time cognitive monitoring. This work advances wearable neurophysiology by demonstrating robust, interpretable ECG-based workload decoding and a principled cross-modal framework for integrating peripheral and central signals. It holds significant potential for scalable cognitive monitoring in everyday settings and safety-critical domains.

Abstract

Understanding the interaction of neural and cardiac systems during cognitive activity is critical to advancing physiological computing. Although EEG has been the gold standard for assessing mental workload, its limited portability restricts its real-world use. Widely available ECG through wearable devices proposes a pragmatic alternative. This research investigates whether ECG signals can reliably reflect cognitive load and serve as proxies for EEG-based indicators. In this work, we present multimodal data acquired from two different paradigms involving working-memory and passive-listening tasks. For each modality, we extracted ECG time-domain HRV metrics and Catch22 descriptors against EEG spectral and Catch22 features, respectively. We propose a cross-modal XGBoost framework to project the ECG features onto EEG-representative cognitive spaces, thereby allowing workload inferences using only ECG. Our results show that ECG-derived projections expressively capture variation in cognitive states and provide good support for accurate classification. Our findings underpin ECG as an interpretable, real-time, wearable solution for everyday cognitive monitoring.

Unveiling the Heart-Brain Connection: An Analysis of ECG in Cognitive Performance

TL;DR

The study addresses the need for portable cognitive-load monitoring by leveraging ECG instead of EEG. It introduces Catch22-based ECG features and a cross-modal transfer-learning framework to map ECG representations to EEG-like cognitive spaces, enabling EEG-like workload inference from wearable sensors. The results show that ECG Catch22 with XGBoost achieves near-EEG performance in memory-load classification, and cross-modal transfers reveal strong heart–brain coupling, validating ECG as a practical surrogate for EEG in real-time cognitive monitoring. This work advances wearable neurophysiology by demonstrating robust, interpretable ECG-based workload decoding and a principled cross-modal framework for integrating peripheral and central signals. It holds significant potential for scalable cognitive monitoring in everyday settings and safety-critical domains.

Abstract

Understanding the interaction of neural and cardiac systems during cognitive activity is critical to advancing physiological computing. Although EEG has been the gold standard for assessing mental workload, its limited portability restricts its real-world use. Widely available ECG through wearable devices proposes a pragmatic alternative. This research investigates whether ECG signals can reliably reflect cognitive load and serve as proxies for EEG-based indicators. In this work, we present multimodal data acquired from two different paradigms involving working-memory and passive-listening tasks. For each modality, we extracted ECG time-domain HRV metrics and Catch22 descriptors against EEG spectral and Catch22 features, respectively. We propose a cross-modal XGBoost framework to project the ECG features onto EEG-representative cognitive spaces, thereby allowing workload inferences using only ECG. Our results show that ECG-derived projections expressively capture variation in cognitive states and provide good support for accurate classification. Our findings underpin ECG as an interpretable, real-time, wearable solution for everyday cognitive monitoring.
Paper Structure (22 sections, 7 equations, 6 figures, 5 tables)

This paper contains 22 sections, 7 equations, 6 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Dataset and Study Design
  3. Related Work
  4. Methodology
  5. Data Recording Protocol
  6. Working Model
  7. ECG Pre-processing
  8. EEG Pre-processing
  9. Feature Extraction
  10. HRV-Based Feature Extraction:
  11. Catch22 Feature Extraction:
  12. Classification Framework
  13. Model Evaluation Metrics
  14. Results
  15. ECG Classification with Classical ML
  16. ...and 7 more sections

Figures (6)

  • Figure 1: Heart-Brain Coupling
  • Figure 2: Digit span task experimental paradigm.
  • Figure 3: Architecture Diagram of the proposed framework.
  • Figure 4: Confusion Matrices for ECG Memory Classifier (MC).
  • Figure 5: Confusion Matrices for ECG Four-Class Classifier (FC).
  • ...and 1 more figures