What is the clinical evidence from this study?

Study design: Other. Population: Biometric identification (n=32). Intervention: Graph Convolutional Networks with Mutual Information (GCN-MI) vs. Conventional biometric methods. Primary outcome: Classification accuracy for user identification.

What does this research mean for the field?

A novel biometric authentication system integrating Graph Convolutional Networks with Mutual Information indices extracted from 12-lead ECG signals achieves 100% accuracy in user identification, outperforming conventional approaches. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

April 8, 2025Open Access

Enhancing biometric identification using 12-lead ECG signals and graph convolutional networks

Key Result

The GCN-MI model achieved 100% accuracy in biometric identification using 12-lead ECG signals, outperforming conventional approaches.

Structured PICO

Population

75 ECG recordings from 32 individuals, each lasting 10 s and sampled at 257 Hz, from the St. Petersburg Institute of Cardiological Techniques' 12-lead Arrhythmia database

Intervention

Graph Convolutional Networks (GCN) integrated with Mutual Information (MI) indices extracted from 12-lead ECG signals

Comparator

Conventional approaches using Pearson correlation, Euclidean distance, and cosine similarity

Outcome

Biometric identification accuracy

A novel GCN-MI model using 12-lead ECG signals achieves 100% accuracy for biometric authentication, offering a highly secure and scalable system.

Limitations

Limited data availability restricting model generalization
Data primarily gathered from the same participants

Abstract

Introduction: The electrocardiogram (ECG) is a highly secure biometric modality due to its intrinsic physiological characteristics, making it resilient to forgery and external attacks. This study presents a novel real-time biometric authentication system integrating Graph Convolutional Networks (GCN) with Mutual Information (MI) indices extracted from 12-lead ECG signals. Methods: The MI index quantifies the statistical dependencies among ECG leads and is computed using entropy-based estimations. This index is used to construct a graph representation, where nodes correspond to ECG features and edges reflect their relationships based on MI values. The GCN model is trained on this graph, enabling it to learn complex patterns for user identification efficiently. Results: Experimental results demonstrate that the proposed GCN-MI model achieves 100% accuracy with a 5-layer architecture at a k-fold of 75, outperforming conventional approaches that require less training data. Discussion: This work introduces several innovations: the integration of MI indices enhances feature selection, improving model robustness and efficiency; the graph-based learning framework effectively captures both spatial and statistical relationships within ECG data, leading to higher classification accuracy; the proposed approach offers a scalable and real-time biometric authentication system suitable for applications in finance, healthcare, and personal device access. These findings highlight the practical value of the GCN-MI approach, setting a new benchmark in ECG-based biometric identification.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper