ECG-Based Patient Identification: A Comprehensive Evaluation Across Health and Activity Conditions
Published in IEEE Access, 2024
Recommended citation: Fuster-Barceló, C., Cámara, C., & Peris-López, P. (2024). ECG-Based Patient Identification: A Comprehensive Evaluation Across Health and Activity Conditions. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3519462 https://ieeexplore.ieee.org/abstract/document/10804759
ECG-Based Patient Identification: A Comprehensive Evaluation Across Health and Activity Conditions
Authors: Caterina Fuster-Barceló, Carmen Cámara, and Pedro Peris-López
Published in: IEEE Access, December 2024
DOI: 10.1109/ACCESS.2024.3519462
🧠 Abstract
Over the course of the past two decades, a substantial body of research has substantiated the viability of utilising cardiac signals as a biometric modality. This paper presents a novel approach for patient identification in healthcare systems using electrocardiogram signals. A convolutional neural network (CNN) is employed to classify users based on electrocardiomatrices, a specific type of image derived from ECG signals.
The system is rigorously evaluated across multiple datasets and scenarios:
- Healthy subjects: 99.84% accuracy
- Patients with cardiovascular diseases: 97.09% accuracy
- Mixed populations (healthy + arrhythmic): 97.89%
- Physical activity variation: 91.32% accuracy
With an exceptionally low False Acceptance Rate (FAR) of 0.01% and False Rejection Rate (FRR) of 0.157%, this approach sets a new benchmark for robust and practical biometric identification systems in clinical contexts.
🔍 Keywords
Medical services, Biometrics, Electrocardiography, Databases, Accuracy, Object recognition, Artificial Intelligence, Health, Patient Identification