# ECG-Based Patient Identification: A Comprehensive Evaluation Across Health and Activity Conditions

arXiv: https://arxiv.org/abs/2302.06529 · HTML: https://mlsanity.com/paper/2302.06529/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 65 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 3 of 3)

- [Unsupervised Face Recognition using Unlabeled Synthetic Data](https://mlsanity.com/paper/2211.07371/) (2022)
- [Deep Learning for Iris Recognition: A Survey](https://mlsanity.com/paper/2210.05866/) (2022)
- [ECG Biometric Recognition: Review, System Proposal, and Benchmark Evaluation](https://mlsanity.com/paper/2204.03992/) (2022)

## Built on by (most cited first, 1 of 1)

- [CrossStateECG: Multi-Scale Deep Convolutional Network with Attention for Rest-Exercise ECG Biometrics](https://mlsanity.com/paper/2510.17467/) (2025)

## Abstract (arXiv)

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 proposed identification system is evaluated in multiple databases, achieving up to 99.84% accuracy on healthy subjects, 97.09% on patients with cardiovascular diseases, and 97.89% on mixed populations including both healthy and arrhythmic patients. The system also performs robustly under varying activity conditions, achieving 91.32% accuracy in scenarios involving different physical activities. These consistent and reliable results, with low error rates such as a FAR of 0.01% and FRR of 0.157% in the best cases, demonstrate the method's significant advancement in subject identification within healthcare systems. By considering patients' cardiovascular conditions and activity levels, the proposed approach addresses gaps in the existing literature, positioning it as a strong candidate for practical applications in real-world healthcare settings.