ElectroCardioGuard: Preventing Patient Misidentification in Electrocardiogram Databases through Neural Networks

• DOI: 10.48550/arxiv.2306.06196
• Publication Date: 2023-01-01
• Authors: Michal Seják; Jakub Sido; David Žahour
• Keywords: Identification; Clinical Practice

Electrocardiograms (ECGs) are commonly used by cardiologists to detect heart-related pathological conditions. Reliable collections of ECGs crucial for precise diagnosis. However, in clinical practice, the assignment captured ECG recordings incorrect patients can occur inadvertently. In collaboration with a and research facility which recognized this challenge reached out us, we present study that addresses issue. work, propose small efficient neural-network based model determining whether two originate from same patient. Our demonstrates great generalization capabilities achieves state-of-the-art performance gallery-probe patient identification on PTB-XL while utilizing 760x fewer parameters. Furthermore, technique leveraging our detection recording-assignment mistakes, showcasing its applicability realistic scenario. Finally, evaluate newly collected dataset specifically curated study, make it public community.