Why the study?
Existing works on ECG for user authentication do not evaluate population sizes close to real applications due to the challenge of finding datasets with large numbers of people.
Population
1500 subjects from the PhysioNet Computing in Cardiology 2018 database
Comparison
DETECT data improvement model vs baseline biometric identification
Design
Model development and validation study
Authors
Loading...
Wearable cardiac sensors risk data breaches; leaves open need for validated security standards before routine clinical or research deployment.
A proposed data improvement model for ECG-based biometric identification significantly increases precision and maintains low error rates in a large dataset of 1500 subjects.
Barros et al. (2020) studied this question.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: