Biometric verification by cross-correlation analysis of 12-lead ECG patterns: Ranking of the most reliable peripheral and chest leads

• Published in: Journal of Electrocardiology Vol. 50; no. 6; pp. 847 - 854
• Main Authors: Krasteva, Vessela, Jekova, Irena, Abächerli, Roger
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.11.2017; Elsevier BV; Elsevier Science Ltd
• Subjects: Adolescent; Adult; Aged; Aged, 80 and over; Biometrics; Biometry; Biometry - methods; Correlation analysis; Cross-correlation analysis; Databases, Factual; Discriminant Analysis; ECG biometrics; Electrocardiography; Electrocardiography - methods; Female; Human identity recognition; Humans; Linear discriminant analysis; Male; Middle Aged; QRS, PQRST patterns; Retrospective Studies; Switzerland; Thorax; True verification rate; Linear discriminant analysis; ECG biometrics; QRS, PQRST patterns; True verification rate; Human identity recognition; Cross-correlation analysis
• ISSN: 0022-0736; 1532-8430; 1532-8430
• DOI: 10.1016/j.jelectrocard.2017.08.021

Electrocardiogram (ECG)-based biometrics relies on the most stable and unique beat patterns, i.e. those with maximal intra-subject and minimal inter-subject waveform differences seen from different leads. We investigated methodology to evaluate those differences, aiming to rank the most prominent single and multi-lead ECG sets for biometric verification across a large population. A clinical standard 12-lead resting ECG database, including 460 pairs of remote recordings (distanced 1year apart) was used. Inter-subject beat waveform differences were studied by cross-correlation and amplitude relations of average PQRST (500ms) and QRS (100ms) patterns, using 8 features/lead in 12-leads. Biometric verification models based on stepwise linear discriminant classifier were trained on the first half of records. True verification rate (TVR) on the remaining test data was further reported as a common mean of the correctly verified equal subjects (true acceptance rate) and correctly rejected different subjects (true rejection rate). In single-lead ECG human identity applications, we found maximal TVR (87–89%) for the frontal plane leads (I, −aVR, II) within (0–60°) sector. Other leads were ranked: inferior (85%), lateral to septal (82–81%), with intermittent V3 drop (77.6%), suggesting anatomical landmark displacements. ECG pattern view from multi-lead sets improved TVR: chest (91.3%), limb (94.6%), 12-leads (96.3%).