Electrocardiogram Signal Quality Analysis to Reduce False Alarms in Myocardial Ischemia Monitoring

The probability of myocardial ischemia is increased following a non-cardiac surgery, therefore, elevating the incidence of post-operative cardiac events. Myocardial ischemia causes a deviation of ST segment in the electrocardiogram (ECG), enabling targeted administration of β-Blockers; however, utilization of ECG was hindered by false alarms. The objective of this thesis is to develop a system to gate false alarms using the signal quality of the ECG and quality of the ST segment deviation estimate. The system was tested using ECG contaminated with motion artifact noise. The system gated 86% of all false alarms attaining a recall and precision of 0.72 and 0.73, respectively, marking an increase of 0.42 in precision and a decrease of 0.05 in recall from the bedside monitor performance (precision: 0.31, recall: 0.78). The signal quality analysis was extended to an ECG biometrics system, gating 57.8% of false identifications at the loss of 8.14% of true identifications.