Find in Library

Electrocardiogram (ECG) signals are widely used to examine heart rhythms and general health conditions. However, the majority of commercial ECG kits are generic and their normal ranges are set based on the averages obtained from a large population of people with normal heart conditions. This averaging ignores the extreme inherent variability of normal heart signals. As such, many false alarms are generated if the thresholds are selected too strict and true alarms are missed if the thresholds are set too loose. Furthermore, false alarms may arise due to the high physical activity of the test person. In this paper, we developed a prototype for patient-specific heart monitoring kit, which learns the properties of a patient's normal ECG signal over time and reports significant deviations from this normal behavior, in addition to presenting significant violations from the global norms. Further, false alarms due to high physical activity levels are eliminated through processing the utilized accelerometer signal. This personalized remote heart monitoring kit with the proposed signal processing and self-tuning capabilities and wireless connectivity provides more detailed information and insightful interpretations of ECG signals compared to generic devices, therefore can be used for remote heart monitoring of high-risk people.