Robust and Accurate Anomaly Detection in ECG Artifacts Using Time Series Motif Discovery

Abstract

Electrocardiogram (ECG) anomaly detection is an important technique for detecting dissimilar heartbeats which helps identify abnormal ECGs before the diagnosis process. Currently available ECG anomaly detection methods, ranging from academic research to commercial ECG machines, still suffer from a high false alarm rate because these methods are not able to differentiate ECG artifacts from real ECG signal, especially, in ECG artifacts that are similar to ECG signals in terms of shape and/or frequency. The problem leads to high vigilance for physicians and misinterpretation risk for nonspecialists. Therefore, this work proposes a novel anomaly detection technique that is highly robust and accurate in the presence of ECG artifacts which can effectively reduce the false alarm rate. Expert knowledge from cardiologists and motif discovery technique is utilized in our design. In addition, every step of the algorithm conforms to the interpretation of cardiologists. Our method can be utilized to both single-lead ECGs and multilead ECGs. Our experiment results on real ECG datasets are interpreted and evaluated by cardiologists. Our proposed algorithm can mostly achieve 100% of accuracy on detection (AoD), sensitivity, specificity, and positive predictive value with 0% false alarm rate. The results demonstrate that our proposed method is highly accurate and robust to artifacts, compared with competitive anomaly detection methods.

Survey on time series motif discovery

“…Motif discovery is applied to various applications and domains, e.g., in: astrophysics, sensors, medicine, motion capturing or trajectory mining, entomology, and music . A survey of these domains and methods is provided by Mueen …”

Subject identification via ECG fiducial-based systems: Influence of the type of QT interval correction

“…Specifically, since it is regarded as highly effective in ECG-related verification or identification tasks [16,17], we employed a 1 Nearest Neighbour (1-NN) classifier using the Dynamic Time Warping (DTW) as distance measure. The DTW public domain implementation provided by [39] was adopted here.…”

“…To further extend our analyses, we compared the results obtained with our fiducial-based approaches with respect to a non fiducialbased solution. Since some authors [16,17] proposed the use of Dynamic Time Warping (DTW) based approaches for ECG Identification, we compared our best finding with the performance of a Nearest Neighbour classifier using the DTW as distance measure.…”

Anomaly Subsequence Detection with Dynamic Local Density for Time Series

“…Anomaly detection for time series is an analysis of inconsistent data with normal data, which always represents an emergency or fault. Itc is applied in many application domains, ranging from financial data [15,19], Electrocardiogram (ECG) data [1,22] to sensor data [8]. For example, analysis of ECG data can timely monitor patients' heart health such as arrhythmia, ventricular atrial hypertrophy, myocardial infarction [13] before diagnosis process.…”