Does a weighted conditional random fields classifier improve automatic heartbeat classification in ECG signals compared to previous methods?
A weighted conditional random fields classifier improves the automatic classification of heartbeats, particularly pathological ones, in ECG signals.
This paper proposes a method for the automatic classification of heartbeats in an ECG signal. Since this task has specific characteristics such as time dependences between observations and a strong class unbalance, a specific classifier is proposed and evaluated on real ECG signals from the MIT arrhythmia database. This classifier is a weighted variant of the conditional random fields classifier. Experiments show that the proposed method outperforms previously reported heartbeat classification methods, especially for the pathological heartbeats.
Lannoy et al. (Wed,) studied this question.