Weighted conditional random fields for supervised interpatient heartbeat classification

de Lannoy, Gaël [UCL] François, Damien [UCL] Delbeke, Jean [UCL] Verleysen, Michel [UCL]

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.