Probabilistic data fusion model for heart beat detection from multimodal physiological data

Abstract

Automatic detection of heart beats constitutes the basis for electrocardiogram (ECG) analysis and mainly relies on detecting QRS complexes. Detection is typically performed by analyzing the ECG signal. However, when signal quality is low, it often leads to the triggering of false alarms. A contemporary approach to reduce false alarm rate is to use multimodal data such as arterial blood pressure (ABP) or photoplethysmogram (PPG) signals. To leverage the correlated temporal nature of these signals, a probabilistic data fusion model for heart beat detection is proposed.A hidden Markov model is used to decode waveforms into segments. A Bayesian network is employed for capturing intersegmental coupling between waveforms and detecting heart beats. The performance of the proposed system was evaluated on a dataset provided by PhysioNet Challenge 2014: Robust Detection of Heart Beats in Multimodal Data. The proposed method is comparatively analyzed with a baseline hidden Markov model method for ECG and an improvement of 9% in sensitivity and 26% in positive predictivity is observed. The efficiency of the proposed model is also compared with related data fusion methods and a comparable performance is found. The robustness of the method is analyzed by inducting Gaussian noise into the dataset. A performance gain of 31% both in sensitivity and positive predictivity is obtained in the worst case where both ECG and ABP are noisy with -6 dB signal-to-noise ratio.

Multiple Physiological Signals Fusion Techniques for Improving Heartbeat Detection: A Review

“…Table 6 presents the signals that have been employed in the reviewed papers. Most of the proposals for heartbeat detection employ the ECG and ABP signals, since these are directly related with cardiac activity [42,43,44,45,46,47,48,49,50,51,52]. Other authors have added some other signals to that group: PPG signal [53,54]; SV and PPG signals [55]; and EEG, EOG, and EMG signals [56,57].…”

“…The Bayesian approaches from References [44,45,50,51] and the machine-learning method from Reference [52] merge the detection and fusion steps into a single one, and therefore, they will described in Section 3.6.4.…”

“…The algorithm from Reference [51] proposes fusing ECG and ABP signals using a more complex Bayesian approach, which is based on two layers. In the first layer, signals are decoded in terms of states related to well-known waveform segments: ISO (isoelectric), P , PQ , QRS , ST , and T for the ECG and SBP , DBP , Diastolic cusp , and Offset for the ABP.…”