RS slope detection algorithm for extraction of heart rate from noisy, multimodal recordings

Abstract

Current gold-standard algorithms for heart beat detection do not work properly in the case of high noise levels and do not make use of multichannel data collected by modern patient monitors. The main idea behind the method presented in this paper is to detect the most prominent part of the QRS complex, i.e. the RS slope. We localize the RS slope based on the consistency of its characteristics, i.e. adequate, automatically determined amplitude and duration. It is a very simple and non-standard, yet very effective, solution. Minor data pre-processing and parameter adaptations make our algorithm fast and noise-resistant. As one of a few algorithms in the PhysioNet/Computing in Cardiology Challenge 2014, our algorithm uses more than two channels (i.e. ECG, BP, EEG, EOG and EMG). Simple fundamental working rules make the algorithm universal: it is able to work on all of these channels with no or only little changes. The final result of our algorithm in phase III of the Challenge was 86.38 (88.07 for a 200 record test set), which gave us fourth place. Our algorithm shows that current standards for heart beat detection could be improved significantly by taking a multichannel approach. This is an open-source algorithm available through the PhysioNet library.

PCG Classification Using a Neural Network Approach

“…We calculated the energy of the normalized signal (the normalization was performed separately in each of 25 windows of the signal) as described in [4]. Next we determined the peaks with Gierałtowski et al method [5] based on the slope detection in the signal. In the next part of the method, we calculate Wavelet coefficients of the whole signal by using Daubechies-2 wavelet at second decomposition level (according to [6]) and use these coefficients as an input signal to later evaluations.…”

Robust detection of heart beats in multimodal data

“…Amplitude thresholding is applied to the extracted source signal to determine the final peak locations. Gieraltowski et al (2014) used a slope detector and achieved good performance. For the ABP signal, and pulsatile waveforms in general, one of the more common approaches uses the slope sum function Zong, Heldt, Moody and Mark (2003); Li et al (2009).…”

Weighted Random Forests to Improve Arrhythmia Classification

“…Random Forest algorithm incorporates the bagging procedure to each decision tree (base learner) [33], generating Ntree ( j ∈ {1, . .…”