ECG signal analysis through hidden Markov models

Andreão, Rodrigo Varejão; Dorizzi, Bernadette; Boudy, Jérôme

doi:10.1109/tbme.2006.877103

Cited by 246 publications

(121 citation statements)

References 27 publications

Supporting

Mentioning

120

Contrasting

Order By: Relevance

“…It is often employed solving for sequential classification tasks. Its applicability has been long proven in areas such as speech recognition [15], natural language processing [16], biological sequence analysis [17] or electrocardiography [18], [19]. For sepsis modelling, we restrict the discussion to a particular type of HMM: the autoregressive HMM.…”

Section: Hidden State Modelsmentioning

confidence: 99%

Autoregressive Hidden Markov Models for the Early Detection of Neonatal Sepsis

Stanculescu

Williams

Freer

2014

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Abstract-Late onset neonatal sepsis is one of the major clinical concerns when premature babies receive intensive care. Current practice relies on slow laboratory testing of blood cultures for diagnosis. A valuable research question is whether sepsis can be reliably detected before the blood sample is taken. This paper investigates the extent to which physiological events observed in the patient's monitoring traces could be used for the early detection of neonatal sepsis. We model the distribution of these events with an autoregressive hidden Markov model (AR-HMM).Both learning and inference carefully use domain knowledge to extract the baby's true physiology from the monitoring data. Our model can produce real-time predictions about the onset of the infection and also handles missing data. We evaluate the effectiveness of the AR-HMM for sepsis detection on a dataset collected from the Neonatal Intensive Care Unit (NICU) at the Royal Infirmary of Edinburgh.Index Terms-neonatal sepsis, autoregressive hidden Markov model, real-time inference, intensive care.

show abstract

Section: Hidden State Modelsmentioning

confidence: 99%

Autoregressive Hidden Markov Models for the Early Detection of Neonatal Sepsis

Stanculescu

Williams

Freer

2014

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…These are then used to calculate various ECG parameters like the RR-interval, the QRS-length, the PR-interval and the elevation/depression of the ST-segment. A plethora of excellent algorithms have been developed for such purpose based on different signal processing approaches, like the time-domain morphology analysis augmented by different types of filtering [7]- [13], artificial neural networks [14], pattern matching [15], hidden Markov models [16], Independent Component Analysis (ICA) [17] and combinations of the above mentioned methods [18]- [23]. Another significant line of approach is based on the Wavelet Transform (WT) which represents a signal in time-scale domain.…”

Section: Background and Motivationmentioning

confidence: 99%

A Low-Complexity ECG Feature Extraction Algorithm for Mobile Healthcare Applications

Mazomenos

Biswas

Acharyya

et al. 2013

IEEE J. Biomed. Health Inform.

153

View full text Add to dashboard Cite

Abstract-This paper introduces a low-complexity algorithm for the extraction of the fiducial points from the Electrocardiogram (ECG). The application area we consider is that of remote cardiovascular monitoring, where continuous sensing and processing takes place in low-power, computationally constrained devices, thus the power consumption and complexity of the processing algorithms should remain at a minimum level. Under this context, we choose to employ the Discrete Wavelet Transform (DWT) with the Haar function being the mother wavelet, as our principal analysis method. From the modulus-maxima analysis on the DWT coefficients, an approximation of the ECG fiducial points is extracted. These initial findings are complimented with a refinement stage, based on the time-domain morphological properties of the ECG, which alleviates the decreased temporal resolution of the DWT. The resulting algorithm is a hybrid scheme of time and frequency domain signal processing. Feature extraction results from 27 ECG signals from QTDB, were tested against manual annotations and used to compare our approach against the state-of-the art ECG delineators. In addition, 450 signals from the 15-lead PTBDB are used to evaluate the obtained performance against the CSE tolerance limits. Our findings indicate that all but one CSE limits are satisfied. This level of performance combined with a complexity analysis, where the upper bound of the proposed algorithm, in terms of arithmetic operations, is calculated as 2.423N + 214 additions and 1.093N + 12 multiplications for N ≤ 861 or 2.553N + 102 additions and 1.093N + 10 multiplications for N > 861 (N being the number of input samples), reveals that the proposed method achieves an ideal trade-off between computational complexity and performance, a key requirement in remote CVD monitoring systems.

show abstract

“…ECG signal made of a P wave, a QRS complex and a T wave [5] During last few years, many systems have been designed for QRS detection. Numerous QRS detection algorithms based on the derivatives [6], filtering techniques [7][8][9][10], wavelet transform [11][12][13], mathematical morphology [14,15], empirical mode decomposition (EMD) [16], geometrical matching [17], artificial neural networks [18] and hybrid approach [19], genetic algorithms [20], syntactic methods [21], Hilbert transform [22], Markov models [23] etc. reported in literature have been developed for R-peaks detection.…”

Section: Introductionmentioning

confidence: 99%

A Robust Approach for R-Peak Detection

Yadav¹,

Grover²

2017

IJIEEB

View full text Add to dashboard Cite

Abstract-Electrocardiogram (ECG) is very crucial and important tool to detect the cardiac problems. For ECG analysis, it is essential to measure ECG parameter accurately. It is very critical in all types of ECG application. The accurate R Peaks detection is starting step in extracting ECG features which is necessary for the other ECG performance stages. It is very essential to detect these R-peaks accurately and efficiently to detect heart diseases or anomalies which create primary source of death in the universe. Hence automatic R-peaks detection in a lengthy duration ECG signal is very meaningful to diagnose the cardiac disorders. Here a latest R-peak exposure algorithm depended on Shannon energy envelope estimator and logic to find peaks has been proposed which uses the simple threshold of Shannon energy.

show abstract

ECG signal analysis through hidden Markov models

Cited by 246 publications

References 27 publications

Autoregressive Hidden Markov Models for the Early Detection of Neonatal Sepsis

Autoregressive Hidden Markov Models for the Early Detection of Neonatal Sepsis

A Low-Complexity ECG Feature Extraction Algorithm for Mobile Healthcare Applications

A Robust Approach for R-Peak Detection

Contact Info

Product

Resources

About