Detection of Apnea Bradycardia from ECG Signals of Preterm Infants Using Layered Hidden Markov Model

Sadoughi, Azadeh; Shamsollahi, Mohammad Bagher; Fatemizadeh, Emad; Beuchée, Alain; Hernández, Alfredo; Ghahjaverestan, Nasim Montazeri

doi:10.1007/s10439-021-02732-z

Cited by 10 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, episodes of apnea-bradycardia have been observed in various studies [32], [33], including one using Coupled Hidden Semi-Markov Models (CHSMM) [34] and another employing layered HMMs, both based on electrocardiographic data. This detection contributes to the rapid diagnosis of this phenomenon in premature infants, a population where it occurs most frequently, thus avoiding neurological developmental issues and mortality [32], [33], [35].…”

Section: Research Backgroundmentioning

confidence: 99%

Hidden Markov Models for early detection of cardiovascular diseases

Núñez Mejía

2023

ing. Solidar

View full text Add to dashboard Cite

Introduction: This article, developed between 2022 and 2023 within the framework of Applied Stochastic Processes by the SciBas group at the Universidad Distrital Francisco José de Caldas, focuses on the role of Hidden Markov Models (HMM) in predicting cardiovascular diseases. Problem: The addressed issue is the need to enhance the early detection of heart diseases, emphasizing how HMM can address uncertainty in clinical data and detect complex patterns. Objective: To evaluate the use of Hidden Markov Models (HMM) in the analysis of electrocardiograms (ECG) for the early detection of cardiovascular diseases. Methodology: The methodology comprises a literature review concerning the relationship between HMM and cardiovascular diseases, followed by the application of HMM to prevent heart attacks and address uncertainty in clinical data. Results: The findings indicate that HMM is effective in preventing heart diseases, yet its effectiveness is contingent upon data quality. These results are promising but not universally applicable. Conclusions: In summary, this study underscores the utility of HMM in early infarction detection and its statistical approach in medicine. It is emphasized that HMM is not infallible and should be complemented with other clinical options and assessment methods in real-world situations. Originality: This work stands out for its statistical and probabilistic approach in the application of Hidden Markov Models (HMM) in medical analysis, offering an innovative perspective and enhancing the understanding of their utility in the field of medicine. Limitations: It is recognized that there are limitations, such as dependence on data quality and variable applicability in clinical cases. These limitations should be considered in the context of their implementation in medical practice.

show abstract

Section: Research Backgroundmentioning

confidence: 99%

Hidden Markov Models for early detection of cardiovascular diseases

Núñez Mejía

2023

ing. Solidar

View full text Add to dashboard Cite

show abstract

“…Most classical machine learning methods based on the extraction of features from single-channel ECG signal have been proposed, such as random forest [7,8] , support vector machines (SVMs) [9,10], artificial neural networks [11,12,13], KNN [14,15,16], and hidden Markov models [17,18]. All these studies have achieved much better performances.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method for Automatic Detection of Arrhythmias Using the Unsupervised Convolutional Neural Network

Zhang

Yao

Gao

et al. 2023

Journal of Artificial Intelligence and Soft Computing Research

View full text Add to dashboard Cite

In recent years, various models based on convolutional neural networks (CNN) have been proposed to solve the cardiac arrhythmia detection problem and achieved saturated accuracy. However, these models are often viewed as “blackbox” and lack of interpretability, which hinders the understanding of cardiologists, and ultimately hinders the clinical use of intelligent terminals. At the same time, most of these approaches are supervised learning and require label data. It is a time-consuming and expensive process to obtain label data. Furthermore, in human visual cortex, the importance of lateral connection is same as feed-forward connection. Until now, CNN based on lateral connection have not been studied thus far. Consequently, in this paper, we combines CNNs, lateral connection and autoencoder (AE) to propose the building blocks of lateral connection convolutional autoencoder neural networks (LCAN) for cardiac arrhythmia detection, which learn representations in an unsupervised manner. Concretely, the LCAN contains a convolution layer, a lateral connection layer, an AE layer, and a pooling layer. The LCAN detects salient wave features through the lateral connection layer. The AE layer and competitive learning is used to update the filters of the convolution network—an unsupervised process that ensures similar weight distribution for all adjacent filters in each convolution layer and realizes the neurons’ semantic arrangement in the LCAN. To evaluate the performances of the proposed model, we have implemented the experiments on the well-known MIT–BIH Arrhythmia Database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results show that the LCAN is not only effective, but also a useful tool for arrhythmia detection.

show abstract

“…Authors have associated these factors with delays in neurodevelopment and numerous other factors related to prematurity associated with longterm negative consequences [13]. The incidence of bradycardia in preterm infants differs based on their gestational age, birth weight, and other risk factors, including respiratory distress syndrome, sepsis, and anemia [14,15]. Furthermore, it has been reported that there is a correlation between bradycardia, low birth weight, and gestational age [16].…”

Section: Introductionmentioning

confidence: 99%

Bradycardia May Decrease Cardiorespiratory Coupling in Preterm Infants

Porta-García,

Quiroz-Salazar,

Abarca-Castro

et al. 2023

Entropy

View full text Add to dashboard Cite

Bradycardia, frequently observed in preterm infants, presents significant risks due to the immaturity of their autonomic nervous system (ANS) and respiratory systems. These infants may face cardiorespiratory events, leading to severe complications like hypoxemia and neurodevelopmental disorders. Although neonatal care has advanced, the influence of bradycardia on cardiorespiratory coupling (CRC) remains elusive. This exploratory study delves into CRC in preterm infants, emphasizing disparities between events with and without bradycardia. Using the Preterm Infant Cardio-Respiratory Signals (PICS) database, we analyzed interbeat (R-R) and inter-breath intervals (IBI) from 10 preterm infants. The time series were segmented into bradycardic (B) and non-bradycardic (NB) segments. Employing information theory measures, we quantified the irregularity of cardiac and respiratory time series. Notably, B segments had significantly lower entropy values for R-R and IBI than NB segments, while mutual information was higher in NB segments. This could imply a reduction in the complexity of respiratory and cardiac dynamics during bradycardic events, potentially indicating weaker CRC. Building on these insights, this research highlights the distinctive physiological characteristics of preterm infants and underscores the potential of emerging non-invasive diagnostic tools.

show abstract

Detection of Apnea Bradycardia from ECG Signals of Preterm Infants Using Layered Hidden Markov Model

Cited by 10 publications

References 23 publications

Hidden Markov Models for early detection of cardiovascular diseases

Hidden Markov Models for early detection of cardiovascular diseases

A Novel Method for Automatic Detection of Arrhythmias Using the Unsupervised Convolutional Neural Network

Bradycardia May Decrease Cardiorespiratory Coupling in Preterm Infants

Contact Info

Product

Resources

About