Real-time prediction of acute cardiovascular events using hardware-implemented Bayesian networks

Tylman, Wojciech; Waszyrowski, Tomasz; Napieralski, A.; Kamiński, Marek; Trafidło, Tamara; Kulesza, Zbigniew; Kotas, Rafał; Marciniak, Pawel; Tomala, Radosław; Wenerski, Maciej

doi:10.1016/j.compbiomed.2015.08.015

Cited by 25 publications

(27 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These data are generally used to develop a model to predict or classify future events, or to find which variables are most relevant to the outcome. Examples of supervised learning algorithms include ordinary least squares regression,18 logistic regression,19 least absolute shrinkage and selection operator (LASSO) regression,20 ridge regression,21 elastic net regression,21 linear discriminant analysis,22 Naïve Bayes classifiers,9 support vector machines,23 Bayesian networks,24 a variety of decision trees25 especially Random Forests26 and AdaBoost or gradient boosting classifiers,27 artificial neural networks and ensemble methods 7. Some of the examples of supervised machine learning tasks include regression, classification, predictive modelling and survival analysis.…”

Section: Introductionmentioning

confidence: 99%

Machine learning in cardiovascular medicine: are we there yet?

Shameer

Johnson

Glicksberg

et al. 2018

Heart

382

229

View full text Add to dashboard Cite

Artificial intelligence (AI) broadly refers to analytical algorithms that iteratively learn from data, allowing computers to find hidden insights without being explicitly programmed where to look. These include a family of operations encompassing several terms like machine learning, cognitive learning, deep learning and reinforcement learning-based methods that can be used to integrate and interpret complex biomedical and healthcare data in scenarios where traditional statistical methods may not be able to perform. In this review article, we discuss the basics of machine learning algorithms and what potential data sources exist; evaluate the need for machine learning; and examine the potential limitations and challenges of implementing machine in the context of cardiovascular medicine. The most promising avenues for AI in medicine are the development of automated risk prediction algorithms which can be used to guide clinical care; use of unsupervised learning techniques to more precisely phenotype complex disease; and the implementation of reinforcement learning algorithms to intelligently augment healthcare providers. The utility of a machine learning-based predictive model will depend on factors including data heterogeneity, data depth, data breadth, nature of modelling task, choice of machine learning and feature selection algorithms, and orthogonal evidence. A critical understanding of the strength and limitations of various methods and tasks amenable to machine learning is vital. By leveraging the growing corpus of big data in medicine, we detail pathways by which machine learning may facilitate optimal development of patient-specific models for improving diagnoses, intervention and outcome in cardiovascular medicine.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine learning in cardiovascular medicine: are we there yet?

Shameer

Johnson

Glicksberg

et al. 2018

Heart

382

229

View full text Add to dashboard Cite

show abstract

“…28 Over the past few years, BNs have been extensively used to model clinical problems in CVD for the purposes of diagnosis, risk assessment and disease prediction. [29][30][31][32][33] In the present study, we introduced a BN analysis to evaulate the aetiological role of HCV infection in CVD risk. Our objective is to characterise the multivariable probabilistic connection between the two diseases and identify factors that mediate and influence this relationship in a population of Canadian adults.…”

Section: Open Accessmentioning

confidence: 99%

Bayesian network modelling study to identify factors influencing the risk of cardiovascular disease in Canadian adults with hepatitis C virus infection

Badawi

Giuseppe

Gupta³

et al. 2020

BMJ Open

View full text Add to dashboard Cite

ObjectivesThe present study evaluates the extent of association between hepatitis C virus (HCV) infection and cardiovascular disease (CVD) risk and identifies factors mediating this relationship using Bayesian network (BN) analysis.Design and settingA population-based cross-sectional survey in Canada.ParticipantsAdults from the Canadian Health Measures Survey (n=10 115) aged 30 to 74 years.Primary and secondary outcome measuresThe 10-year risk of CVD was determined using the Framingham Risk Score in HCV-positive and HCV-negative subjects. Using BN analysis, variables were modelled to calculate the probability of CVD risk in HCV infection.ResultsWhen the BN is compiled, and no variable has been instantiated, 73%, 17% and 11% of the subjects had low, moderate and high 10-year CVD risk, respectively. The conditional probability of high CVD risk increased to 13.9%±1.6% (p<2.2×10-16) when the HCV variable is instantiated to ‘Present’ state and decreased to 8.6%±0.2% when HCV was instantiated to ‘Absent’ (p<2.2×10-16). HCV cases had 1.6-fold higher prevalence of high-CVD risk compared with non-infected individuals (p=0.038). Analysis of the effect modification of the HCV-CVD relationship (using median Kullback-Leibler divergence; DKL) showed diabetes as a major effect modifier on the joint probability distribution of HCV infection and CVD risk (DKL=0.27, IQR: 0.26 to 0.27), followed by hypertension (0.24, IQR: 0.23 to 0.25), age (0.21, IQR: 0.10 to 0.38) and injection drug use (0.19, IQR: 0.06 to 0.59).ConclusionsExploring the relationship between HCV infection and CVD risk using BN modelling analysis revealed that the infection is associated with elevated CVD risk. A number of risk modifiers were identified to play a role in this relationship. Targeting these factors during the course of infection to reduce CVD risk should be studied further.

show abstract

“…Electrode movement alters the signal baseline and brings the signal fluctuate perpendicularly to the baseline. If the electrode moves drastically enough to drop from the skin, baseline drift will overwhelm the signal and waveform distortion occurs [ 9 ]. Motion artifact is generally attributed to the variation of electrode-skin impedance during a subject's motion.…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, efficient R-peak extraction is still difficult in the dynamic and noisy environment due to the time-varying waveform morphology. This would be more difficult when ECG signal is overwhelmed by noises with similar frequency in energy distribution [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

An Adaptive and Time-Efficient ECG R-Peak Detection Algorithm

Qin

Yue

et al. 2017

Journal of Healthcare Engineering

View full text Add to dashboard Cite

R-peak detection is crucial in electrocardiogram (ECG) signal analysis. This study proposed an adaptive and time-efficient R-peak detection algorithm for ECG processing. First, wavelet multiresolution analysis was applied to enhance the ECG signal representation. Then, ECG was mirrored to convert large negative R-peaks to positive ones. After that, local maximums were calculated by the first-order forward differential approach and were truncated by the amplitude and time interval thresholds to locate the R-peaks. The algorithm performances, including detection accuracy and time consumption, were tested on the MIT-BIH arrhythmia database and the QT database. Experimental results showed that the proposed algorithm achieved mean sensitivity of 99.39%, positive predictivity of 99.49%, and accuracy of 98.89% on the MIT-BIH arrhythmia database and 99.83%, 99.90%, and 99.73%, respectively, on the QT database. By processing one ECG record, the mean time consumptions were 0.872 s and 0.763 s for the MIT-BIH arrhythmia database and QT database, respectively, yielding 30.6% and 32.9% of time reduction compared to the traditional Pan-Tompkins method.

show abstract

Real-time prediction of acute cardiovascular events using hardware-implemented Bayesian networks

Cited by 25 publications

References 15 publications

Machine learning in cardiovascular medicine: are we there yet?

Machine learning in cardiovascular medicine: are we there yet?

Bayesian network modelling study to identify factors influencing the risk of cardiovascular disease in Canadian adults with hepatitis C virus infection

An Adaptive and Time-Efficient ECG R-Peak Detection Algorithm

Contact Info

Product

Resources

About