Generic Ensemble-Based Representation of Global Cardiovascular Dynamics for Personalized Treatment Discovery and Optimization

Senyukova, Olga V.; Gavrishchaka, Valeriy V.; Sasonko, M. L.; Gurfinkel, Yuri; Gorokhova, Svetlana; Antsygin, Nikolay

doi:10.1007/978-3-319-45243-2_18

Cited by 8 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…collected by Holter monitor) are available. As evident from Figure 19, ensemble-based indicator shows significant improvement in all three cases [79].…”

Section: Universal Indicators For Robust Detection Of Complex Asymptmentioning

confidence: 79%

“…collecting such detailed test data, results of the application of our overall framework to real clinical data are very encouraging [79].…”

Section: Generic Ensemble-based Representation Of Global Cardiovasculmentioning

confidence: 90%

“…Direct comparison of full ECG (RR) time series from two individuals is not effective due to the high level of noise and natural long-term variations of the ECG time series. Collection of consecutive EDL vectors provides effectively filtered representation using natural discretization (classification framework) that removes unimportant variations but preserves differentiation among key micro-states [79]. By calculating Euclidean distances between each EDL vector of one subject with each EDL vector of another subject, the distance matrix is obtained.…”

Section: Generic Ensemble-based Representation Of Global Cardiovasculmentioning

confidence: 99%

“…Representing long RR time series with a collection of consecutive EDL vectors and using MST for computing aggregated distance between such collections, one can obtain differentiation even within the same abnormality type as illustrated in Figure 21 [79]. Here we show MST-based distances between each pair of 20 CHF patients using a collection of 50 consecutive EDL vectors obtained from the same normal-abnormal ensemble indicator as in Figure 19.…”

Section: Generic Ensemble-based Representation Of Global Cardiovasculmentioning

confidence: 99%

“…The importance of (1) using ensemble measures, (2) MST for handling cross-subject distance metrics, and (3) long-duration ECG time series, is demonstrated in Figure 22 [79]. Here, we rank the distance of each CHF subject to himself against distances to other subjects.…”

Section: Generic Ensemble-based Representation Of Global Cardiovasculmentioning

confidence: 99%

See 4 more Smart Citations

Synergy of physics-based reasoning and machine learning in biomedical applications: towards unlimited deep learning with limited data

Gavrishchaka

Senyukova

Koepke

2019

Advances in Physics: X

Self Cite

View full text Add to dashboard Cite

Technological advancements enable collecting vast data, i. e., Big Data, in science and industry including biomedical field. Increased computational power allows expedient analysis of collected data using statistical and machine-learning approaches. Historical data incompleteness problem and curse of dimensionality diminish practical value of pure data-driven approaches, especially in biomedicine. Advancements in deep learning (DL) frameworks based on deep neural networks (DNN) improved accuracy in image recognition, natural language processing, and other applications yet severe data limitations and/or absence of transferlearning-relevant problems drastically reduce advantages of DNN-based DL. Our earlier works demonstrate that hierarchical data representation can be alternatively implemented without NN, using boosting-like algorithms for utilization of existing domain knowledge, tolerating significant data incompleteness, and boosting accuracy of low-complexity models within the classifier ensemble, as illustrated in physiological-data analysis. Beyond obvious use in initial-factor selection, existing simplified models are effectively employed for generation of realistic synthetic data for later DNN pre-training. We review existing machine learning approaches, focusing on limitations caused by trainingdata incompleteness. We outline our hybrid framework that leverages existing domain-expert models/knowledge, boosting-like model combination, DNN-based DL and other machine learning algorithms for drastic reduction of training-data requirements. Applying this framework is illustrated in context of analyzing physiological data.

show abstract

“…collected by Holter monitor) are available. As evident from Figure 19, ensemble-based indicator shows significant improvement in all three cases [79].…”

Section: Universal Indicators For Robust Detection Of Complex Asymptmentioning

confidence: 79%

“…collecting such detailed test data, results of the application of our overall framework to real clinical data are very encouraging [79].…”

Section: Generic Ensemble-based Representation Of Global Cardiovasculmentioning

confidence: 90%

Section: Generic Ensemble-based Representation Of Global Cardiovasculmentioning

confidence: 99%

Section: Generic Ensemble-based Representation Of Global Cardiovasculmentioning

confidence: 99%

Section: Generic Ensemble-based Representation Of Global Cardiovasculmentioning

confidence: 99%

See 3 more Smart Citations

Synergy of physics-based reasoning and machine learning in biomedical applications: towards unlimited deep learning with limited data

Gavrishchaka

Senyukova

Koepke

2019

Advances in Physics: X

Self Cite

View full text Add to dashboard Cite

show abstract

Leveraging Domain-expert Knowledge, Boosting and Deep Learning for Identification of Rare and Complex States

Miao¹,

Yang²,

Gavrishchaka

2019

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Multi-expert evolving system for objective psychophysiological monitoring and fast discovery of effective personalized therapies

Senyukova

Gavrishchaka

Tulnova³

2017

2017 Evolving and Adaptive Intelligent Systems (EAIS)

View full text Add to dashboard Cite

Generic Ensemble-Based Representation of Global Cardiovascular Dynamics for Personalized Treatment Discovery and Optimization

Cited by 8 publications

References 11 publications

Synergy of physics-based reasoning and machine learning in biomedical applications: towards unlimited deep learning with limited data

Synergy of physics-based reasoning and machine learning in biomedical applications: towards unlimited deep learning with limited data

Leveraging Domain-expert Knowledge, Boosting and Deep Learning for Identification of Rare and Complex States

Multi-expert evolving system for objective psychophysiological monitoring and fast discovery of effective personalized therapies

Contact Info

Product

Resources

About