An Approach for Prediction of Acute Hypotensive Episodes via the Hilbert-Huang Transform and Multiple Genetic Programming Classifier

Acute hypotensive episodes (AHEs) are one of the hemodynamic instabilities with high mortality rate that is frequent among many groups of patients. This study presents a methodology to predict AHE for ICU patients based on big data time series. The experimental data we used is mean arterial pressure...

Full description

Saved in:
Bibliographic Details
Main Authors: Dazhi Jiang, Liyu Li, Bo Hu, Zhun Fan
Format: Article
Language:English
Published: Wiley 2015-08-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1155/2015/354807
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849738801001267200
author Dazhi Jiang
Liyu Li
Bo Hu
Zhun Fan
author_facet Dazhi Jiang
Liyu Li
Bo Hu
Zhun Fan
author_sort Dazhi Jiang
collection DOAJ
description Acute hypotensive episodes (AHEs) are one of the hemodynamic instabilities with high mortality rate that is frequent among many groups of patients. This study presents a methodology to predict AHE for ICU patients based on big data time series. The experimental data we used is mean arterial pressure (MAP), which is transformed from arterial blood pressure (ABP) data. Then, the Hilbert-Huang transform method was used to calculate patient's MAP time series and some features, which are the bandwidth of the amplitude modulation, the frequency modulation, and the power of intrinsic mode function (IMF), were extracted. Finally, the multiple genetic programming (Multi-GP) is used to build the classification models for detection of AHE. The methodology is applied in the datasets of the 10th PhysioNet and Computers Cardiology Challenge in 2009 and Multiparameter Intelligent Monitoring for Intensive Care (MIMIC-II). We achieve the accuracy of 83.33% in the training set and 91.89% in the testing set of the 2009 challenge's dataset and the 84.13% in the training set and 82.41% in the testing set of the MIMIC-II dataset.
format Article
id doaj-art-effda54121824d8abe44712cdd3aae29
institution DOAJ
issn 1550-1477
language English
publishDate 2015-08-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-effda54121824d8abe44712cdd3aae292025-08-20T03:06:27ZengWileyInternational Journal of Distributed Sensor Networks1550-14772015-08-011110.1155/2015/354807354807An Approach for Prediction of Acute Hypotensive Episodes via the Hilbert-Huang Transform and Multiple Genetic Programming ClassifierDazhi Jiang0Liyu Li1Bo Hu2Zhun Fan3 State Key Laboratory of Software Engineering, Computer School, Wuhan University, Wuhan 430074, China Department of Computer Science, School of Engineering, Shantou University, Shantou 515063, China Department of Computer Science, School of Engineering, Shantou University, Shantou 515063, China Department of Electronic and Information Engineering, School of Engineering, Shantou University, Shantou 515063, ChinaAcute hypotensive episodes (AHEs) are one of the hemodynamic instabilities with high mortality rate that is frequent among many groups of patients. This study presents a methodology to predict AHE for ICU patients based on big data time series. The experimental data we used is mean arterial pressure (MAP), which is transformed from arterial blood pressure (ABP) data. Then, the Hilbert-Huang transform method was used to calculate patient's MAP time series and some features, which are the bandwidth of the amplitude modulation, the frequency modulation, and the power of intrinsic mode function (IMF), were extracted. Finally, the multiple genetic programming (Multi-GP) is used to build the classification models for detection of AHE. The methodology is applied in the datasets of the 10th PhysioNet and Computers Cardiology Challenge in 2009 and Multiparameter Intelligent Monitoring for Intensive Care (MIMIC-II). We achieve the accuracy of 83.33% in the training set and 91.89% in the testing set of the 2009 challenge's dataset and the 84.13% in the training set and 82.41% in the testing set of the MIMIC-II dataset.https://doi.org/10.1155/2015/354807
spellingShingle Dazhi Jiang
Liyu Li
Bo Hu
Zhun Fan
An Approach for Prediction of Acute Hypotensive Episodes via the Hilbert-Huang Transform and Multiple Genetic Programming Classifier
International Journal of Distributed Sensor Networks
title An Approach for Prediction of Acute Hypotensive Episodes via the Hilbert-Huang Transform and Multiple Genetic Programming Classifier
title_full An Approach for Prediction of Acute Hypotensive Episodes via the Hilbert-Huang Transform and Multiple Genetic Programming Classifier
title_fullStr An Approach for Prediction of Acute Hypotensive Episodes via the Hilbert-Huang Transform and Multiple Genetic Programming Classifier
title_full_unstemmed An Approach for Prediction of Acute Hypotensive Episodes via the Hilbert-Huang Transform and Multiple Genetic Programming Classifier
title_short An Approach for Prediction of Acute Hypotensive Episodes via the Hilbert-Huang Transform and Multiple Genetic Programming Classifier
title_sort approach for prediction of acute hypotensive episodes via the hilbert huang transform and multiple genetic programming classifier
url https://doi.org/10.1155/2015/354807
work_keys_str_mv AT dazhijiang anapproachforpredictionofacutehypotensiveepisodesviathehilberthuangtransformandmultiplegeneticprogrammingclassifier
AT liyuli anapproachforpredictionofacutehypotensiveepisodesviathehilberthuangtransformandmultiplegeneticprogrammingclassifier
AT bohu anapproachforpredictionofacutehypotensiveepisodesviathehilberthuangtransformandmultiplegeneticprogrammingclassifier
AT zhunfan anapproachforpredictionofacutehypotensiveepisodesviathehilberthuangtransformandmultiplegeneticprogrammingclassifier
AT dazhijiang approachforpredictionofacutehypotensiveepisodesviathehilberthuangtransformandmultiplegeneticprogrammingclassifier
AT liyuli approachforpredictionofacutehypotensiveepisodesviathehilberthuangtransformandmultiplegeneticprogrammingclassifier
AT bohu approachforpredictionofacutehypotensiveepisodesviathehilberthuangtransformandmultiplegeneticprogrammingclassifier
AT zhunfan approachforpredictionofacutehypotensiveepisodesviathehilberthuangtransformandmultiplegeneticprogrammingclassifier