Machine Learning Methods Applied to Predict Ventilator-Associated Pneumonia with Pseudomonas aeruginosa Infection via Sensor Array of Electronic Nose in Intensive Care Unit

Yu-Hsuan Liao, Zhong-Chuang Wang, Fu-Gui Zhang, Maysam F Abbod, Chung-Hung Shih, Jiann-Shing Shieh

研究成果: 雜誌貢獻文章

摘要

One concern to the patients is the off-line detection of pneumonia infection status after using the ventilator in the intensive care unit. Hence, machine learning methods for ventilator-associated pneumonia (VAP) rapid diagnose are proposed. A popular device, Cyranose 320 e-nose, is usually used in research on lung disease, which is a highly integrated system and sensor comprising 32 array using polymer and carbon black materials. In this study, a total of 24 subjects were involved, including 12 subjects who are infected with pneumonia, and the rest are non-infected. Three layers of back propagation artificial neural network and support vector machine (SVM) methods were applied to patients' data to predict whether they are infected with VAP with Pseudomonas aeruginosa infection. Furthermore, in order to improve the accuracy and the generalization of the prediction models, the ensemble neural networks (ENN) method was applied. In this study, ENN and SVM prediction models were trained and tested. In order to evaluate the models' performance, a fivefold cross-validation method was applied. The results showed that both ENN and SVM models have high recognition rates of VAP with Pseudomonas aeruginosa infection, with 0.9479 ± 0.0135 and 0.8686 ± 0.0422 accuracies, 0.9714 ± 0.0131, 0.9250 ± 0.0423 sensitivities, and 0.9288 ± 0.0306, 0.8639 ± 0.0276 positive predictive values, respectively. The ENN model showed better performance compared to SVM in the recognition of VAP with Pseudomonas aeruginosa infection. The areas under the receiver operating characteristic curve of the two models were 0.9842 ± 0.0058 and 0.9410 ± 0.0301, respectively, showing that both models are very stable and accurate classifiers. This study aims to assist the physician in providing a scientific and effective reference for performing early detection in Pseudomonas aeruginosa infection or other diseases.
原文英語
期刊Sensors (Basel, Switzerland)
19
發行號8
DOIs
出版狀態已發佈 - 四月 18 2019

指紋

ventilators
Electronic Nose
pneumonia
Ventilator-Associated Pneumonia
Pseudomonas Infections
Intensive care units
machine learning
pseudomonas
Sensor arrays
infectious diseases
Pseudomonas aeruginosa
Intensive Care Units
Learning systems
Neural Networks (Computer)
sensors
Support vector machines
electronics
Neural networks
Pneumonia
Soot

引用此文

Machine Learning Methods Applied to Predict Ventilator-Associated Pneumonia with Pseudomonas aeruginosa Infection via Sensor Array of Electronic Nose in Intensive Care Unit. / Liao, Yu-Hsuan; Wang, Zhong-Chuang; Zhang, Fu-Gui; Abbod, Maysam F; Shih, Chung-Hung; Shieh, Jiann-Shing.

於: Sensors (Basel, Switzerland), 卷 19, 編號 8, 18.04.2019.

研究成果: 雜誌貢獻文章

@article{abb997dcdc264fd4a4234b0f900797ee,
title = "Machine Learning Methods Applied to Predict Ventilator-Associated Pneumonia with Pseudomonas aeruginosa Infection via Sensor Array of Electronic Nose in Intensive Care Unit",
abstract = "One concern to the patients is the off-line detection of pneumonia infection status after using the ventilator in the intensive care unit. Hence, machine learning methods for ventilator-associated pneumonia (VAP) rapid diagnose are proposed. A popular device, Cyranose 320 e-nose, is usually used in research on lung disease, which is a highly integrated system and sensor comprising 32 array using polymer and carbon black materials. In this study, a total of 24 subjects were involved, including 12 subjects who are infected with pneumonia, and the rest are non-infected. Three layers of back propagation artificial neural network and support vector machine (SVM) methods were applied to patients' data to predict whether they are infected with VAP with Pseudomonas aeruginosa infection. Furthermore, in order to improve the accuracy and the generalization of the prediction models, the ensemble neural networks (ENN) method was applied. In this study, ENN and SVM prediction models were trained and tested. In order to evaluate the models' performance, a fivefold cross-validation method was applied. The results showed that both ENN and SVM models have high recognition rates of VAP with Pseudomonas aeruginosa infection, with 0.9479 ± 0.0135 and 0.8686 ± 0.0422 accuracies, 0.9714 ± 0.0131, 0.9250 ± 0.0423 sensitivities, and 0.9288 ± 0.0306, 0.8639 ± 0.0276 positive predictive values, respectively. The ENN model showed better performance compared to SVM in the recognition of VAP with Pseudomonas aeruginosa infection. The areas under the receiver operating characteristic curve of the two models were 0.9842 ± 0.0058 and 0.9410 ± 0.0301, respectively, showing that both models are very stable and accurate classifiers. This study aims to assist the physician in providing a scientific and effective reference for performing early detection in Pseudomonas aeruginosa infection or other diseases.",
author = "Yu-Hsuan Liao and Zhong-Chuang Wang and Fu-Gui Zhang and Abbod, {Maysam F} and Chung-Hung Shih and Jiann-Shing Shieh",
year = "2019",
month = "4",
day = "18",
doi = "10.3390/s19081866",
language = "English",
volume = "19",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "8",

}

TY - JOUR

T1 - Machine Learning Methods Applied to Predict Ventilator-Associated Pneumonia with Pseudomonas aeruginosa Infection via Sensor Array of Electronic Nose in Intensive Care Unit

AU - Liao, Yu-Hsuan

AU - Wang, Zhong-Chuang

AU - Zhang, Fu-Gui

AU - Abbod, Maysam F

AU - Shih, Chung-Hung

AU - Shieh, Jiann-Shing

PY - 2019/4/18

Y1 - 2019/4/18

N2 - One concern to the patients is the off-line detection of pneumonia infection status after using the ventilator in the intensive care unit. Hence, machine learning methods for ventilator-associated pneumonia (VAP) rapid diagnose are proposed. A popular device, Cyranose 320 e-nose, is usually used in research on lung disease, which is a highly integrated system and sensor comprising 32 array using polymer and carbon black materials. In this study, a total of 24 subjects were involved, including 12 subjects who are infected with pneumonia, and the rest are non-infected. Three layers of back propagation artificial neural network and support vector machine (SVM) methods were applied to patients' data to predict whether they are infected with VAP with Pseudomonas aeruginosa infection. Furthermore, in order to improve the accuracy and the generalization of the prediction models, the ensemble neural networks (ENN) method was applied. In this study, ENN and SVM prediction models were trained and tested. In order to evaluate the models' performance, a fivefold cross-validation method was applied. The results showed that both ENN and SVM models have high recognition rates of VAP with Pseudomonas aeruginosa infection, with 0.9479 ± 0.0135 and 0.8686 ± 0.0422 accuracies, 0.9714 ± 0.0131, 0.9250 ± 0.0423 sensitivities, and 0.9288 ± 0.0306, 0.8639 ± 0.0276 positive predictive values, respectively. The ENN model showed better performance compared to SVM in the recognition of VAP with Pseudomonas aeruginosa infection. The areas under the receiver operating characteristic curve of the two models were 0.9842 ± 0.0058 and 0.9410 ± 0.0301, respectively, showing that both models are very stable and accurate classifiers. This study aims to assist the physician in providing a scientific and effective reference for performing early detection in Pseudomonas aeruginosa infection or other diseases.

AB - One concern to the patients is the off-line detection of pneumonia infection status after using the ventilator in the intensive care unit. Hence, machine learning methods for ventilator-associated pneumonia (VAP) rapid diagnose are proposed. A popular device, Cyranose 320 e-nose, is usually used in research on lung disease, which is a highly integrated system and sensor comprising 32 array using polymer and carbon black materials. In this study, a total of 24 subjects were involved, including 12 subjects who are infected with pneumonia, and the rest are non-infected. Three layers of back propagation artificial neural network and support vector machine (SVM) methods were applied to patients' data to predict whether they are infected with VAP with Pseudomonas aeruginosa infection. Furthermore, in order to improve the accuracy and the generalization of the prediction models, the ensemble neural networks (ENN) method was applied. In this study, ENN and SVM prediction models were trained and tested. In order to evaluate the models' performance, a fivefold cross-validation method was applied. The results showed that both ENN and SVM models have high recognition rates of VAP with Pseudomonas aeruginosa infection, with 0.9479 ± 0.0135 and 0.8686 ± 0.0422 accuracies, 0.9714 ± 0.0131, 0.9250 ± 0.0423 sensitivities, and 0.9288 ± 0.0306, 0.8639 ± 0.0276 positive predictive values, respectively. The ENN model showed better performance compared to SVM in the recognition of VAP with Pseudomonas aeruginosa infection. The areas under the receiver operating characteristic curve of the two models were 0.9842 ± 0.0058 and 0.9410 ± 0.0301, respectively, showing that both models are very stable and accurate classifiers. This study aims to assist the physician in providing a scientific and effective reference for performing early detection in Pseudomonas aeruginosa infection or other diseases.

U2 - 10.3390/s19081866

DO - 10.3390/s19081866

M3 - Article

C2 - 31003541

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 8

ER -