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

Authors:
Fu-Gui Zhang
Fu-Gui Zhang
State Key Laboratory of Oral Diseases
Maysam F Abbod
Maysam F Abbod
College of Engineering
Tampa | United States
Jiann-Shing Shieh
Jiann-Shing Shieh
Yuan Ze University
Taiwan

Sensors (Basel) 2019 Apr 18;19(8). Epub 2019 Apr 18.

Department of Mechanical Engineering, Yuan Ze University, Chungli 32003, Taiwan.

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 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 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 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 infection or other diseases.

Download full-text PDF

Source
https://www.mdpi.com/1424-8220/19/8/1866
Publisher Site
http://dx.doi.org/10.3390/s19081866DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6514817PMC
April 2019
7 Reads

Publication Analysis

Top Keywords

vap infection
12
pneumonia infection
8
intensive care
8
care unit
8
enn svm
8
method applied
8
ventilator-associated pneumonia
8
prediction models
8
learning methods
8
methods applied
8
machine learning
8
infection
6
models
5
evaluate models'
4
order evaluate
4
tested order
4
models trained
4
applied study
4
study enn
4
svm prediction
4

Similar Publications