{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T06:42:07Z","timestamp":1781592127878,"version":"3.54.5"},"reference-count":52,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2019,4,18]],"date-time":"2019-04-18T00:00:00Z","timestamp":1555545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Taiwan carbon nanometer technology corporation, Taiwan","award":["ME-103006"],"award-info":[{"award-number":["ME-103006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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\u2019 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\u2019 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 \u00b1 0.0135 and 0.8686 \u00b1 0.0422 accuracies, 0.9714 \u00b1 0.0131, 0.9250 \u00b1 0.0423 sensitivities, and 0.9288 \u00b1 0.0306, 0.8639 \u00b1 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 \u00b1 0.0058 and 0.9410 \u00b1 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.<\/jats:p>","DOI":"10.3390\/s19081866","type":"journal-article","created":{"date-parts":[[2019,4,18]],"date-time":"2019-04-18T11:58:21Z","timestamp":1555588701000},"page":"1866","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Machine Learning Methods Applied to Predict Ventilator-Associated Pneumonia with Pseudomonas aeruginosa Infection via Sensor Array of Electronic Nose in Intensive Care Unit"],"prefix":"10.3390","volume":"19","author":[{"given":"Yu-Hsuan","family":"Liao","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Yuan Ze University, Chungli 32003, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong-Chuang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Yuan Ze University, Chungli 32003, Taiwan"},{"name":"College of Mechanical Engineering, Guizhou University, Guiyang 550025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fu-Gui","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering, Guizhou University, Guiyang 550025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8515-7933","authenticated-orcid":false,"given":"Maysam F.","family":"Abbod","sequence":"additional","affiliation":[{"name":"College of Engineering, Design and Physical Sciences, Brunel University London, Uxbridge UB8 3PH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung-Hung","family":"Shih","sequence":"additional","affiliation":[{"name":"Division of Thoracic Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan"},{"name":"Division of Pulmonary Medicine, Department of Internal Medicine, Taipei Medical University Hospital, Taipei 11031, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiann-Shing","family":"Shieh","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Yuan Ze University, Chungli 32003, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,4,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1164\/ajrccm.165.7.2105078","article-title":"Ventilator-associated pneumonia","volume":"165","author":"Chastre","year":"2002","journal-title":"Am. J. Resp. Crit. Care Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1926","DOI":"10.1001\/archinte.160.13.1926","article-title":"Ventilator-associated pneumonia","volume":"160","author":"Morehead","year":"2000","journal-title":"Arch. Intern. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1700582","DOI":"10.1183\/13993003.00582-2017","article-title":"International ERS\/ESICM\/ESCMID\/ALAT guidelines for the management of hospital-acquired pneumonia and ventilator-associated pneumonia: Guidelines for the management of hospital-acquired pneumonia (HAP)\/ventilator-associated pneumonia (VAP) of the European Respiratory Society (ERS), European Society of Intensive Care Medicine (ESICM), European Society of Clinical Microbiology and Infectious Diseases (ESCMID) and Asociaci\u00f3n Latinoamericana del T\u00f3rax (ALAT)","volume":"50","author":"Torres","year":"2017","journal-title":"Eur. Respir. J."},{"key":"ref_4","unstructured":"Disease Control Bureau, Ministry of Health and Welfare, Taipei (2017). Statistical Report on the Cause of Death."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.microc.2004.10.008","article-title":"Breath analysis: Trends in techniques and clinical applications","volume":"79","author":"Fuoco","year":"2005","journal-title":"Microchem. J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"030301","DOI":"10.1088\/1752-7163\/2\/3\/030301","article-title":"Exhaled breath analysis: The new frontier in medical testing","volume":"2","author":"Dweik","year":"2008","journal-title":"J. Breath Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"34001","DOI":"10.1088\/1752-7155\/9\/3\/034001","article-title":"Established methodological issues in electronic nose research: How far are we from using these instruments in clinical settings of breath analysis?","volume":"9","author":"Bikov","year":"2015","journal-title":"J. Breath Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/S0925-4005(01)00625-6","article-title":"Application of the electronic nose for uremia diagnosis","volume":"76","author":"Guo","year":"2001","journal-title":"Sens. Actuators B Chem."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1007\/s10439-005-1438-2","article-title":"Smelling Renal Dysfunction via Electronic Nose","volume":"33","author":"Voss","year":"2005","journal-title":"Ann. Biomed. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1109\/TBCAS.2011.2116786","article-title":"A Low-Power Electronic Nose Signal-Processing Chip for a Portable Artificial Olfaction System","volume":"5","author":"Tang","year":"2011","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1111\/j.1600-0846.2007.00284.x","article-title":"Identification of melanoma with a gas sensor array","volume":"14","author":"Bono","year":"2008","journal-title":"Ski. Res. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.snb.2005.01.040","article-title":"Analysis of diabetic patient\u2019s breath with conducting polymer sensor array","volume":"108","author":"Yu","year":"2005","journal-title":"Sens. Actuators B. Chem."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1089\/1520915041705992","article-title":"Volatile Metabolic Monitoring of Glycemic Status in Diabetes Using Electronic Olfaction","volume":"6","author":"Dalton","year":"2004","journal-title":"Technol. Ther."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Blatt, R., Bonarini, A., Calabr\u00f2, E., Della Torre, M., Matteucci, M., and Pastorino, U. (2007, January 12\u201317). Lung Cancer Identification by an Electronic Nose based on an Array of MOS Sensors. Proceedings of the 2007 International Joint Conference on Neural Networks, Orlando, FL, USA.","DOI":"10.1109\/IJCNN.2007.4371167"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.1016\/S0956-5663(03)00086-1","article-title":"Lung cancer identification by the analysis of breath by means of an array of non-selective gas sensors","volume":"18","author":"Macagnano","year":"2003","journal-title":"Biosens. Bioelectron."},{"key":"ref_16","first-page":"856","article-title":"An electronic nose in the discrimination of patients with asthma and controls","volume":"120","author":"Dragonieri","year":"2007","journal-title":"J. Clin. Immunol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s11325-014-1003-z","article-title":"Evening and morning exhaled volatile compound patterns are different in obstructive sleep apnoea assessed with electronic nose","volume":"19","author":"Kunos","year":"2015","journal-title":"Sleep Breath"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1006\/abio.1997.2069","article-title":"Method for the Collection and Assay of Volatile Organic Compounds in Breath","volume":"247","author":"Phillips","year":"1997","journal-title":"Anal. Biochem."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1586\/17434440.2.5.559","article-title":"Medical applications of electronic nose technology","volume":"2","author":"Thaler","year":"2005","journal-title":"Rev. Med Devices"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1177\/0885066606288837","article-title":"Ventilator-Associated Pneumonia: A Review","volume":"21","author":"Davis","year":"2006","journal-title":"J. Intensiv. Care Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/S0873-2159(15)30145-8","article-title":"Airways inflammation evaluation. Upper and lower airways","volume":"15","author":"Geraldes","year":"2009","journal-title":"Rev. Port. Pneumol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"27108","DOI":"10.1088\/1752-7155\/6\/2\/027108","article-title":"The versatile use of exhaled volatile organic compounds in human health and disease","volume":"6","author":"Boots","year":"2012","journal-title":"J. Breath Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e1003311","DOI":"10.1371\/journal.ppat.1003311","article-title":"Volatile Metabolites of Pathogens: A Systematic Review","volume":"9","author":"Bos","year":"2013","journal-title":"PLoS Pathog."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1016\/j.rmed.2015.09.014","article-title":"Electronic nose analysis of exhaled breath to diagnose ventilator-associated pneumonia","volume":"109","author":"Schnabel","year":"2015","journal-title":"Respir. Med."},{"key":"ref_25","unstructured":"Wong, M. (2013). Detection of Electronic Nasal Pneumonia Using Pattern Recognition, National Tsinghua University."},{"key":"ref_26","first-page":"183","article-title":"Review data analysis for electronic nose systems","volume":"15","author":"Scott","year":"2007","journal-title":"Microchim. Acta"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2015\/536863","article-title":"Computational Depth of Anesthesia via Multiple Vital Signs Based on Artificial Neural Networks","volume":"2015","author":"Sadrawi","year":"2015","journal-title":"Biomed Res. Int."},{"key":"ref_28","first-page":"1","article-title":"EEG Signals Analysis Using Multiscale Entropy for Depth of Anesthesia Monitoring during Surgery through Artificial Neural Networks","volume":"2015","author":"Liu","year":"2015","journal-title":"Comput. Math. Methods Med."},{"key":"ref_29","first-page":"30","article-title":"HRV-derived data similarity and distribution index based on ensemble neural network for measuring depth of anaesthesia","volume":"5","author":"Liu","year":"2017","journal-title":"PeerJ"},{"key":"ref_30","first-page":"230","article-title":"Model selection for support vector machines","volume":"Volume 12","author":"Chapelle","year":"2000","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/S0925-2312(03)00375-8","article-title":"Model selection for support vector machine classification","volume":"55","author":"Gold","year":"2003","journal-title":"Neurocomputing"},{"key":"ref_32","first-page":"109","article-title":"Hyper parameter design criteria for support vector classifiers","volume":"55","author":"Anguita","year":"2003","journal-title":"Neuro Comput."},{"key":"ref_33","unstructured":"Ancona, N., Cicirelli, G., and Distance, A. (2002, January 12\u201317). Complexity reduction and parameter selection in support vector machines. Proceedings of the 2002 International Joint Conference on Neural Networks, Honolulu, HI, USA."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"34001","DOI":"10.1088\/1752-7155\/8\/3\/034001","article-title":"The human volatilome: Volatile organic compounds (VOCs) in exhaled breath, skin emanations, urine, feces and saliva","volume":"8","author":"Amann","year":"2014","journal-title":"J. Breath Res."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"17179","DOI":"10.1038\/srep17179","article-title":"Analysis of volatile organic compounds in exhaled breath to diagnose ventilator-associated pneumonia","volume":"5","author":"Schnabel","year":"2015","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1093\/jat\/25.1.26","article-title":"FT-IR breath test in the diagnosis and control of treatment of methanol intoxications","volume":"25","author":"Laakso","year":"2001","journal-title":"J. Anal. Toxicol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1016\/j.jchromb.2008.08.031","article-title":"GC-MS analysis of breath odour compounds in liver patients","volume":"875","author":"Nevens","year":"2008","journal-title":"J. Chromatogr. B"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.ijms.2004.08.010","article-title":"Applications of breath gas analysis in medicine","volume":"239","author":"Amann","year":"2004","journal-title":"Int. J. Mass Spectrom."},{"key":"ref_39","unstructured":"Pearce, T., Schiffman, S., Nagle, H., and Gardner, J. (2006). Handbook of Machine Olfaction: Electronic Nose Technology, Wiley."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Gardner, J., and Bartlett, P. (1992). Sensors and Sensory Systems for an Electronic Nose, Springer.","DOI":"10.1007\/978-94-015-7985-8"},{"key":"ref_41","first-page":"4","article-title":"Bacteria classification using Cyranose 320 electronic nose","volume":"1","author":"Dutta","year":"2002","journal-title":"Biomed. Eng."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1109\/34.58871","article-title":"Neural network ensembles","volume":"12","author":"Hansen","year":"1990","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/S0004-3702(02)00190-X","article-title":"Ensembling neural networks: Many could be better than all","volume":"137","author":"Zhou","year":"2002","journal-title":"Artif. Intell."},{"key":"ref_44","first-page":"17","article-title":"Increasing Efficiency of Support Vector Machine using the Novel Kernel Function: Combination of Polynomial and Radial Basis Function","volume":"3","author":"Bhavsar","year":"2014","journal-title":"Int. J. Adv. Comput. Theory Eng."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Ye, Z., and Li, H. (2012, January 16\u201318). Based on radial basis kernel function of support vector machines for speaker. Proceedings of the 5th International Congress on Image and Signal Processing, Chongqing, China.","DOI":"10.1109\/CISP.2012.6469807"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1016\/S0895-4356(01)00395-X","article-title":"Comparison of logistic regression and neural networks to predict rehospitalization in patients with stroke","volume":"54","author":"Ottenbacher","year":"2001","journal-title":"J. Clin. Epidemiol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.medengphy.2008.04.011","article-title":"Human heart beat analysis using a modified algorithm of detrended fluctuation analysis based on empirical mode decomposition","volume":"31","author":"Yeh","year":"2009","journal-title":"Med. Eng. Phys."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_49","unstructured":"Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., and Shpanskaya, K. (2017). CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"Ledsam","year":"2018","journal-title":"Nat. Med."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"285501","DOI":"10.1088\/1361-6528\/aabf2f","article-title":"Flexible gas sensor based on graphene\/ethyl cellulose nanocomposite with ultra-low strain response for volatile organic compounds rapid detection","volume":"29","author":"Zhang","year":"2018","journal-title":"Nanotechnology"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Xia, Y. (2018). 3D Architectured Graphene\/Metal Oxide Hybrids for Gas Sensors: A Review. Sensors, 18.","DOI":"10.3390\/s18051456"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/8\/1866\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:46:33Z","timestamp":1760186793000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/8\/1866"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,18]]},"references-count":52,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2019,4]]}},"alternative-id":["s19081866"],"URL":"https:\/\/doi.org\/10.3390\/s19081866","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,18]]}}}