Table 1.
Application of e-nose for evaluation of different diseases using urine samples.
| Reference Number | Authors (Year) | Disease Studied | Detection System | Data Processing Methods |
|---|---|---|---|---|
| [49] | Pavlou et al. (2002) | BC | 14 CP | GA, NN, PCA, DFA-cv |
| [50] | Bruins et al. (2009) | BC | 1 MOS | SW-MV, DTW |
| [51] | Yates et al. (2005) | BC | 32 CP (Cyrano Sciences C320, Smiths Detection, Bushey, Hertfordshire, UK) | MPL, ARX, RBFs, non linear ARX |
| [52] | Aathithan et al. (2001) | BC | 4 CP (Osmetech Microbial Analyzer-OMA, Osmetech plc, Crewe, UK) | PCA |
| [53] | Pavlou et al. (2002) | UTI | 14 CP | GA, NN, PCA, DFA-cv |
| [54] | Kodogiannis et al. (2008) | UTI | 14 CP (Bloodhound BH-114, Bloodhound Sensors Ltd., Leeds, UK) | implementation of an advanced NN |
| [55] | Roine et al. (2014) | UTI | 6 MOS (ChemPro 100i, Environics Inc., Mikkeli, Finland) | LDA, LR, PCA |
| [56] | Kodogiannis et al. (2005) | UTI | 32 CP (Cyranose E-320, Sensigent, Baldwin Park, CA, USA ) | NN, EM, SM |
| [57] | Sabeel et al. (2013) | UTI | 32 CP (Cyranose E-320, Sensigent, Baldwin Park, CA, USA) | PCA |
| [58] | Persaud et al. (2005) | UTI | CP | PCA |
| [59] | Bernabei et al. (2007) | CD | 8 QCM | PCA, PLS-DA |
| [60] | Weber et al. (2011) | CD | 12 MOS, 12 MOSFET, 1 capacitance-based humidity sensor and 1 IR-based CO2 sensor | PLS-DA |
| [61] | Horstmann et al.(2015) | CD | MOS | PCA |
| [62] | D’Amico et al. (2012) | CD | 8 QCM | PLS-DA |
| [63] | Santonico et al. (2014) | CD | 8 QCM | PLS-DA |
| [64] | Asimakopoulos et al. (2014) | CD | 8 QCM | PLS-DA |
| [65] | Roine et al. (2014) | CD | 8 electrode strips and 1 MOS (ChemPro® 100, Environics Inc., Mikkeli, Finland) | LDA, LOOCV |
| [66] | Westenbrink et al. (2014) | CD | 8 amperometric electro-chemical sensors (Alphasense Ltd., Great Notley, Essex, UK), 2 non-dispersive IR, optical devices (Clairair Ltd., Witham, UK) and 1 photo-ionisation detector (Mocon, Minneapolis, MN, USA). | LDA |
| [67] | Satetha Siyang et al. (2012) | D | 8 commercial chemical gas sensors, based on change of resistance (TGS sensors) | PCA, CA |
| [68] | Ping et al. (1997) | D | MOS | NN, fuzzy cluster pattern recognition |
| [69] | Di Natale et al. (1999) | KD | QMB | PCA |
| [70] | Arasaradnam et al. (2012) | BD | 6 MOS, 1 optical IR sensor, 1 pellistor, 6 electrochemical sensors | PCA, LDA |
| [71] | Arasaradnam et al. (2013) | BD | 18 MOS (Fox 4000, AlphaMOS, Toulouse, France) | PCA |
| [72] | Covington et al. (2013) | BD | 10 MOS | PCA, LDA |
| [73] | Mohamed et al. (2013) | exposure to toxic agents | 10 MOS (PEN3, Airsense Analytics GmbH, Schwerin, Germany) | PCA |
Abbreviations: Genetic algorithms (GA), neural networks (NN), principal components analysis (PCA), discriminant function analysis and cross-validation (DFA-cv), Sliding Window-Minimum Variance matching adaptation of the Dynamic Time Warping algorithm (SW-MV, DTW), Multilayer perceptron (MLP), autoregressive exogenous type (ARX), Radial basis functions (RBFs), parametric Discriminant Function Analyses and cross validation (DFA-cv), linear discriminant analysis (LDA), logistic regression (LR), Expectation Maximization algorithm (EM), Split and Merge (SM), partial least squares-discriminant analysis (PLS-DA), leave-one-out cross-validation (LOOCV), cluster analysis (CA), bacteria cultures (BC), urinary tract infections(UTI), cancer diseases (CD), diabetes (D), kidney diseases (KD), bowel diseases (BD), metal oxide semiconductors (MOS), quartz microbalances (QMB or QCM), metal oxide semiconductor field effect transistor (MOSFET), conducting polymer (CP).