RT (min) Bio-Marker Possible origin QF % Sick (n=17) % Healthy (n=9) Molecule Structure Known as biomarker for
3.72 3-Hexanone Dietary [36], Lipid Peroxidation [37] 80 41% 0% image -
3.92 Hexanal Systemic, dietary [36], Lipid Peroxidation [38] 87 47% 0% image Lung cancer [39], Liver Cancer [40]
6.88 3-Ethylcyclopentanone Pheromone[41] 83 35.5% 0% image Age and may be related to oxidative stress [42]
7.84 Ethanol, 2-(2-ethoxyethoxy) Environmental 83 94% 44.5% image  
8.08 1-Propene, 1-(ethylthio)-2-methyl- Environmental – smoking [43] 87 35.5% 11% image  
8.28 Benzeneacetaldehyde Environmental 90 70.5% 55.5% image Antioxidant [44]
8.96 Unknown - - 76.5% 78% - -
9.28 Urea endogenous metabolites 80 94% 89% image  
9.68 Urea 86 88% 55.5%  
10.52 Dodecane, 4-methyl- Probably oxidative stress [45] 89 76.5% 78% image breast cancer [46], Tuberculosis [47] and Melanoma [48], Lung cancer [49]
10.68 3,4-Dimethylbenzaldehyde Environmental –smoking and pollution [50-52] 93 88% 33.5% image  
11.32 Naphthalene, 2-methyl- Environmental –smoking [53] 93 47% 44.5% image Carcinogen [54]
  Or
Naphthalene, 1-methyl-
93    
11.84 2-Methoxy-4-vinylphenol Dietary – smoked food [55] 95 82.5% 66.5% image Antioxidant [56]
12.12 Piperitenone Dietary – mint species [57] 93 47% 11% image Antioxidant [58]
12.28 Toluene-2,4-diisocyanate Environmental 94 64.5% 33.5% image Carcinogen [59]
12.92 5-Methyl-1,3-dihydro-2H-benzimidazol-2-one Drug 91 94% 100% image  
12.96 Unknown - - 94% 100% - -
16.96 2-Pentadecanone, 6,10,14-trimethyl- Dietary
Environmental – Smoking[60]
87 59% 22%  image Antioxidant
17.56 Lidocaine Drug 91 70.5% 0% image  
19.92 Unknown - - 17.5% 0% - -
20.12 Bisphenol A Dietary and Environmental 93 35.5% 22% image Endocrine disruptor [61]
24.00 Unknown - - 35.5% 22% - -
Table 2: Summary of the chemical identity of potential biomarkers obtained using the ANN approach. The chemical identity of a peak is assigned only if the Quality Factor (QF) was greater than 80, otherwise the peak is assigned as unknown. For some peaks in the chromatogram a few possible assignments were possible, in such case all possibilities with QF>80 are shown. There are compounds which occur in both sick and healthy women samples; however their concentration in urine of sick women is 2-3 folds higher.