ASSESSMENT OF QUANTITATIVE ARTIFICIAL NEURAL-NETWORK ANALYSIS IN A METABOLICALLY DYNAMIC EX-VIVO P-31 NMR PIG-LIVER STUDY

Quantitative artificial neural network analysis for 1550 ex vivo P-31 nuclear magnetic resonance spectra from hypothermically reperfused pig livers was assessed. These spectra show wide ranges of metabolite con centrations and have been analyzed using metabolite prior knowledge ba sed lineshape fitting analysis which had proved robust in its biochemi cal interpretation. This finding provided a good opportunity to assess the performance of artificial neural network analysis in a biochemica lly complex situation. The results showed high correlations (0.865 les s than or equal to R less than or equal to 0.992) between the lineshap e fitting and artificial neural network analysis for the metabolite va lues, and the artificial neural network analysis was able to fully rep resent the trends in the metabolic fluctuations during the experiments .