Nuclear magnetic resonance (NMR) spectroscopy is finding increasing use in studies of plasma and lipoproteins in health and disease, including cancer. Analysis of the NMR data is not straightforward due to complex systems and also partly unknown underlying biochemistry. Here we demonstrate how artificial neural networks can be utilised in biomedical NMR. Their quantification power is illustrated by establishing lipoprotein lipid quantification directly from plasma 1H NMR data. The biochemical rationale for this example is elucidated on the basis of the relative weights of the spectral inputs in a trained network. A novel application of a Kohonen-type network architecture to classify plasma 1H NMR spectra is also presented.