A machine-learning approach to the prediction of oxidative stress in chronic inflammatory disease
Source: Redox Report, Volume 14, Number 1, February 2009 , pp. 23-33(11)
Publisher: Maney Publishing
Abstract:Oxidative stress is implicated in the development of a wide range of chronic human diseases, ranging from cardiovascular to neurodegenerative and inflammatory disorders. As oxidative stress results from a complex cascade of biochemical reactions, its quantitative prediction remains incomplete. Here, we describe a machine-learning approach to the prediction of levels of oxidative stress in human subjects. From a database of biochemical analyses of oxidative stress biomarkers in blood, plasma and urine, non-linear models have been designed, with a statistical methodology that includes variable selection, model training and model selection. Our data demonstrate that, despite a large inter- and intra-individual variability, levels of biomarkers of oxidative damage in biological fluids can be predicted quantitatively from measured concentrations of a limited number of exogenous and endogenous antioxidants.
Document Type: Research Article
Affiliations: 1: École Supérieure de Physique et de Chimie Industrielles, ESPCI–Paristech, Laboratoire d'Électronique (CNRS UMR 7084), Paris, France 2: UMR S551 'Dyslipoproteinemia and Atherosclerosis', Université Pierre et Marie Curie (Paris 6), Paris, France; INSERM, UMR S551, Paris, France 3: Department of Metabolic Biochemistry, La Pitié Hospital (AP-HP), Paris, France; Department of Biochemistry, EA 3617, Faculty of Pharmacy, Paris Descartes University, Paris, France 4: UMR S551 'Dyslipoproteinemia and Atherosclerosis', Université Pierre et Marie Curie (Paris 6), Paris, France; INSERM, UMR S551, Paris, France; AP-HP, Groupe hospitalier Pitié–Salpétrière, Paris, France
Publication date: 2009-02-01