The development and validation of biomarkers that link environmental exposures to the pathogenesis of human disease is a leading priority in the field of environmental research. The validation of biomarkers as early predictors of clinical disease can enhance health risk assessment and contribute to effective new disease prevention policies in environmental and occupational settings. The process of validating biomarkers involves dealing with a range of characteristics that include the intrinsic qualities of the biomarker, its determinants, and the analytic procedure. We discuss here a three phase approach to validation. The final phase, consisting of longitudinal studies, is reached after the biomarker has been determined to be technically reliable and after the effect of external variables on the association with the outcome has been evaluated. We provide some examples of biomarkers reputed to be early predictors of cancer and cardiovascular disease (CVD). We then present original data to support the potential of DNA adducts to predict cancer and show, through re-evaluation of the Italian database on cytogenetic biomarkers, a lack of association between the frequency of chromosomal aberrations in circulating lymphocytes and CVD mortality rates - a finding that should not be considered conclusive. In general, whenever a biomarker has been determined to be a valid predictor of disease, it should be used in risk assessment and public health policy. (C) 2001 Elsevier Science B.V. All rights reserved.
