Abstract

Prediction research is relatively new to the occupational health field while it is well established to support decision making in clinical medicine. Prediction models are developed to estimate the individual probability of the presence (diagnostic model) or future occurrence (prognostic model) of an outcome (i.e. disease). In contrast to etiologic studies, prediction studies utilize the associations between predictors and the outcome to estimate the probability of having or developing an outcome and are not aiming at explaining causal associations. Diagnostic prediction in the field of occupational health will enable objective and standardized quantification of the individual probability of having an occupational disease in a cost-effective manner by avoiding as much as possible the use of (invasive) advanced and costly reference test. Nevertheless, investigators should carefully design the model and clearly state the context where and how it can be used.