Prognostic methods in medicine

Prognosis-the prediction of the course and outcome of disease processes-pla ys an important role in patient management tasks like diagnosis and treatme nt planning. As a result, prognostic models form an integral part of a numb er of systems supporting these tasks. Furthermore, prognostic models consti tute instruments to evaluate the quality of health care and the consequence s of health care policies by comparing predictions according to care norms with actual results. Approaches to developing prognostic models vary from u sing traditional probabilistic techniques, originating from the field of st atistics, to more qualitative and model-based techniques, originating from the field of artificial intelligence (AI). In this paper, various approache s to constructing prognostic models, with emphasis on methods from the fiel d of AI, are described and compared. (C) 1999 Elsevier Science B.V. All rig hts reserved.