Probabilities for decision-analytic models are routinely obtained from the medical literature. This study describes development and use of a literature database to facilitate obtaining probabilities for decision-analytic models of thrombolytic therapy for acute myocardial infarction. Implementation demonstrates the concept of a literature database to be both feasible and effective. Specific difficulties encountered in the evaluation of continuous variables, the potential storage of actual probabilities, and the advantage for easy growth with the literature are discussed.