The determination of the clinical pretest probability using clinical prediction models is an important step in the assessment of patients with suspected pulmonary embolism (PE). It helps establish which test or sequence of tests can effectively corroborate or safely rule out PE. For example, it has been demonstrated that it is safe to withhold anticoagulant therapy in patients with negative d-dimer results and low pretest probability at initial presentation. Clinical probability will also increase the diagnostic yield of ventilation perfusion lung scan. Compared with clinical gestalt, clinical prediction rules provide a standardized and more reproducible estimate of a patient's probability of having a PE. Clinical prediction models combine aspects of the history and physical examination to categorize a patient's probability of having a disease. The models classify patients as having a low, moderate, or high likelihood of having PE. Clinical prediction models have been validated and are well established for the diagnosis of PE in symptomatic patients. They allow all physicians, whatever their expertise, to reliably determine the clinical pretest probability of PE, and thus safely manage their patients using diagnostic and therapeutic algorithms.