Purpose: An objective and simple prognostic model for patients with pulmonary embolism (PE) could be helpful in medical decision making by guiding initial intensity of treatment. We therefore sought to develop a clinical prediction rule that accurately classifies patients with PE into categories of increasing risk of mortality and other adverse medical outcomes. Methods: We randomly allocated 15,531 inpatient discharges with an ICD-9-CM diagnosis of PE from 186 Pennsylvania hospitals between 1/2000 and 11/2002 to derivation (67%) and internal validation (33%) samples. We derived our prediction rule using logistic regression with 30-day mortality as the primary outcome, and patient demographic and clinical data routinely available at presentation as potential predictor variables. We externally validated the rule in 221 inpatients with prospectively diagnosed PE from 3 Swiss and French emergency departments. We compared mortality and nonfatal adverse medical outcomes across the derivation and 2 validation samples. Results: The prediction rule assigns points based on the following 11 patient characteristics that were independently associated with mortality: age, male sex, cancer, heart failure, chronic lung disease, pulse ³110/minute, systolic blood pressure <100 mm Hg, respiratory rate ³30/minute, altered mental status, temperature <36ºC, and arterial oxygen saturation <90%. Patients were stratified into 5 severity classes, with 30-day mortality rates of 0-1.6% in class I, 1.8-3.5% in class II, 3.1-7.1% in class III, 4.2-11.4% in class IV, and 8.7-24.5% in class V across the derivation and validation samples. Mortality in each risk class did not significantly differ between the derivation and validation samples. The rates of inpatient death and nonfatal medical complications were £1.1% among patients in class I and £1.9% among patients in class II. Conclusions: We derived and validated a practical bedside tool for risk stratification that accurately classifies patients with PE into classes of increasing risk of mortality and other adverse medical outcomes. Outpatient management or early hospital discharge of patients in risk classes I and II has the potential to result in large cost-savings. Further validation of the rule in a formal outcome study is important prior to its implementation as a decision aid to guide the initial mangement of patients with PE.