Pulmonary embolism is a common and potentially fatal condition in emergency medicine, where accurate early risk stratification is crucial for clinical management. Existing models such as PESI and PERFORM use discrete scoring systems and subjective variables, which can lead to bias and lower accuracy. The study proposes a new CON-PERFORM model that includes three readily available objective parameters, arterial pressure and heart rate, with weighted coefficients determined by functional optimization for continuous risk scores. The model was tested on a retrospective cohort of 559 patients with confirmed pulmonary embolism (373 in the training set, 186 in the validation set) and a prospective cohort of 128 patients. In the training cohort, CON-PERFORM achieved an AUC of 0.841 versus 0.793 for PERFORM, with similar improvements in the validation cohorts. The model effectively divided patients into high- and low-risk groups that had different patterns of survival and discharge at 30 days. CON-PERFORM is a simple, objective and robust tool for individualized risk assessment in pulmonary embolism with improved diagnostic performance and stability across cohorts.