An optimal approach to the diagnosis of deep vein thrombosis (DVT) in lower limbs in the emergency department is still unknown. In this prospective cohort study, we aimed to evaluate the accuracy of the widely available plasma D-dimer test (VIDAS) and establish the usefulness of combining D-dimer testing with a clinical model to reduce the need for serial ultra-sonographies and improve the diagnostic strategy of DVT. We performed a cohort study in 383 consecutive outpatients referred to the emergency department of Hospital La Princesa, with clinical suspicion of DVT. The patients were stratified into three pre-test probability categories using an explicit clinical model (Wells score), and underwent a quantitative automated ELISA D-dimer assay (VIDAS D-Dimer bioMérieux). Patients were managed according to the diagnostic strategy based on clinical probability and compression ultrasonography (CU). Patients for whom DVT was considered a high pre-test probability with negative ultrasonographic findings in the initial CU, returned the following week for repeat ultrasonography. All patients with DVT excluded did not receive anticoagulant therapy, and were followed up for three months to monitor the development of venous thromboembolic complications. DVT was confirmed in 102 patients (26.6%): 95 in the initial test, four in the second test, and three who developed venous thromboembolic complications in the three-month follow-up period. The calculated D-dimer cut-off level was 1 micro g/ml. One hundred patients (98%) with DVT had positive D-dimer. D-dimer had a sensitivity of 98% and a negative predictive value of 98.6%. Among the high-probability patients with positive D-dimer tests and initial negative CU, 9.75% had DVT on repeat CU at one week. The study results suggest that the addition of VIDAS D-dimer to this diagnostic algorithm could improve the management of patients with suspected DVT in daily practice. A diagnostic approach of DVT based on D-dimer (cut-off > or =1 microg/ml) as the first diagnostic tool for the exclusion of DVT, and the clinical probability model as the tool that identifies those patients requiring a second ultrasonography is useful and suitable for daily medical practice.