Epidemiology of device-associated infections related to a long-term implantable vascular access device

Abstract

Objective: To examine risk factors for, and determine the incidence of, device-associated infections among patients with an implantable vascular access device.

Setting: Grady Health System, including a 1,000-bed, inner-city, public, teaching hospital and human immunodeficiency virus (HIV), oncology, and sickle cell clinics in Atlanta, Georgia.

Patients: 123 consecutive patients who received a PAS-Port implantable venous access device between January 1 and June 30, 1995.

Design: Retrospective cohort study with follow-up > or = 1 year following device implantation.

Results: Underlying illnesses included HIV infection in 66 patients (median CD4 count, 24.4 cells/mm3), malignancy in 51, and sickle cell disease in 6. Mean age of patients was 43.7 years, 50% were male, and 74% were black. Thirty-one (25%) of 123 patients developed a primary or device-associated bloodstream infection (BSI), and 3 of the 31 patients experienced two separate episodes of infection. The overall rate of infection was 1.23 primary BSIs per 1,000 device days. Patients with cancer had a lower rate of infection than those with HIV infection, but the difference was not statistically significant (0.96 vs 1.50 BSIs/1,000 device days; relative risk, 0.58; 95% confidence interval, 0.27-1.26). Subgroup analysis of patients with different malignancies indicated that infection rates differed according to type of cancer, and there was a trend for heterogeneity across the different cancer strata (P=.06). Gram-positive pathogens accounted for 60% of the pathogens recovered. Six (19%) of 31 patients who developed an infection did so within the first 14 days after implantation. In 11 (32%) of the 34 BSIs, the port required removal; two patient deaths were attributed to device-associated bacteremias (0.072 deaths/1,000 device days).

Conclusions: Approximately one fourth of patients who had a vascular access device implanted developed a primary BSI, but the overall infection rate (per 1,000 device days) was relatively low, even among those with HIV infection. Primary BSI rates in patients with vascular access devices appeared to differ according to the specific underlying illness.