The residual risk of sepsis: modeling the effect of concentration on bacterial detection in two-bottle culture systems and an estimation of false-negative culture rates

Abstract

Background: Septic reactions continue to be reported with culture-tested platelet (PLT) products, probably due to false-negative results associated with inadequate sampling of low-concentration bacteria. The mechanism of test failure was modeled and false-negative rates were estimated utilizing published data.

Study design and methods: The effect of concentration on the probability of sampling one or more viable bacteria in an 8-mL sample of a 300-mL product was determined. The ratio of single- versus dual-bottle-positive tests in repeated cultures utilizing two-bottle systems was used to assess mean bacterial concentrations and to predict false-negative tests.

Results: Published reports reveal a mean residual risk of sepsis of 2.3 per 10(5) products tested. Modeling the effect of concentration predicts that 50 and 95 percent of samples are detected at 0.09 and 0.36 CFU per mL for organisms that grow under both aerobic and anaerobic conditions, and suggest a 50 and 5 percent false-negative culture rate at these concentrations. Reanalysis of published studies documenting single-bottle growth of nonfastidious organisms indicate that low bacterial concentrations are frequently encountered and predict false-negative cultures in products contaminated with common bacteria at rates that varied from 4 to more than 75 percent. The model highlights the weakness of the AABB definition of false-positive culture results at low bacterial concentrations, especially for organisms that grow poorly in aerobic storage conditions.

Conclusion: Continuing reports of septic reactions after transfusion of culture-tested apheresis PLTs, and frequent single-bottle-positive results when testing with two-bottle systems, suggest appreciable levels of false-negative results with a commercially available bacterial detection system (BacT/ALERT, bioMéreiux) as implemented.