Background

Dyspnea is a common chief complaint in the emergency department (ED); differentiating heart failure (HF) from other causes can be challenging. Brain Natriuretic Peptide (BNP) is a new diagnostic test for HF for use in dyspneic patients in the ED. The purpose of this study is to systematically review the accuracy of BNP in the emergency diagnosis of HF.

Methods

We searched MEDLINE (1975–2005) supplemented by reference tracking. We included studies that reported the sensitivity and specificity of BNP for diagnosing HF in ED patients with acute dyspnea. Two reviewers independently assessed study quality. We pooled sensitivities and specificities within five ranges of BNP cutoffs.

Results

Ten studies including 3,344 participants met inclusion criteria. Quality was variable; possible verification or selection bias was common. No studies eliminated patients with obvious medical causes of dyspnea. Most studies used the Triage BNP assay; all utilized a clinical reference standard. Pooled sensitivity and specificity at a BNP cutoff of 100–105 pg/ml were 90% and 74% with negative likelihood ratio (LR) of 0.14; pooled sensitivity was 81% with specificity of 90% at cutoffs between 300 and 400 pg/ml with positive LR of 7.6.

Conclusion

Our analysis suggests that BNP has moderate accuracy in detecting HF in the ED. Our results suggest utilizing a BNP of less than 100 pg/ml to rule out HF and a BNP of greater than 400 pg/ml to diagnose HF. Many studies were of marginal quality, and all included patients with varying degrees of diagnostic uncertainty. Further studies focusing on patients with diagnostic uncertainty will clarify the real-world utility of BNP in the emergency management of dyspnea.