Objective To determine whether B-type natriuretic peptide （BNP） levels combined with Spontaneous breathing trial (SBT) could improve the weaning outcome. Methods Eighty-three patients who were ready to undergo a 90-minute weaning trial （low-pressure support level） were enrolled .Weaning was considered to be successful if the patient passed the trial and sustained spontaneous breathing for more than 48 h after extubation. Plasma BNP was measured just before and at the end of the trial. All patients were divided into a weaning success group and a weaning failure group according to the outcomes of weaning. Categorical variables，expressed as percentages，were analyzed with a chi-square test or a Fisher’s exact test. Continuous variables were expressed as median （25th-75th percentile） and were compared using the Wilcoxon paired test （for related samples） or the Kolgomorov-Smirnov test （for independent samples）. A two-tailed p value of less than 0.05 was taken to indicate statistical significance. Receiver operating characteristic （ROC） curve analysis was performed to assess plasma BNP’s ability to discriminate the subjects who weaned succesfully or failed. Results Overall，13 patients （16.7%） failed the weaning process （6 patients passed the trial but failed extubation）. At the end of SBT，the BNP levels of the weaning failure group were significantly higher than the weaning success group. The BNP levels of the weaning failure group were significantly higher than the weaning success group （Plt;0.001）. The area under cure （AUC） of the ROC curve of BNP to predict the failure of weaning was 0.94±0.03 （Plt;0.001）.At a cut-off level of 123 pg/mL,BNP had a predictive efficiency in weaning outcome as Yourdon’s index of 0.837，sensitivity of 92.3%，and specificity of 91.4%. Conclusion Monitoring the change of BNP during a SBT may improve weaning outcome.