Background: The predictive power of extubation failure diagnosed by cough strength is various in different studies. We aimed to summarize the diagnostic power of extubation failure tested by cough strength. Methods: A comprehensive on-line search was performed to select any potentially eligible studies that evaluated the predictive power of extubation failure tested by cough strength. A manual research was also performed to identify additional studies. Data were extracted to calculate the pooled sensitivity, specificity, positive likelihood ratio (LR), negative LR, diagnostic odds ratio (DOR), and area under the receiver operating characteristic curves (AUC) to evaluate predictive power of extubation failure. I2 was used to test the heterogeneity and deek’s funnel plot was used to detect the publication bias.Results: A total of 35 studies involving 7515 patients were included. Of them, 1113 patients (14.8%) experienced extubation failure. Twenty studies involving 2787 patients assessed cough strength by measure of cough peak flow (CPF) to predict extubation failure. The pooled sensitivity, specificity, positive LR, negative LR, DOR, and AUC were 0.77 (95%CI: 0.72-0.80), 0.75 (0.69-0.80), 2.84 (2.36-3.42), 0.34 (0.29-0.39), 9.16 (6.14-13.67), and 0.81 (0.77-0.84), respectively. Twenty studies involving 5508 patients assessed cough strength by measurement of a semiquantitative cough strength scale (SCSS) to predict extubation failure. The pooled sensitivity, specificity, positive LR, negative LR, DOR, and AUC were 0.54 (95%CI: 0.43-0.65), 0.82 (0.73-0.88), 2.48 (1.92-3.21), 0.63 (0.54-0.74), 4.61 (3.03-7.01), and 0.74 (0.70-0.78), respectively. Conclusions: Cough strength can be measured by CPF and SCSS. The CPF has good predictive power to diagnose extubation failure and SCSS has moderate predictive power.