To evaluate and compare the predictive value of Face, Arm, Speech Test (FAST) and Balance, Eyes, Face, Arm, Speech, Time (BEFAST) scale in the acute ischemic stroke (AIS).We searched Medline and Ovid databases for relevant literature in the English language. There were no limitations on the date. The sensitivity, specificity, likelihood ratio, and diagnostic odds ratio were pooled for meta-analysis. The symmetric receiver operator characteristic curve and Fagan's Nomogram were drawn, and meta-regression and subgroup analysis were used to explore the source of heterogeneity.A total of 9 studies, including 6,151 participants, were analyzed. The combined sensitivity of FAST was 0.77 [95% CI (0.64-0.86)], specificity was 0.60 [95% CI (0.38-0.78)], the area under the ROC curve was 0.76, and the diagnostic ratio was 1.57, while the sensitivity of BEFAST was 0.68 [95% CI (0.23-0.93)], specificity was 0.85 [95% CI (0.72-0.92)], the area under the ROC curve was 0.86, and the diagnostic odds ratio was 2.44. No publication bias was detected in Deeks' funnel plot. For FAST, meta-regression analysis showed that the prospective design, satisfactory description of the index test, and a broad spectrum of disease contributed to the heterogeneity in sensitivity, while no sources contributed to the heterogeneity in sensitivity. When the pretest probability was set as 20%, the posterior probability in Fagan's Nomogram was 32%; however, when the pretest probability was set as 20% in BEFAST, the posterior probability in Fagan's Nomogram was 52%.Our findings indicated that FAST and BEFAST might be useful in the diagnosis of acute ischemic stroke. The diagnostic value of BEFAST in acute ischemic stroke was higher than in FAST; thus, it might have an important role in the fast recognition of acute ischemic stroke.Copyright © 2022 Chen, Zhao, Xu, Guo, Yang, Zhong, Weng and Liu.