Background Non-physician health workers play an important role in identifying and treating pneumonia in children in low-and middle-income countries (LMICs). In this systematic review, we summarized the evidence on whether health workers can accurately measure respiratory rate (RR) and identify fast breathing to diagnose pneumonia in children under five years of age. Methods We searched MEDLINE, EMBASE, Web of Science, and Scopus from January 1990 to August 2020 without any language restrictions. Reference lists of included studies were also screened for additional records. Studies evaluating the performance of health workers in measuring RR and/or identifying fast breathing compared to a reference standard were included. The methodological quality of the included studies was assessed using the QUADAS-2 tool. A meta-analysis was conducted to report pooled estimates of sensitivity and specificity. Hierarchical summary receiver operating characteristic curve (HSROC) models were fitted, and subgroup and sensitivity analyses were performed to examine the effects of study variables. Results We included 16 studies, eight of which reported the agreement in RR count between health workers and a reference standard. The median agreements were 39%, 47%, and 67% within ??2, ??3, and ??5 breaths per minute, respectively. Among the 16 included studies, we identified 15 studies that reported the accuracy of a health worker classifying breathing into either fast or normal categories compared to a reference standard. The median sensitivity, specificity, accuracy, and kappa value were 77%, 86%, 81%, and 0.75, respectively. Seven studies reporting the accuracy of identifying fast breathing were included in the meta-analysis. The pooled estimates of sensitivity and specificity were 78% (95% CI = 72-82) and 86% (95% CI = 78-91), respectively. Conclusions Despite the problematic nature of reference standards and their variability across studies, our review suggests that the health worker performance in accurately counting RR is relatively poor. However, their performance shows reasonable specificity and moderate sensitivity in identifying fast breathing. Improving the detection of fast breathing in children with suspected pneumonia among health workers is an important child health programme objective and should be given appropriate priority.