Background Neutrophil‐to‐lymphocyte ratio (NLR) is an accessible and widely used biomarker. NLR may be used as an early marker of poor prognosis in patients with COVID‐19. Objective To evaluate the prognostic value of the NLR in patients diagnosed with COVID‐19. Methods We conducted a systematic review and meta‐analysis. Observational studies that reported the association between baseline NLR values (ie, at hospital admission) and severity or all‐cause mortality in COVID‐19 patients were included. The quality of the studies was assessed using the Newcastle‐Ottawa Scale (NOS). Random effects models and inverse variance method were used for meta‐analyses. The effects were expressed as odds ratios (ORs) and their 95% confidence intervals (CIs). Small study effects were assessed with the Egger's test. Results We analysed 61 studies (n = 15 522 patients), 58 cohorts, and 3 case‐control studies. An increase of one unit of NLR was associated with higher odds of severity (OR 6.22; 95%CI 4.93 to 7.84; P < .001) and higher odds of all‐cause mortality (OR 12.6; 95%CI 6.88 to 23.06; P < .001). In our sensitivity analysis, we found that 41 studies with low risk of bias and moderate heterogeneity (I2 = 53% and 58%) maintained strong association between NLR values and both outcomes (severity: OR 5.36; 95% CI 4.45 to 6.45; P < .001; mortality: OR 10.42 95% CI 7.73 to 14.06; P = .005). Conclusions Higher values of NLR were associated with severity and all‐cause mortality in hospitalised COVID‐19 patients.