Background: This meta-analysis was designed to explore the relationship between the level of serum potassium and the treatment effect of epidermal growth factor receptor (EGFR) antagonist in advanced non-small cell lung cancer (aNSCLC). Methods: We searched phase II/III prospective clinical trials on treatment with EGFR antagonists for aNSCLC patients. The objective response rate (ORR) and/or the disease control rate (DCR) and the incidence of hypokalemia of high grade (equal to or greater than grade 3) were summarized from all eligible trials. Heterogeneity, which was evaluated by Cochran’s Q-test and the I² statistics, was used to determine whether a random effects model or a fixed effects model will be used to calculate pooled proportions. Subgroup analysis was performed on different interventions, line types, phases, and drug numbers. Results: From 666 potentially relevant articles, 36 clinical trials with a total of 9,761 participants were included in this meta-analysis. The pooled ORR was 16.25% (95%CI = 12.45–21.19) when the incidence of hypokalemia was 0%–5%, and it increased to 34.58% (95%CI = 24.09–45.07) when the incidence of hypokalemia was greater than 5%. The pooled DCR were 56.03% (95%CI = 45.03–67.03) and 64.38% (95%CI = 48.60–80.17) when the incidence rates of hypokalemia were 0%–5% and greater than 5%, respectively. The results of the subgroup analysis were consistent with the results of the whole population, except for not first-line treatment, which may have been confounded by malnutrition or poor quality of life in long-term survival. Conclusion: The efficacy of anti-EGFR targeted therapy was positively associated with the hypokalemia incidence rate. Treatment effects on the different serum potassium strata need to be considered in future clinical trials with targeted therapy.