We previously reported that a patient’s smoking status was an independent predictor of progression-free survival (PFS) in gefitinib and erlotinib therapy for patients with non-small cell lung cancer (NSCLC) harboring EGFR mutations. However, other indicators that can elaborate on the clinical efficacy to the EGFR-TKI therapy remain understudied. The inflammatory indicator neutrophil-to-lymphocyte ratio (NLR) in peripheral blood serves as a predictive factor for NSCLC patients treated with anti-cancer agents such as cytotoxic drugs and PD-1 inhibitors. Here, we aimed to evaluate the correlation between NLR and clinical efficacy of EGFR-TKIs in NSCLC patients harboring EGFR mutations. We retrospectively collected information of 205 patients with advanced NSCLC harboring exon 19 deletion or L858R point mutation and receiving gefitinib or erlotinib, between March 2009 and June 2016, were enrolled. The date cut-off date was March 2019. The clinical outcomes in the NSCLC patients were evaluated based on NLR level before EGFR-TKI therapy. Variables (including gender, age, performance status [PS], NLR, EGFR genotype, smoking status, clinical stage prior to EGFR-TKI treatment [Stage IV vs. postoperative recurrence], the presence or absence of brain metastases, type of EGFR-TKI [gefitinib vs. erlotinib]) were entered into a Cox proportional hazards regression model to estimate the hazards ratios for PFS and overall survival (OS). We used PFS longer or shorter than 10 months as the binary variables for ROC curves. The patient cohort comprised of 60% women, with 70 years median age, and 65% of good PS. An optimal cut-off value of 3.55 was chosen for NLR, with an area under the curve (AUC) value of 0.67 [95% confidence interval (CI): 0.59–0.74, P < 0.0001]. The response rates in the low-NLR and high-NLR groups were 69.2% (95% CI: 60.3–78.1%) and 51.5% (95% CI: 41.8–61.2%). In addition, the mean values of NLR in responders (patients with partial response) and non-responders (patients with stable disease or progressive disease) were 4.8 and 11.3 respectively, indicating a significant difference (P = 0.021). A median follow-up period for the survival analysis was 25.2 months. The median PFS and OS of all the patients together were 10.8 months (95% CI: 8.8– 12.8 months) and 28.0 months (95% CI: 23.5– 32.5 months). The median PFS in the low-NLR and high-NLR groups were 15.7 months (95% CI: 12.7–18.7 months) and 6.7 months (95% CI: 4.6–8.8 months). The median OS in the low-NLR and high-NLR groups were 37.6 months (95% CI: 30.3–44.9 months) and 19.2 months (95% CI: 10.6–27.8 months). The multivariate analysis identified PS, NLR, stage, and smoking status as independent predictors of PFS. Moreover, the PS and NLR were identified as independent predictors of OS. NLR was a significant predictor of clinical efficacy in NSCLC patients harboring EGFR mutations treated with gefitinib or erlotinib.