Purpose The neutrophil-to-lymphocyte ratio (NLR) is an emerging biomarker for predicting febrile neutropenia (FN) in cancer patients. This study aimed to evaluate the association between pre-treatment NLR and the risk of FN in breast and ovarian cancer patients.Methods In this prospective study, 130 patients (109 breast, 21 ovarian) were analyzed. Pre-treatment NLR was measured, and the optimal cutoff was determined using receiver operating characteristic (ROC) curve analysis. Clinical and pathological variables, including age, body surface area (BSA), chemotherapy regimen, cancer type, and stage, were assessed using univariate analyses.Results ROC analysis showed an area under the curve (AUC) of 0.628 (95% CI 0.511–0.746) for NLR. An NLR cutoff ≥ 2.1 demonstrated a sensitivity of 72.7%, specificity of 50%, positive predictive value of 27.9%, and a negative predictive value of 90%. Baseline NLR ≥ 2.1 was associated with increased odds of FN (OR 2.67, 95% CI 0.97–7.33, p = 0.057); meanwhile, age, BSA, cancer stage, cancer type, and chemotherapy regimen were not significantly associated with FN.Conclusion Pre-treatment NLR ≥ 2.1 demonstrates moderate discriminatory ability for predicting febrile neutropenia, although the association was not statistically significant. These findings suggest NLR may serve as a supportive predictive marker, warranting further validation in larger cohorts.