Abstract:Objective To analyze the predictive value of serum epidermal growth factor receptor (EGFR) and E-cadherin in predicting treatment response to neoadjuvant chemotherapy for breast cancer.Methods A total of 151 breast cancer patients admitted to the Third People's Hospital of Mianyang City from January 2020 to March 2023 undergoing neoadjuvant chemotherapy were included. Multivariable stepwise logistic regression was used to analyze the influencing factors, and the receiver operating characteristic (ROC) curve was used to verify the diagnostic efficacy.Results The proportion of stage II tumors and the level of E-cadherin in the pCR group were higher than those in the non-pCR group, while the proportion of KI-67 antigen expression ≥30% and the levels of CEA and EGFR were lower in the pCR group than in the non-pCR group. Multivariable stepwise logistic regression analysis showed that stage III tumors [O^R = 4.899 (95% CI: 2.016, 11.909) ], high EGFR levels [O^R = 3.904 (95% CI: 1.594, 9.563) ], and low E-cadherin levels [O^R = 0.308 (95% CI: 0.127, 0.748) ] were all risk factors for incomplete response to neoadjuvant chemotherapy in breast cancer patients (P < 0.05). ROC curve analysis revealed that the sensitivities of EGFR, E-cadherin, and the combined model for predicting incomplete response to neoadjuvant chemotherapy were 69.44% (95% CI: 0.517, 0.831), 72.2% (95% CI: 0.546, 0.852), and 83.33% (95% CI: 0.665, 0.930), respectively, with corresponding specificities being 75.65% (95% CI: 0.666, 0.830), 70.43% (95% CI: 0.611, 0.784), and 88.69% (95% CI: 0.811, 0.936), respectively, and the areas under the curves being 0.722 (95% CI: 0.609, 0.834), 0.726 (95% CI: 0.629, 0.822), and 0.896 (95% CI: 0.826, 0.966), respectively.Conclusion Combined detection of serum EGFR and E-cadherin can improve the predictive performance for the efficacy of neoadjuvant chemotherapy in breast cancer.