Abstract:Objective:Based on the quantitative parameters of multimodal ultrasound, a prediction model was established, and the predictive value of the prediction model for axillary lymph node pathological complete remission (pCR) after neoadjuvant chemotherapy (NAC) for breast cancer was analyzed.Methods:150 breast cancer patients who underwent NAC in our hospital from January, 2020 to December, 2022 were divided into pCR group (43 cases) and non-pCR group (107 cases) according to whether axillary lymph nodes were pCR. The risk factors of axillary pCR in breast cancer patients after NAC were analyzed, and the prediction model of axillary pCR in breast cancer patients after NAC was constructed. Hosmer-Lemeshow was used to test the fitting degree of the model, and the value of the prediction model was analyzed by the receiver"s working characteristics (ROC) curve.Result:There was no significant difference in age, pathological type, clinical stage, cT stage, axillary lymph node metastasis rate, family history rate of breast cancer, Ki67 index, menopause rate and neoadjuvant chemotherapy scheme between the two groups (P<0.05), but there was significant difference in molecular classification and lymph node size between the two groups (P< 0.05). The change rate of RI, PSV, PI and longest diameter in pCR group was significantly higher than that in non-pCR group (P<0.05), and the elasticity score in pCR group was significantly lower than that in non-pCR group (P<0.05). Multivariate binary Logistic analysis showed that high RI was a risk factor for axillary pCR in breast cancer patients after NAC (P<0.05), and high elasticity score was a protective factor for axillary pCR in breast cancer patients after NAC (P<0.05). Hosmer-Lemeshow test shows that χ2=6.966, P=0.540, and the model has a good goodness of fit. The curve analysis of receiver"s operating characteristics (ROC) shows that the AUC of the risk model of axillary pCR for breast cancer patients after NAC is 0.858, the Jordan index is 0.716, the sensitivity and specificity are 74.42% and 97.206% respectively, and the accuracy of practical application is 90.67%.Conclusion:In this study, the prediction model of axillary pCR for breast cancer patients after NAC based on multimodal ultrasound quantitative parameters is effective.