Objective: To explore the application value of ALP, tumor markers (CEA, CA125, CA153, CYFRA21-1) and immune-inflammatory indicators(NLR, PLR, LMR, SII, SIRI) in predicting the risk of breast cancer bone metastasis. Methods: A total of 150 patients with breast cancer who were newly diagnosed at Sun Yat-sen Memorial Hospital of Sun Yat-sen University from October 2016 to October 2020 were included,including 50 patients with bone metastasis and 100 patients without bone metastasis.Clinical data and test results of serum ALP, serum tumor markers (CEA, CA125, CA153, CYFRA21-1), and peripheral blood immune-inflammatory indicators (NLR, PLR, LMR, SII, SIRI) were collected before treatment. The differences in clinical data and various indicators were compared between patients with and without bone metastasis.Spearman correlation analysis was conducted to evaluate the correlation between each indicator and the grade of bone metastasis in breast cancer.Logistic regression analysis was performed to identify effective indicators for predicting bone metastasis in breast cancer,and the predictive value of each indicator was assessed using ROC curves. Results: There were significant statistical differences (P<0.05) in histological classification, tumor size, lymph node metastasis, and visceral metastasis between the breast cancer patients with and without bone metastasis. The levels of ALP, CEA, CA125, CA153, CYFRA21-1, NLR, PLR, SII and SIRI in the breast cancer bone metastasis group were significantly higher than those in the non-bone metastasis group, while the level of LMR was significantly lower than that in the non-bone metastasis group, and all differences were statistically significant(P<0.05).The levels of ALP, CEA, CA125, CA153, CYFRA21-1, NLR, PLR, SII, and SIRI were positively correlated with the grade of bone metastasis in breast cancer (P<0.05). Conversely, the level of LMR was negatively correlated with the grade of bone metastasis in breast cancer (P<0.05).Visceral metastasis, elevated levels of ALP, CEA, CYFRA21-1, and NLR were identified as risk factors for bone metastasis in breast cancer.The areas under the ROC curves of ALP, CEA,CYFRA21-1 and NLR were 0.824,0.746,0.845 and 0.718, respectively. The combined detection of these four indicators had an AUC of 0.915, which was higher than any individual indicator, with a sensitivity and specificity of 78.0% and 89.0%, respectively. Conclusion: The combined detection of serum ALP, CEA, CYFRA21-1, and peripheral blood NLR has significant application value in predicting the risk of breast cancer bone metastasis,which can aid in the early detection and evaluation of bone metastasis in breast cancer patients.