AUTHOR=Ji Lichen , Zhang Wei , Zhong Xugang , Zhao Tingxiao , Sun Xixi , Zhu Senbo , Tong Yu , Luo Junchao , Xu Youjia , Yang Di , Kang Yao , Wang Jin , Bi Qing 

TITLE=Osteoporosis, fracture and survival: Application of machine learning in breast cancer prediction models

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.973307

DOI=10.3389/fonc.2022.973307

ISSN=2234-943X

ABSTRACT=The risk of osteoporosis in breast cancer patients is higher than that in healthy populations. The fracture and death rates increase after they are diagnosed with osteoporosis. We aimed to develop machine learning-based models to predict the risk of osteoporosis as well as the relative fracture occurrence and prognosis. We selected 749 breast cancer patients from two independent Chinese center and applied six different methods of machine learning to develop osteoporosis, fracture and survival risk assessment models. The performance of the models was compared with current models, such as the FRAX，OSTA and TNM, by applying ROC, DCA curve analysis, and the calculation of accuracy and sensitivity in both internal and independent external cohorts. Three models were developed. The XGB model demonstrated the best discriminatory performance among the models. Internal validation and external validation revealed that the AUC of the model was 0.86 and 0.87 in osteoporosis model, compared with the FRAX model score (0.84 and 0.72)/OSTA model score (0.77 and 0.66). The fracture model had a high AUC in the internal and external cohorts of 0.93 and 0.92, which was higher than the FRAX model score (0.89 and 0.86). The survival model was also assessed and showed high reliability via internal and external validation (AUC of 0.96 and 0.95), which was better than that of the TNM model (AUC of 0.87 and 0.87). Our models offer a solid approach to help improve decision making.