Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis  

作　　者：Yaxin Chen Tianyi Yang Xiaofeng Gao Ajing Xu 

机构地区：[1]Department of Pharmacy,Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine,Shanghai 200240,China [2]Shanghai Key Laboratory of Scalable Computing and Systems,Department of Computer Science and Engineering,Shanghai Jiao Tong University,Shanghai 200240,China [3]Clinical Research Unit,Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine,Shanghai 200240,China

出　　处：《Frontiers of Medicine》2022年第3期496-506,共11页医学前沿（英文版）

基　　金：supported by the National Key R&D Program of China(Nos.2020YFC2005502 and 2018YFB 1004700);the National Natural Science Foundation of China(Nos,6187238 and 61972254);the Science and Technology Commission of Shanghai Municipality No.19401900500)the Innovation Program of Shanghai Health Commission(Nos.201840121 and ZY(2018-2020)-ZWB-1001-CPJS1);the CCF-Huawei Database System Innovation Research Plan(No.CCF-Huawei DBIR2019002A);and the program of Hospital Clinical Research,Xinhua Hospital Afiliated to Shanghai Jiao Tong University School of Medicine(No.19XHCR11C).

摘　　要：The fracture risk of patients with diabetes is higher than those of patients without diabetes due to hyperglycemia,usage of diabetes drugs,changes in insulin levels,and excretion,and this risk begins as early as adolescence.Many factors including demographic data(such as age,height,weight,and gender),medical history(such as smoking,drinking,and menopause),and examination(such as bone mineral density,blood routine,and urine routine)may be related to bone metabolism in patients with diabetes.However,most of the existing methods are qualitative assessments and do not consider the interactions of the physiological factors of humans.In addition,the fracture risk of patients with diabetes and osteoporosis has not been further studied previously.In this paper,a hybrid model combining XGBoost with deep neural network is used to predict the fracture risk of patients with diabetes and osteoporosis,and investigate the effect of patients’physiological factors on fracture risk.A total of 147 raw input features are considered in our model.The presented model is compared with several benchmarks based on various metrics to prove its effectiveness.Moreover,the top 18 influencing factors of fracture risks of patients with diabetes are determined.

关 键 词：XGBoost deep neural network healthcare risk prediction 

分 类 号：R587.1[医药卫生—内分泌] R68[医药卫生—内科学]