RESUMO
Background: Patients with diabetes are more likely to be predisposed to fractures compared to those without diabetes. In clinical practice, predicting fracture risk in diabetics is still difficult because of the limited availability and accessibility of existing fracture prediction tools in the diabetic population. The purpose of this study was to develop and validate models using machine learning (ML) algorithms to achieve high predictive power for fracture in patients with diabetes in China. Methods: In this study, the clinical data of 775 hospitalized patients with diabetes was analyzed by using Decision Tree (DT), Gradient Boosting Decision Tree (GBDT), Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost) and Probabilistic Classification Vector Machines (PCVM) algorithms to construct risk prediction models for fractures. Moreover, the risk factors for diabetes-related fracture were identified by the feature selection algorithms. Results: The ML algorithms extracted 17 most relevant factors from raw clinical data to maximize the accuracy of the prediction results, including bone mineral density, age, sex, weight, high-density lipoprotein cholesterol, height, duration of diabetes, total cholesterol, osteocalcin, N-terminal propeptide of type I, diastolic blood pressure, and body mass index. The 7 ML models including LR, SVM, RF, DT, GBDT, XGBoost, and PCVM had f1 scores of 0.75, 0.83, 0.84, 0.85, 0.87, 0.88, and 0.97, respectively. Conclusions: This study identified 17 most relevant risk factors for diabetes-related fracture using ML algorithms. And the PCVM model proved to perform best in predicting the fracture risk in the diabetic population. This work proposes a cheap, safe, and extensible ML algorithm for the precise assessment of risk factors for diabetes-related fracture.
RESUMO
A variety of studies have demonstrated the role of lipocalin 2 (LCN2) in both diabetes and neurological disorders. Nevertheless, the relationship between LCN2 and diabetic peripheral neuropathy (DPN) needs to be elucidated in humans. Therefore, this study aimed to investigate the association of LCN2 with DPN in type 2 diabetes (T2D). A total of 207 participants with T2D and 40 participants with normal glucose tolerance (NGT) were included in this study. All participants were classified into DPN group and non-DPN (NDPN) group based on the Toronto Clinical Neuropathy Scoring (TCNS). Demographic and biochemical parameters were measured. Serum LCN2 levels were determined using an ELISA technique. Serum LCN2 levels in NGT group were lower than those in either DPN group (P = 0.000) or NDPN group (P = 0.043), while serum LCN2 levels in DPN group were higher than NDPN group (P = 0.001). Moreover, serum LCN2 levels positively correlated to TCNS scores, which reflects neuropathy severity (r = 0.438, P = 0.000). Multivariate stepwise regression analysis showed that BMI, triglycerides, and diastolic pressure were independently associated with serum LCN2 in DPN. Additionally, logistic regression analysis demonstrated that LCN2 (odds ratio (OR) = 1.009) and diabetes duration (OR = 1.058) were independently associated with the occurrence of DPN in T2D. Our report reveals the association of serum LCN2 with DPN in T2D. LCN2 might be used to evaluate DPN severity and serve a role in the pathogenesis of DPN.