Construction and verification of prediction model for Alzheimer's disease in diabetic patients

构建和验证糖尿病患者阿尔茨海默病预测模型

阅读:1

Abstract

OBJECTIVE: This study aimed to construct a prediction model for Alzheimer's disease (AD) in diabetic patients and evaluate its clinical application value. METHODS: A total of 322 patients was included and randomly divided into a training set (n=225) and a validation set (n=97) at a ratio of 7:3. Clinical characteristic data of the patients were collected. In the training set, univariate analysis and multivariate logistic regression analysis were used to identify the relevant risk factors for AD onset, and a nomogram prediction model was constructed accordingly. The receiver operating characteristic (ROC) curve and calibration curve were plotted and validated in an independent validation dataset. In addition, decision curve analysis (DCA) was used to further evaluate the application value and significance of the nomogram model in clinical practice. RESULTS: The incidence of AD in the training set was 18.67% (42/225), and that in the validation set was 18.56% (18/97). Multivariate regression analysis showed that age, duration of diabetes, fasting plasma glucose (FPG), glycosylated hemoglobin (HbA1c), triglyceride (TG), and homeostasis model assessment of insulin resistance (HOMA-IR) were all independent risk factors for AD onset (all P < 0.05). In the training set and validation set, the nomogram prediction model showed good predictive performance, with the concordance index (C-index) reaching 0.868 and 0.710 respectively. Calibration curve analysis showed a high degree of agreement between the predicted values and the observed values. The mean absolute errors in the training set and validation set were 0.103 and 0.116 respectively. The results of the Hosmer-Lemeshow test were χ² = 10.515, P = 0.230 and χ² = 5.987, P = 0.648 respectively. The ROC curve showed that the AUCs of the nomogram model for predicting occurrence of AD in the training set and validation set were 0.866 (95% CI: 0.794- 0.939) and 0.718 (95% CI: 0.517-0.920) respectively. CONCLUSION: The prediction model for AD in diabetic patients can assist in the early prediction of the risk of AD onset, laying a solid foundation for formulating effective clinical intervention strategies. This is crucial for delaying the progression of AD and significantly improving the quality of life of patients.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。