Development and validation of a risk prediction model for frailty in patients with diabetes

Abstract

Background: Frailty is the third most common complication of diabetes after macrovascular and microvascular complications. The aim of this study was to develop a validated risk prediction model for frailty in patients with diabetes.

Methods: The research used data from the China Health and Retirement Longitudinal Study (CHARLS), a dataset representative of the Chinese population. Twenty-five indicators, including socio-demographic variables, behavioral factors, health status, and mental health parameters, were analyzed in this study. The study cohort was randomly divided into a training set and a validation set at a ratio of 70 to 30%. LASSO regression analysis was used to screen the variables for the best predictors of the model based on a 10-fold cross-validation. The logistic regression model was applied to explore the associated factors of frailty in patients with diabetes. A nomogram was constructed to develop the prediction model. Calibration curves were applied to evaluate the accuracy of the nomogram model. The area under the receiver operating characteristic curve and decision curve analysis were conducted to assess predictive performance.

Results: One thousand four hundred thirty-six patients with diabetes from the CHARLS database collected in 2013 (n = 793) and 2015 (n = 643) were included in the final analysis. A total of 145 (10.9%) had frailty symptoms. Multivariate logistic regression analysis showed that marital status, activities of daily living, waist circumference, cognitive function, grip strength, social activity, and depression as predictors of frailty in people with diabetes. These factors were used to construct the nomogram model, which showed good concordance and accuracy. The AUC values of the predictive model and the internal validation set were 0.912 (95%CI 0.887-0.937) and 0.881 (95% CI 0.829-0.934). Hosmer-Lemeshow test values were P = 0.824 and P = 0.608 (both > 0.05). Calibration curves showed significant agreement between the nomogram model and actual observations. ROC and DCA indicated that the nomogram had a good predictive performance.

Conclusions: Comprehensive nomogram constructed in this study was a promising and convenient tool to evaluate the risk of frailty in patients with diabetes, and contributed clinicians to screening the high-risk population.

Keywords: Diabetic patients; Diabetics; Frailty; Predictive model.

Fig. 1

Demographic and clinical feature selection using the LASSO regression model. A According to the logarithmic (lambda) sequence, a coefficient profile was generated, and non-zero coefficients were produced by the optimal lambda. B The optimal parameter (lambda) in the LASSO model was selected via tenfold cross-validation using minimum criteria. The partial likelihood deviation (binomial deviation) curve relative to log (lambda) was plotted. A virtual vertical line at the optimal value was drawn using one SE of minimum criterion (the 1-SE criterion)

Fig. 2

Nomogram

Fig. 3

A Nomogram ROC curves generated from the training dataset. B Nomogram ROC curves generated using the validation dataset

Fig. 4

A Calibration plot for the training dataset. B Calibration plot for the validation dataset

Fig. 5

A DCA curves for the training dataset. B DCA curves for the validation dataset