Page 59 - GHR_NursingCMU2024_Final.indd

Construction and Validation of Risk Prediction Model for Impaired Fasting Blood
Glucose Based on Nomogram

L. Liu 1

School of Nursing, Liaoning University of Traditional Chinese Medicine, China
1

Background: Impaired fasting blood glucose (IFG) is a high-risk group of diabetes. Early
identification of it can prevent or delay the occurrence of diabetes.The prediction model can
comprehensively evaluate the risk factors of IFG, so as to predict the risk probability of IFG.This study
help to screen high-risk groups of IFG, provide evidence for IFG intervention.

Objective: To explore the risk factors of impaired fasting blood glucose, construct and validate a risk
prediction model.

Methods: A retrospective study was conducted on 3 037 individuals who underwent routine physical
examinations at a tertiary hospital in Shenyang from August to December 2023. The population was
randomly divided into a training group (n=2 126) and a validation group (n=911) by a 7:3 ratio, and
Oral Presentation Abstracts
their physical examination data were collected. Using Lasso regression analysis to screen predictive
variables, logistic regression analysis was used to further screen and construct a column chart
predictive model. The validation group conducted internal validation on the feasibility of the model,
and the area under the ROC curve (AUC) and Goodness of fit tests were used to evaluate the
effectiveness of the model.

Results: Among the 3037 individuals, 2880 did not experience IFG and 157 did. The results showed
that age [OR=1.04, 95%CI(1.02, 1.05)] , body mass index[OR=1.10, 95%CI(1.05, 1.17)], systolic blood
pressure[OR=1.01, 95%CI(1.00, 1.03)], triglycerides[OR=1.22, 95%CI(0.99, 1.51)], and a history of
hypertension[OR=1.58, 95%CI(0.86, 2.88)] were independent risk factors. In the training group, the
prediction model predicted an AUC of 0.722 [ 95%CI(0.68, 0.77)], while in the validation group, the
prediction model predicted an AUC of 0.907 [95%CI(0.87, 0.94)]. The results of Hosmer Lemeshow
Goodness of fit test show that the model calibration is good.

Conclusion: This study constructed a risk prediction model for impaired fasting blood glucose
occurrence, which includes five variables: age, BMI, SBP, TG, and history of hypertension. This model
helps to identify high-risk groups of impaired fasting blood glucose.

Keywords: impaired fasting blood glucose, lasso regression, nomogram, prediction model, risk
factors

_____________________________________________________________________________________________________
Correspondence: Lei Liu, School of Nursing, Liaoning University of Traditional Chinese Medicine, China
E-mail: liulei0428@sina.com

57