Disease's type
GDM
Experimental grouping
Training dataset:GDM(n=204),Normal Glucose Tolerance(n=620) and validation dataset: GDM(n=196),Normal Glucose Tolerance(n=196)
GPT's summary
The study developed and validated a nomogram using LASSO logistic regression and multivariate ROC risk analysis to predict GDM risk factors in early pregnancy. Data from 824 pregnant women formed the training dataset, while 392 women's data served as the validation set. Five significant predictors were identified: age, BUN, FAR, BUN/Cr, and BUN/ALB. Evaluation through ROC, C-index, calibration, and DCA showed that the nomogram has strong predictive power and can be used clinically for early GDM risk assessment and intervention.
RF's name
Fibrinogen to Albumin ratio
Sample's type
Serum
Gestational weeks
12th to 16th gestational weeks
Experiemental methods
Clot-Based Method
Machine learning algorithms
Logistic Regression
Title
Establishment and validation of a predictive nomogram for gestational diabetes mellitus during early pregnancy term: A retrospective study
Evidence's type
Risk factor
Year
2023
Journal
Frontiers in Endocrinology
PMID