Commentary
The aim of this retrospective cohort study was to develop a risk nomogram for NAFLD in a Chinese population with T2DM. A questionnaire survey, physical examination and biochemical indicator testing were performed on 874 patients with T2DM.
A total of nine predictors, namely sex, age, total cholesterol, body mass index, waistline, diastolic blood pressure, serum uric acid, course of disease and high-density lipoprotein-cholesterol, were identified regression analysis from a total of 24 variables studied. The prediction model was established using LASSO regression, logistic regression, and a newly developed risk nomogram. The LASSO regression analysis minimizes prediction error for a quantitative response variable by imposing a constraint on the model parameters that cause the regression coefficients for some variables to shrink toward zero.
This nomogram of NAFLD was validated, and the results were also verified by external verification methods (including ROC, C-INDEX, DCA), with good results.
