fig3

Figure 3. Logistic regression nomogram and calibration. (A) Nomogram for predicting CKM multimorbidity risk in Chinese adults with overweight and obesity incorporating 9 selected predictors; (B) Calibration curve of the logistic regression model in the training and testing sets. The Hosmer-Lemeshow test indicated good calibration. For the categorical variables, the following codings were used: depression (0 = no, 1 = yes), pain (0 = no, 1 = yes), dyslipidemia (0 = no, 1 = yes), hypertension (0 = no, 1 = yes), heart disease (0 = no, 1 = yes), kidney disease (0 = no, 1 = yes), health expectation (1 = almost impossible, 2 = not very likely, 3 = maybe, 4 = very likely, 5 = almost certain), and weight change (1 = Don’t know, 2 = No, 3 = Yes, first gained and then lost weight, 4 = Yes, first lost and then gained weight, 5 = Yes, only gained weight, 6 = Yes, only lost weight). CKM: Cardiovascular-kidney-metabolic; df: degrees of freedom.