Association between the triglyceride to high-density lipoprotein cholesterol ratio and diabetes mellitus likelihood in patients with chronic kidney disease

Abstract

Background: Patients with chronic kidney disease (CKD) are at an increased risk of diabetes mellitus (DM) and dyslipidemia, yet the specific relationship between lipid profiles, particularly triglyceride-to-high-density lipoprotein cholesterol ratio (TG/HDL-C ratio), and DM likelihood in this population has not been thoroughly elucidated.

Methods: We conducted a cross-sectional analysis of 20,310 unselected patients with CKD enrolled from 2006 to 2015. The relationship between the TG/HDL-C ratio and the likelihood of DM was evaluated using binary logistic regression. Sensitivity and subgroup analyses were performed, and a generalized additive model with smooth curve fitting assessed potential non-linear associations. We also performed the receiver operating characteristic (ROC) curve and decision curve analysis to assess the determination and clinical use, respectively.

Results: Among the participants (mean age 60.907 ± 10.044 years; 79.580% male), 1,758 (8.656%) had DM. The median TG/HDL-C ratio was 0.655(interquartile range 0.465-0.920). After adjusting for covariates, a significant positive association was found between the TG/HDL-C ratio and DM likelihood (odds ratio [OR], 1.494; 95% confidence interval [CI], 1.354-1.648; P < 0.001). A non-linear relationship was observed with an inflection point at a TG/HDL-C ratio of 1.030. The ORs below and above this point were 1.866 (95% CI, 1.472-2.365) and 1.297 (95% CI, 1.094-1.538), respectively. The area under curve (AUC) of the nomogram was of 0.580 (95% CI, 0.566-0.594). Subgroup analyses indicated a stronger association in patients without hypertension, in female and patients with AF.

Conclusion: The TG/HDL-C ratio is independently associated with DM likelihood in patients with CKD, exhibiting a non-linear relationship particularly significant when the ratio is below 1.030. The TG/HDL-C ratio may serve as a useful marker for DM likelihood assessment in CKD patients, though prospective studies are needed to determine its role in prevention strategies.

Clinical trial number: Not applicable.

Keywords: Chronic kidney disease; Cross-sectional study; Diabetes; Non-linear; Triglyceride to high-density lipoprotein cholesterol ratio.

Fig. 1

Flowchart of study participants. Showed the inclusion of participants. 101,150 participants were assessed for eligibility in the original study. We excluded participants less than 45 years old (N = 22512), eGFR ≥ 60mL/min per 1.73 m2 and proteinuria negative(N = 56379), missing or invalid baseline data (N = 630), previous dialysis or transplant(N = 42), missed TG (n = 288), missed HDL-C (n = 2), missed DM related data (n = 563), unreasonable abnormal values of TG /HDL-C (n = 424). The final analysis included 20310subjects in the present study

Fig. 2

The non-linear relationship between TG/HDL-C ratio and DM. Illustrates the non-linear relationship between TG/HDL-C ratio and diabetes mellitus risk using generalized additive model (GAM) with smooth curve fitting. The solid line represents the fitted smooth curve with 95% confidence intervals (shaded area). The analysis identified an inflection point at TG/HDL-C ratio = 1.03, demonstrating a steeper association below this threshold (OR = 1.866, 95% CI: 1.472–2.365) compared to a more moderate association above this point (OR = 1.297, 95% CI: 1.094–1.538). The model was adjusted for age, gender, WC, history of alcohol intake, smoking, education, hypertension, AF, MI, congestive heart failure, PAD, DBP, SBP, CRP, LDL-C

Fig. 3

Receiver Operating Characteristic (ROC) Curve Analysis for TG/HDL-C Ratio in Predicting Diabetes Mellitus. ROC curve for the TG/HDL-Cratio in predicting diabetes mellitus among patients with chronic kidney disease (n = 20,310). The area under the curve (AUC) was 0.58 (95% CI: 0.566–0.594), indicating moderate discriminatory performance for diabetes prediction

Fig. 4

Decision curve analysis for the TG/HDL-C ratio model in predicting DM odds. Decision curve analysis evaluating the clinical utility of the TG/HDL-C ratio model for diabetes prediction in chronic kidney disease patients. The red line represents the TG/HDL-C ratio model, the grey line represents the “treat all” strategy, and the black line represents the “treat none” strategy. The y-axis shows the standardized net benefit, and the x-axis shows the high-risk threshold probabilities. The model demonstrates superior net benefit compared to both reference strategies across risk thresholds from 0.02 to 0.35, indicating clinical utility for diabetes odds prediction in this population