Background: The American Heart Association recently introduced the concept of cardiovascular-kidney-metabolic (CKM) syndrome, highlighting the increasing importance of the complex interplay between metabolic, renal, and cardiovascular diseases (CVD). While substantial evidence supports a correlation between the estimated glucose disposal rate (eGDR) and CVD events, its predictive value compared with other insulin resistance (IR) indices, such as triglyceride–glucose (TyG) index, TyG-waist circumference, TyG-body mass index, TyG-waist-to-height ratio, triglyceride-to-high density lipoprotein cholesterol ratio, and the metabolic score for insulin resistance, remains unclear. Methods: This prospective cohort study utilized data from the China Health and Retirement Longitudinal Study (CHARLS). The individuals were categorized into four subgroups based on the quartiles of eGDR. The associations between eGDR and incident CVD were evaluated using multivariate logistic regression analyses and restricted cubic spline. Seven machine learning models were utilized to assess the predictive value of the eGDR index for CVD events. To assess the model’s performance, we applied receiver operating characteristic (ROC) and precision-recall (PR) curves, calibration curves, and decision curve analysis. Results: A total of 4,950 participants (mean age: 73.46 ± 9.93 years), including 50.4% females, were enrolled in the study. During follow-up between 2011 and 2018, 697 (14.1%) participants developed CVD, including 486 (9.8%) with heart disease and 263 (5.3%) with stroke. The eGDR index outperformed six other IR indices in predicting CVD events, demonstrating a significant and linear relationship with all outcomes. Each 1-unit increase in eGDR was associated with a 14%, 14%, and 19% lower risk of CVD, heart disease, and stroke, respectively, in the fully adjusted model. The incorporation of the eGDR index into predictive models significantly improved prediction performance for CVD events, with the area under the ROC and PR curves equal to or exceeding 0.90 in both the training and testing sets. Conclusions: The eGDR index outperforms six other IR indices in predicting CVD, heart disease, and stroke in individuals with CKM syndrome stages 0–3. Its incorporation into predictive models enhances risk stratification and may aid in the early identification of high-risk individuals in this population. Further studies are needed to validate these findings in external cohorts. Graphical

While several indicators have been studied, the association of body roundness index (BRI) with non-alcoholic fatty liver disease (NAFLD) remains unclear. We aimed to explore the association between BRI and ultrasound-defined NAFLD. The sample dataset was extracted from the National Health and Nutrition Examination Survey (NHANES) during the period of 2017–2018. The diagnosis of NAFLD was determined based on the controlled attenuated parameter (CAP≥248 dB/m) score of liver ultrasound transient elastography (LUTE). Participants with excessive alcohol use and viral hepatitis were excluded. To delve deeper into the relationship, Multivariable logistic regression with adjustment for confounding variables and smoothing curve analysis was used to investigate the association and nonlinear relationships between BRI and NAFLD. Among 4210 individuals aged 20 years or older included in the study, 28.2 % had NAFLD. Compared to the first tertile, BRI notably increased the risk of NAFLD 3.53-fold [95 % confidence interval (CI) = 2.73–4.57] in the second tertile and 7.00-fold (95%CI = 5.29–9.27) in the third tertile after adjusting for multiple covariates (P for trend <0.001). Furthermore, when BRI was treated as a continuous variable, one unit of increment in BRI was associated with 41 % higher odds of NAFLD [adjusted odds ratio (aOR) = 1.41; 95%CI = 1.34–1.48; P < 0.001]. The associations of BRI with NAFLD persisted in all subgroup analyses. A smoothing curve fitting demonstrated that the relationship between BRI and NAFLD was a nonlinear connection. The risk of NAFLD increased significantly when BRI was lower than 4.82, after which the curve showed a modest ascent. Higher BRI was consistently associated with an increased risk of NAFLD in US adults. BRI is a risk factor for NAFLD, and there is an imperative to give more attention to lowering the BRI.

Background: Patients with alpha-fetoprotein (AFP)-positive hepatocellular carcinoma (HCC) have aggressive biological behavior and poor prognosis. Therefore, survival time is one of the greatest concerns for patients with AFP-positive HCC. This study aimed to demonstrate the utilization of six machine learning (ML)-based prognostic models to predict overall survival of patients with AFP-positive HCC. Methods: Data on patients with AFP-positive HCC were extracted from the Surveillance, Epidemiology, and End Results database. Six ML algorithms (extreme gradient boosting [XGBoost], logistic regression [LR], support vector machine [SVM], random forest [RF], K-nearest neighbor [KNN], and decision tree [ID3]) were used to develop the prognostic models of patients with AFP-positive HCC at one year, three years, and five years. Area under the receiver operating characteristic curve (AUC), confusion matrix, calibration curves, and decision curve analysis (DCA) were used to evaluate the model. Results: A total of 2,038 patients with AFP-positive HCC were included for analysis. The 1-, 3-, and 5-year overall survival rates were 60.7%, 28.9%, and 14.3%, respectively. Seventeen features regarding demographics and clinicopathology were included in six ML algorithms to generate a prognostic model. The XGBoost model showed the best performance in predicting survival at 1-year (train set: AUC = 0.771; test set: AUC = 0.782), 3-year (train set: AUC = 0.763; test set: AUC = 0.749) and 5-year (train set: AUC = 0.807; test set: AUC = 0.740). Furthermore, for 1-, 3-, and 5-year survival prediction, the accuracy in the training and test sets was 0.709 and 0.726, 0.721 and 0.726, and 0.778 and 0.784 for the XGBoost model, respectively. Calibration curves and DCA exhibited good predictive performance as well. Conclusions: The XGBoost model exhibited good predictive performance, which may provide physicians with an effective tool for early medical intervention and improve the survival of patients.

As non-alcoholic fatty liver disease (NAFLD) becomes increasingly common and affects population health, simple and effective screening tools for NAFLD are essential. The triglyceride high-density cholesterol-glucose body index (TyHGB), a novel metabolic index, has shown promise for predicting metabolic disorders. The objective of this research was to assess TyHGB’s predictive capability for NAFLD across two distinct cohorts. This retrospective study utilized data obtained from two independent cohorts: a Chinese hospital cohort (n = 181,241) and the National Health and Nutrition Examination Survey (NHANES) cohort (n = 3,286). TyHGB was computed according to the following equation: triglyceride level/high-density lipoprotein cholesterol level + 0.7 × fasting blood glucose level (mmol/L) + 0.1 × body mass index (kg/m²). NAFLD was diagnosed using ultrasonography. The TyHGB-NAFLD association was evaluated using multivariable logistic regression analysis, restricted cubic spline methodology, and receiver operating characteristic (ROC) curves. To establish the added predictive capacity of TyHGB over the triglyceride-glucose (TyG) index, net reclassification improvement (NRI) and integrated discrimination improvement (IDI) were determined. In both cohorts, participants with higher TyHGB values demonstrated a significantly higher prevalence of NAFLD. After full adjustment for potential confounders, the odds ratios for NAFLD on comparing the highest versus lowest quartiles of TyHGB were 12.22 (95% confidence interval [CI]: 10.73–13.93) in the Chinese cohort and 3.17 (95% CI: 2.25–4.46) in the NHANES cohort. Restricted cubic spline modeling demonstrated significant nonlinear associations between TyHGB values and NAFLD risk in both populations (P for nonlinearity < 0.001). TyHGB demonstrated superior discriminative ability for NAFLD in comparison with the TyG index, with area under the curve (AUC) values of 0.8410 versus 0.7995 in the Chinese cohort and 0.6492 versus 0.5952 in the NHANES cohort (both P < 0.001). Adding TyHGB to the baseline prediction models significantly improved risk discrimination, with greater improvements than those achieved by adding TyG (NRI: 0.0183, 95% CI: 0.015–0.0217; IDI: 0.0067, 95% CI: 0.0057–0.0076; both P < 0.001). TyHGB demonstrated robust and superior performance in predicting NAFLD in comparison with the established TyG index across two diverse populations. Since TyHGB only requires routinely measured clinical parameters, it represents a practical and equitable tool for early NAFLD risk stratification across diverse healthcare settings, potentially reducing health disparities in liver disease detection and enabling cost-effective prevention strategies at the population level.