Development and Internal Validation of a Risk Prediction Model for Carotid Atherosclerosis in the Hyperuricemia Population.

Purpose: The aim of this study was to identify independent risk factors for carotid atherosclerosis (CAS) in a population with hyperuricemia (HUA) and develop a CAS risk prediction model. Patients and Methods: This retrospective study included 3579 HUA individuals who underwent health examinations, including carotid ultrasonography, at the Zhenhai Lianhua Hospital in Ningbo, China, in 2020. All participants were randomly assigned to the training and internal validation sets in a 7:3 ratio. Multivariable logistic regression analysis was used to identify independent risk factors associated with CAS. The characteristic variables were screened using the least absolute shrinkage and selection operator combined with 10-fold cross-validation, and the resulting model was visualized by a nomogram. The discriminative ability, calibration, and clinical utility of the risk model were validated using the receiver operating characteristic curve, calibration curve, and decision curve analysis. Results: Sex, age, mean red blood cell volume, and fasting blood glucose were identified as independent risk factors for CAS in the HUA population. Age, gamma-glutamyl transpeptidase, serum creatinine, fasting blood glucose, total triiodothyronine, and direct bilirubin, were screened to construct a CAS risk prediction model. In the training and internal validation sets, the risk prediction model showed an excellent discriminative ability with the area under the curve of 0.891 and 0.901, respectively, and a high level of fit. Decision curve analysis results demonstrated that the risk prediction model could be beneficial when the threshold probabilities were 1-87% and 1-100% in the training and internal validation sets, respectively. Conclusion: We developed and internally validated a risk prediction model for CAS in a population with HUA, thereby contributing to the CAS early identification.

Predicting the risk of subclinical atherosclerosis based on interpretable machine models in a Chinese T2DM population.

Background: Cardiovascular disease (CVD) has emerged as a global public health concern. Identifying and preventing subclinical atherosclerosis (SCAS), an early indicator of CVD, is critical for improving cardiovascular outcomes. This study aimed to construct interpretable machine learning models for predicting SCAS risk in type 2 diabetes mellitus (T2DM) patients. Methods: This study included 3084 T2DM individuals who received health care at Zhenhai Lianhua Hospital, Ningbo, China, from January 2018 to December 2022. The least absolute shrinkage and selection operator combined with random forest-recursive feature elimination were used to screen for characteristic variables. Linear discriminant analysis, logistic regression, Naive Bayes, random forest, support vector machine, and extreme gradient boosting were employed in constructing risk prediction models for SCAS in T2DM patients. The area under the receiver operating characteristic curve (AUC) was employed to assess the predictive capacity of the model through 10-fold cross-validation. Additionally, the SHapley Additive exPlanations were utilized to interpret the best-performing model. Results: The percentage of SCAS was 38.46% (n=1186) in the study population. Fourteen variables, including age, white blood cell count, and basophil count, were identified as independent risk factors for SCAS. Nine predictors, including age, albumin, and total protein, were screened for the construction of risk prediction models. After validation, the random forest model exhibited the best clinical predictive value in the training set with an AUC of 0.729 (95% CI: 0.709-0.749), and it also demonstrated good predictive value in the internal validation set [AUC: 0.715 (95% CI: 0.688-0.742)]. The model interpretation revealed that age, albumin, total protein, total cholesterol, and serum creatinine were the top five variables contributing to the prediction model. Conclusion: The construction of SCAS risk models based on the Chinese T2DM population contributes to its early prevention and intervention, which would reduce the incidence of adverse cardiovascular prognostic events.

High free triiodothyronine, and free-triiodothyronine-to-free-thyroxine ratio are associated with metabolic syndrome in a euthyroid employee population: the Zhejiang Zhenhai study.

Objective: The aim of this study was to elaborate the link of thyroid hormones (THs) and metabolic syndrome (MetS) in a Chinese euthyroid employee population with MetS component(s). Methods: An annual health checkup was performed on employees in 2019. Anthropometric parameters, metabolic parameters, and thyroid function were measured. A questionnaire was used in conjunction with Zhenhai Lianhua Hospital database to receive employees' medication records and thyroid surgical history records. Results: A total of 5486 eligible employees were included; the prevalence of MetS was generally higher in males than in females (38.9 vs. 30.4%, P < 0.001). Among employees with central obesity, hypertriglyceridemia, hyperglycemia, hypertension, and low high-density lipoprotein cholesterol (HDL-C), the prevalence of MetS was 68.8, 63.6, 68.2, 48.8, and 60.0% in males and 72.6, 63.3, 61.3, 42.3, and 42.3% in females, respectively. Logistic regression analysis showed that thyroid-stimulating hormone and free thyroxine (FT4) quartiles had no significant impact on MetS. Free triiodothyronine/free thyroxine (FT3/FT4) and free triiodothyronine (FT3)) quartiles were positively associated with the increased odds ratio (OR) for MetS and dyslipidemia (hypertriglyceridemia and low HDL-C), regardless of gender. In males, FT3 and FT3/FT4 quartiles were positively associated with the OR for central obesity, whereas FT4 quartiles were negatively associated; both FT3 and FT4 quartiles were positively associated with increased OR of hyperglycemia, while similar results were not observed in females. Interaction analysis indicated no significant effect of gender and TH interactions on risk of MetS. Conclusion: High FT3 and FT3/FT4 were strongly linked with MetS and dyslipidemia in our study, even in the euthyroid individuals. Tighter control of thyroid function was necessary for those with preexisting MetS component(s).