Nomogram and Carotid Risk Score for Predicting Moderate or High Carotid Atherosclerosis among Asymptomatic Elderly Recycling Volunteers

Development and validation of a carotid plaque risk prediction model for coal miners

Objective

Carotid plaque represents an independent risk factor for cardiovascular disease and a significant threat to human health. The aim of the study is to develop an accurate and interpretable predictive model for early detection the occurrence of carotid plaque.

Methods

A cross-sectional study was conducted by selecting coal miners who participated in medical examinations from October 2021 to January 2022 at a hospital in North China. The features were initially screened using extreme gradient boosting (XGBoost), random forest, and LASSO regression, and the model was subsequently constructed using logistic regression. The three models were then compared, and the optimum model was identified. Finally, a nomogram was plotted to increase its interpretability.

Results

The XGBoost algorithm demonstrated superior performance in feature screening, identifying the top five features as follows: age, systolic blood pressure, low-density lipoprotein cholesterol, white blood cell count, and body mass index (BMI). The area under the curve (AUC), sensitivity, and specificity of the model constructed based on the XGBoost algorithm were 0.846, 0.867, and 0.702, respectively.

Conclusions

It is possible to predict the presence of carotid plaque using machine learning. The model has high application value and can better predict the risk of carotid artery plaque in coal miners. Furthermore, it provides a theoretical basis for the health management of coal miners.

Usefulness of Atherogenic Indices for Predicting High Values of Avoidable Lost Life Years Heart Age in 139,634 Spanish Workers

BACKGROUND

Cardiovascular diseases (CVDs) are the leading cause of morbidity and mortality worldwide, accounting for one-third of all global deaths. The World Health Organization (WHO) asserts that prevention is the most effective strategy to combat CVD, emphasizing the need for non-invasive, low-cost tools to identify individuals at high risk of CVD. Atherogenic indices and heart age (HA) are valuable tools for assessing cardiovascular risk (CVR). The aim of our study was to evaluate the association between atherogenic indices and HA.

METHODS

A cross-sectional study was conducted involving 139,634 Spanish workers to determine the association between three atherogenic indices and HA. ROC curves were employed to identify the cut-off values for the various atherogenic indices used to estimate high HA. The cut-off points, along with their sensitivity, specificity, and Youden index, were determined, and the area under the curve (AUC) was calculated.

RESULTS

As the values of the atherogenic indices increased, so did the risk of having elevated avoidable lost life years (ALLY) HA. In the ROC curve analysis, the AUC with the best results corresponded to the total cholesterol/HDL-c atherogenic index, with an AUC of 0.803 in females and 0.790 in males. The LDL-c/HDL-c atherogenic index showed an AUC of 0.780 in women and 0.750 in men, with Youden indices around 0.4. When analyzing the AUC of the atherogenic index for triglycerides/HDL-c, the results were 0.760 in women and 0.746 in men.

CONCLUSIONS

Atherogenic indices and HA show a close relationship, with an increase in these indices leading to a rise in HA values. Raising patient awareness that as their CVR levels increase, so does their HA may be useful in achieving some benefit in reducing CVR.

Screening for carotid atherosclerosis: development and validation of a high-precision risk scoring tool

Objective

This study aimed to investigate the prevalence of carotid atherosclerosis (CAS), especially among seniors, and develop a precise risk assessment tool to facilitate screening and early intervention for high-risk individuals.

Methods

A comprehensive approach was employed, integrating traditional epidemiological methods with advanced machine learning techniques, including support vector machines, XGBoost, decision trees, random forests, and logistic regression.

Results

Among 1,515 participants, CAS prevalence reached 57.4%, concentrated within older individuals. Positive correlations were identified with age, systolic blood pressure, a history of hypertension, male gender, and total cholesterol. High-density lipoprotein (HDL) emerged as a protective factor against CAS, with total cholesterol and HDL levels proving significant predictors.

Conclusions

This research illuminates the risk factors linked to CAS and introduces a validated risk scoring tool, highlighted by the logistic classifier's consistent performance during training and testing. This tool shows potential for pinpointing high-risk individuals in community health programs, streamlining screening and intervention by clinical physicians. By stressing the significance of managing cholesterol levels, especially HDL, our findings provide actionable insights for CAS prevention. Nonetheless, rigorous validation is paramount to guarantee its practicality and efficacy in real-world scenarios.

Validity and Reliability of Point-of-Care Ultrasound for Detecting Moderate- or High-Grade Carotid Atherosclerosis in an Outpatient Department

The prevalence of carotid stenosis is considerably higher in asymptomatic individuals with multiple risk factors than in the general population. We investigated the validity and reliability of carotid point-of-care ultrasound (POCUS) for rapid carotid atherosclerosis screening. We prospectively enrolled asymptomatic individuals with carotid risk scores of ≥7 who underwent outpatient carotid POCUS and laboratory carotid sonography. Their simplified carotid plaque scores (sCPSs) and Handa's carotid plaque scores (hCPSs) were compared. Of 60 patients (median age, 81.9 years), 50% were diagnosed as having moderate- or high-grade carotid atherosclerosis. The overestimation and underestimation of outpatient sCPSs were more likely in patients with low and high laboratory-derived sCPSs, respectively. Bland-Altman plots indicated that the mean differences between the participants' outpatients and laboratory sCPSs were within two standard deviations of their laboratory sCPSs. A Spearman's rank correlation coefficient revealed a strong positive linear correlation between outpatient and laboratory sCPSs (r = 0.956, p < 0.001). An intraclass correlation coefficient analysis indicated excellent reliability between the two methods (0.954). Both carotid risk score and sCPS were positively and linearly correlated with laboratory hCPS. Our findings indicate that POCUS has satisfactory agreement, strong correlation, and excellent reliability with laboratory carotid sonography, making it suitable for rapid screening of carotid atherosclerosis in high-risk patients.

Predictive nomogram for coronary heart disease in patients with type 2 diabetes mellitus

Objective

This study aimed to identify risk factors for coronary heart disease (CHD) in patients with type 2 diabetes mellitus (T2DM), build a clinical prediction model, and draw a nomogram.

Study design and methods

Coronary angiography was performed for 1,808 diabetic patients who were recruited at the department of cardiology in The Second Affiliated Hospital of Nanchang University from June 2020 to June 2022. After applying exclusion criteria, 560 patients were finally enrolled in this study and randomly divided into training cohorts (n = 392) and validation cohorts (n = 168). The least absolute shrinkage and selection operator (LASSO) is used to filter features in the training dataset. Finally, we use logical regression to establish a prediction model for the selected features and draw a nomogram.

Results

The discrimination, calibration, and clinical usefulness of the prediction model were evaluated using the c-index, receiver operating characteristic (ROC) curve, calibration chart, and decision curve. The effects of gender, diabetes duration, non-high-density lipoprotein cholesterol, apolipoprotein A1, lipoprotein (a), homocysteine, atherogenic index of plasma (AIP), nerve conduction velocity, and carotid plaque merit further study. The C-index was 0.803 (0.759-0.847) in the training cohort and 0.775 (0.705-0.845) in the validation cohort. In the ROC curve, the Area Under Curve (AUC) of the training set is 0.802, and the AUC of the validation set is 0.753. The calibration curve showed no overfitting of the model. The decision curve analysis (DCA) demonstrated that the nomogram is effective in clinical practice.

Conclusion

Based on clinical information, we established a prediction model for CHD in patients with T2DM.