Predictive validity of the risk SCORE model in a Mediterranean population with dyslipidemia

Machine learning model for cardiovascular disease prediction in patients with chronic kidney disease

Introduction

Cardiovascular disease (CVD) is the leading cause of death in patients with chronic kidney disease (CKD). This study aimed to develop CVD risk prediction models using machine learning to support clinical decision making and improve patient prognosis.

Methods

Electronic medical records from patients with CKD at a single center from 2015 to 2020 were used to develop machine learning models for the prediction of CVD. Least absolute shrinkage and selection operator (LASSO) regression was used to select important features predicting the risk of developing CVD. Seven machine learning classification algorithms were used to build models, which were evaluated by receiver operating characteristic curves, accuracy, sensitivity, specificity, and F1-score, and Shapley Additive explanations was used to interpret the model results. CVD was defined as composite cardiovascular events including coronary heart disease (coronary artery disease, myocardial infarction, angina pectoris, and coronary artery revascularization), cerebrovascular disease (hemorrhagic stroke and ischemic stroke), deaths from all causes (cardiovascular deaths, non-cardiovascular deaths, unknown cause of death), congestive heart failure, and peripheral artery disease (aortic aneurysm, aortic or other peripheral arterial revascularization). A cardiovascular event was a composite outcome of multiple cardiovascular events, as determined by reviewing medical records.

Results

This study included 8,894 patients with CKD, with a composite CVD event incidence of 25.9%; a total of 2,304 patients reached this outcome. LASSO regression identified eight important features for predicting the risk of CKD developing into CVD: age, history of hypertension, sex, antiplatelet drugs, high-density lipoprotein, sodium ions, 24-h urinary protein, and estimated glomerular filtration rate. The model developed using Extreme Gradient Boosting in the test set had an area under the curve of 0.89, outperforming the other models, indicating that it had the best CVD predictive performance.

Conclusion

This study established a CVD risk prediction model for patients with CKD, based on routine clinical diagnostic and treatment data, with good predictive accuracy. This model is expected to provide a scientific basis for the management and treatment of patients with CKD.

[Predictive validity of the risk SCORE model in a Mediterranean population with arterial hypertension]

INTRODUCTION AND OBJECTIVES

Hypertension is the most prevalent risk factor globally. Calculation of cardiovascular risk in hypertensive patients before initiation of treatment is recommended. This study aimed to assess the predictive value and clinical utility of the SCORE scale in preventing cardiovascular events and all-cause mortality in patients with hypertension.

METHODS

Patients with hypertension from the ESCARVAL-RISK cohort were included. Cardiovascular risk was calculated using the SCORE scale. All deaths and cardiovascular events were recorded during a 5-year follow-up period. Sensitivity, specificity and predictive values were calculated for different cut-off points and the effect of different risk factors on the diagnostic accuracy of SCORE charts were assessed.

RESULTS

In a final cohort of 9834 patients, there were 555 cardiovascular events and 69 deaths. The recommended risk value for initiating drug treatment (5%) had a specificity of 92% for death and 91% for cardiovascular events, and a sensitivity of 20% for death and 22% for cardiovascular events. In addition, the scale classified 80.4% of patients who experienced a cardiovascular event and 78.3% of those who died as low risk. Age, body mass index, retinopathy and anticoagulant therapy were associated with reduced predictive ability of the SCORE scale, while being female was associated with better risk prediction.

CONCLUSIONS

The predictive ability of the SCORE scale for cardiovascular disease and total mortality in patients with hypertension is limited.

High sensitivity troponins: A potential biomarkers of cardiovascular risk for primary prevention

There have been several approaches to building charts for CV risk, all of which have both strengths and limitations. Identifying early organ damage provides relevant information and should be included in risk charts, although the direct relationship with risk is imprecise, variability between operators at the time to assess, and low availability in some healthcare systems, limits its use. Biomarkers, like troponin (cTns) isoforms cTnI and cTnT, a cardiac specific myocyte injury marker, have the great advantage of being relatively reproducible, more readily accessible, and applicable to different populations. New and improved troponin assays have good analytical performance, can measure very low levels of circulating troponin, and have low intra individual variation, below 10 %. Several studies have analyzed the blood levels in healthy subjects and their predictive value for cardiovascular events in observational, prospective and post-hoc studies. All of them offered relevant information and shown that high sensitivity hs-cTnI has a place as an additional clinical marker to add to current charts, and it also reflects sex- and age-dependent differences. Although few more questions need to be answered before recommend cTnI for assessing CV risk in primary prevention, seems to be a potential strong marker to complement CV risk charts.

Gender Differences in the Diagnosis of Dyslipidemia: ESCARVAL-GENERO

Evidence shows that objectives for detecting and controlling dyslipidemia are not being effectively met, and outcomes differ between men and women. This study aimed to assess gender-related differences in diagnostic inertia around dyslipidemia. This ambispective, epidemiological, cohort registry study included adults who presented to public primary health care centers in a Spanish region from 2008 to 2012, with dyslipidemia and without cardiovascular disease. Diagnostic inertia was defined as the registry of abnormal diagnostic parameters-but no diagnosis-on the person's health record in a window of six months from inclusion. A total of 58,970 patients were included (53.7% women) with a mean age of 58.4 years in women and 57.9 years in men. The 6358 (20.1%) women and 4312 (15.8%) men presenting diagnostic inertia had a similar profile, although in women the magnitude of the association with younger age was larger. Hypertension showed a larger association with diagnostic inertia in women than in men (prevalence ratio 1.81 vs. 1.56). The overall prevalence of diagnostic inertia in dyslipidemia is high, especially in women. Both men and women have a higher risk of cardiovascular morbidity and mortality.

Circulating Amyloid Beta 1-40 Is Associated with Increased Rate of Progression of Atherosclerosis in Menopause: A Prospective Cohort Study

BACKGROUND

 Accumulating evidence suggests that circulating amyloidβ 1-40 (Αβ1-40), a proatherogenic aging peptide, may serve as a novel biomarker in cardiovascular disease (CVD). We aimed to explore the role of plasma Αβ1-40 and its patterns of change over time in atherosclerosis progression in postmenopausal women, a population with substantial unrecognized CVD risk beyond traditional risk factors (TRFs).

METHODS

 In this prospective study, Αβ1-40 was measured in plasma by enzyme-linked immunosorbent assay and atherosclerosis was assessed using carotid high-resolution ultrasonography at baseline and after a median follow-up of 28.2 months in 152 postmenopausal women without history or symptoms of CVD.

RESULTS

 At baseline, high Αβ1-40 was independently associated with higher carotid bulb intima-media thickness (cbIMT) and the sum of maximal wall thickness in all carotid sites (sumWT) (p < 0.05). Αβ1-40 levels increased over time and were associated with decreasing renal function (p < 0.05 for both). Women with a pattern of increasing or persistently high Αβ1-40 levels presented accelerated progression of cbIMT and maximum carotid wall thickness and sumWT (p < 0.05 for all) after adjustment for baseline Αβ1-40 levels, TRFs, and renal function.

CONCLUSION

 In postmenopausal women, a pattern of increasing or persistently high Αβ1-40 was associated with the rate of progression of subclinical atherosclerosis irrespective of its baseline levels. These findings provide novel insights into a link between Αβ1-40 and atherosclerosis progression in menopause and warrant further research to clarify the clinical value of monitoring its circulating levels as an atherosclerosis biomarker in women without clinically overt CVD.

[Cardiovascular preventive recommendations. PAPPS 2020 update]

The recommendations of the semFYC's Program for Preventive Activities and Health Promotion (PAPPS) for the prevention of cardiovascular diseases (CVD) are presented. The following sections are included: Epidemiological review, where the current morbidity and mortality of CVD in Spain and its evolution as well as the main risk factors are described; Cardiovascular (CV) risk tables and recommendations for the calculation of CV risk; Main risk factors such as arterial hypertension, dyslipidemia and diabetes mellitus, describing the method for their diagnosis, therapeutic objectives and recommendations for lifestyle measures and pharmacological treatment; Indications for antiplatelet therapy, and recommendations for screening of atrial fibrillation. The quality of testing and the strength of the recommendation are included in the main recommendations.