RESUMO
Coronary artery disease (CAD) is still a serious global health issue that has a substantial impact on death and illness rates. The goal of primary prevention strategies is to lower the risk of developing CAD. Nevertheless, current methods usually rely on simple risk assessment instruments that might overlook significant individual risk factors. This limitation highlights the need for innovative methods that can accurately assess cardiovascular risk and offer personalized preventive care. Recent advances in machine learning and artificial intelligence (AI) have opened up interesting new avenues for optimizing primary preventive efforts for CAD and improving risk prediction models. By leveraging large-scale databases and advanced computational techniques, AI has the potential to fundamentally alter how cardiovascular risk is evaluated and managed. This review looks at current randomized controlled studies and clinical trials that explore the application of AI and machine learning to improve primary preventive measures for CAD. The emphasis is on their ability to recognize and include a range of risk elements in sophisticated risk assessment models.
RESUMO
INTRODUCTION: Coronavirus disease 2019 (COVID-19) has multiorgan involvement and its severity varies with the presence of pre-existing risk factors like cardiovascular disease (CVD) and hypertension (HTN). Therefore, it is important to evaluate their effect on outcomes of COVID-19 patients. The objective of this meta-analysis and meta-regression is to evaluate outcomes of COVID-19 amongst patients with CVD and HTN. METHODS: English full-text observational studies having data on epidemiological characteristics of patients with COVID-19 were identified searching PubMed from December 1, 2019, to July 31, 2020, following Meta-analysis Of Observational Studies in Epidemiology (MOOSE) protocol. Studies having pre-existing CVD and HTN data that described outcomes including mortality and invasive mechanical ventilation (IMV) utilization were selected. Using random-effects models, risk of composite poor outcomes (meta-analysis) and isolated mortality and IMV utilization (meta-regression) were evaluated. Pooled prevalence of CVD and HTN, correlation coefficient (r) and odds ratio (OR) were estimated. The forest plots and correlation plots were created using random-effects models. RESULTS: Out of 29 studies (n=27,950) that met the criteria, 28 and 27 studies had data on CVD and HTN, respectively. Pooled prevalence of CVD was 18.2% and HTN was 32.7%. In meta-analysis, CVD (OR: 3.36; 95% CI: 2.29-4.94) and HTN (OR: 1.94; 95% CI: 1.57-2.40) were associated with composite poor outcome. In age-adjusted meta-regression, pre-existing CVD was having significantly higher correlation of IMV utilization (r: 0.28; OR: 1.3; 95% CI: 1.1-1.6) without having any association with mortality (r: -0.01; OR: 0.9; 95% CI: 0.9-1.1) among COVID-19 hospitalizations. HTN was neither correlated with higher IMV utilization (r: 0.01; OR: 1.0; 95% CI: 0.9-1.1) nor correlated with higher mortality (r: 0.001; OR: 1.0; 95% CI: 0.9-1.1). CONCLUSION: In age-adjusted analysis, though we identified pre-existing CVD as a risk factor for higher utilization of mechanical ventilation, pre-existing CVD and HTN had no independent role in increasing mortality.
RESUMO
Background: According to past studies, recovery and survival following severe vascular events such as acute myocardial infarction and stroke are negatively impacted by vitamin D deficiency. However, the national estimate on disability-related burden is unclear. We intend to evaluate the prevalence and outcomes of vitamin D deficiency (VDD) among patients with cardiovascular disease (CVD) and cerebrovascular disorder (CeVD). Methods: We performed a cross-sectional study on the Nationwide Inpatient Sample data (2016-2017) of adult (≥18 years) hospitalizations. We identified patients with a secondary diagnosis of VDD and a primary diagnosis of CVD and CeVD using the 9th revision of the International Classification of Diseases, clinical modification code (ICD-10-CM) codes. A univariate and mixed-effect multivariable survey logistic regression analysis was performed to evaluate the prevalence, disability, and discharge disposition of patients with CVD and CeVD in the presence of VDD. Results: Among 58,259,589 USA hospitalizations, 3.44%, 2.15%, 0.06%, 1.28%, 11.49%, 1.71%, 0.38%, 0.23%, and 0.08% had primary admission of IHD, acute MI, angina, AFib, CHF, AIS, TIA, ICeH, and SAH, respectively and 1.82% had VDD. The prevalence of hospitalizations due to CHF (14.66% vs. 11.43%), AIS (1.87% vs. 1.71%), and TIA (0.4% vs. 0.38%) was higher among VDD patients as compared with non-VDD patients (p < 0.0001). In a regression analysis, as compare with non-VDD patients, the VDD patients were associated with higher odds of discharge to non-home facilities with an admission diagnosis of CHF (aOR 1.08, 95% CI 1.07-1.09), IHD (aOR 1.24, 95% CI 1.21-1.28), acute MI (aOR 1.23, 95% CI 1.19-1.28), AFib (aOR 1.21, 95% CI 1.16-1.27), and TIA (aOR 1.19, 95% CI 1.11-1.28). VDD was associated with higher odds of severe or extreme disability among patients hospitalized with AIS (aOR 1.1, 95% CI 1.06-1.14), ICeH (aOR 1.22, 95% CI 1.08-1.38), TIA (aOR 1.36, 95% CI 1.25-1.47), IHD (aOR 1.37, 95% CI 1.33-1.41), acute MI (aOR 1.44, 95% CI 1.38-1.49), AFib (aOR 1.10, 95% CI 1.06-1.15), and CHF (aOR 1.03, 95% CI 1.02-1.05) as compared with non-VDD. Conclusions: CVD and CeVD in the presence of VDD increase the disability and discharge to non-home facilities among USA hospitalizations. Future studies should be planned to evaluate the effect of VDD replacement for improving outcomes.