A Head-to Head Comparison of Machine Learning Algorithms for Identification of Implanted Cardiac Devices.

Application of artificial intelligence techniques in medicine has rapidly expanded in recent years. Two algorithms for identification of cardiac implantable electronic devices using chest radiography were recently developed: The PacemakerID algorithm, available as a mobile phone application (PIDa) and a web platform (PIDw) and The Pacemaker Identification with Neural Networks (PPMnn), available via web platform. In this study, we assessed the relative accuracy of these algorithms. The machine learning algorithms (PIDa, PIDw, PPMnn) were used to predict device manufacturer using chest X-rays for patients with implanted devices. Each prediction was considered correct if predicted certainty was >75%. For comparative purposes, accuracy of each prediction was compared to the result using the CARDIA-X algorithm. 500 X-rays were included from a convenience sample. Raw accuracy was PIDa 89%, PIDw 73%, PPMnn 71% and CARDIA-X 85%. In conclusion, machine learning algorithms for identification of cardiac devices are accurate at determining device manufacturer, have capacity for improved accuracy with additional training sets and can utilize simple user interfaces. These algorithms have clinical utility in limiting potential infectious exposures and facilitate rapid identification of devices as needed for device reprogramming.

Nonalcoholic Fatty Liver Disease and the Heart: JACC State-of-the-Art Review.

Nonalcoholic fatty liver disease (NAFLD) and cardiovascular disease (CVD) are both manifestations of end-organ damage of the metabolic syndrome. Through multiple pathophysiological mechanisms, CVD and NAFLD are associated with each other. Systemic inflammation, endothelial dysfunction, hepatic insulin resistance, oxidative stress, and altered lipid metabolism are some of the mechanisms by which NAFLD increases the risk of CVD. Patients with NAFLD develop increased atherosclerosis, cardiomyopathy, and arrhythmia, which clinically result in cardiovascular morbidity and mortality. Defining the mechanisms linking these 2 diseases offers the opportunity to further develop targeted therapies. The aim of this comprehensive review is to examine the association between CVD and NAFLD and discuss the overlapping management approaches.

The art of cardiovascular risk assessment.

Cardiovascular disease (CVD) remains the leading cause of death in the United States. Healthcare expenditures have been principally allocated toward treatment of CVD at the end of the health/disease continuum, rather than toward health promotion and disease prevention. A focused effort on both primordial and primary prevention can promote cardiovascular health and reduce the burden of CVD. Risk-factor assessment for predicting atherosclerotic CVD events serves as the foundation of preventive cardiology and has been driven by population-based scoring algorithms based on traditional risk factors. Incorporating individual nontraditional risk factors, biomarkers, and selective use of noninvasive measures may help identify more at-risk patients as well as truly low-risk individuals, allowing for better targeting of treatment intensity. Using a combination of validated population-based atherosclerotic CVD risk-assessment tools, nontraditional risk factors, social health determinants, and novel markers of atherosclerotic disease, we should be able to improve our ability to assess CVD risk. Through scientific evidence, clinical judgment, and discussion between the patient and clinician, we can implement an effective evidence-based strategy to assess and reduce CVD risk.

Reconfiguring Cardiac Rehabilitation to Achieve Panvascular Prevention: New Care Models for a New World.

Atherosclerotic cardiovascular disease (ASCVD) and its associated economic burden are increasing globally. Although cardiac rehabilitation is a vital component of secondary prevention with proven benefits, it is underutilized due to numerous barriers, especially in resource-limited settings. New care models for delivery of comprehensive prevention programs such as community-based, home-based, and "hybrid" models implementing m-health, e-health, and telemedicine need to be adopted. Such new care models should be offered to all patients with established ASCVD (coronary, cerebral, and peripheral) and additionally to those at high risk of developing ASCVD with multiple risk factors for panvascular prevention.

Performance of J-CTO and PROGRESS CTO Scores in Predicting Angiographic Success and Long-term Outcomes of Percutaneous Coronary Interventions for Chronic Total Occlusions.

Patient selection for and predicting clinical outcomes of chronic total occlusion (CTO) percutaneous coronary intervention (PCI) remain challenging. We hypothesized that both J-CTO (Multicenter Chronic Total Occlusion Registry of Japan) and PROGRESS CTO (Prospective Global Registry for the Study of Chronic Total Occlusion Intervention) scores will predict not only angiographic success but also long-term clinical outcomes of the patients who underwent PCI of CTO. Of 325 CTO PCIs performed at 2 Emory University hospitals from January 2012 to August 2015, 249 patients with complete baseline clinical, angiographic and follow-up data, were included in this analysis. Major adverse cardiovascular events (MACEs) consisted of a composite of death, myocardial infarction, and target vessel revascularization. Mean age was 63 ± 11 years old and mean follow-up was 19.8 ± 13.1 months. Angiographic success rates increased from 74.5% in 2012 to 85.7% in 2015. Greater J-CTO and PROGRESS CTO scores were not only associated with lower likelihood of angiographic success but also higher rates of long-term MACE. Compared with the scores of 0 to 2, J-CTO and PROGRESS CTO scores of ≥3 were associated with higher MACE. Multivariable analysis demonstrated that PROGRESS CTO scores of ≥3, male sex, and peripheral vascular disease were independent predictors of MACE. In conclusion, J-CTO and PROGRESS CTO scores are useful in predicting procedural success. In addition, the PROGRESS CTO score, and to a lesser degree J-CTO score, have predictive value for long-term outcomes in patients who underwent CTO PCI.

Comparison of the Association Between High-Sensitivity Troponin I and Adverse Cardiovascular Outcomes in Patients With Versus Without Chronic Kidney Disease.

It is unknown whether the association of high-sensitivity troponin I (hs-TnI) with adverse cardiovascular outcomes varies by the presence of chronic kidney disease (CKD). We examined the association of hs-TnI with adverse cardiovascular outcomes in those with and without CKD in 4,107 (mean age, 64 years; 63% men; 20% black) patients from the Emory Cardiovascular Biobank who underwent coronary angiography. CKD (n = 1,073) was defined as estimated glomerular filtration rate <60 ml/min/1.73 m2 or urine albumin/creatinine ratio >30 mg/g at baseline. Cox regression was used to compute hazard ratios (HR) for the association between hs-TnI levels (per doubling of hs-TnI: log2[hs-TnI] + 1) and death, cardiovascular death, and major adverse cardiac events (MACE), separately. Hs-TnI was a stronger predictor of death (CKD: HR 1.23, 95% confidence interval [CI] 1.15 to 1.31; no CKD: HR 1.11, 95% CI 1.05 to 1.17, p-interaction = 0.023), cardiovascular death (CKD: HR 1.24, 95% CI 1.14 to 1.34; no CKD: HR 1.15, 95% CI 1.07 to 1.22, p-interaction = 0.12), and MACE (CKD: HR 1.18, 95% CI 1.11 to 1.25; no CKD: HR 1.11, 95% CI 1.06 to 1.16, p-interaction = 0.095) in CKD compared with non-CKD. The association between hs-TnI and death in patients with CKD was stronger for patients without obstructive coronary artery disease (no obstructive coronary artery disease: HR 1.60, 95% CI 1.27 to 2.01; obstructive coronary artery disease: HR 1.19, 95% CI 1.11 to 1.27, p-interaction = 0.041). In conclusion, hs-TnI is a stronger predictor of adverse cardiovascular events in patients who have CKD than those without, even in the absence of obstructive coronary artery disease. Hs-TnI may identify CKD patients who are high risk for adverse cardiovascular outcomes in whom aggressive risk factor modification strategies are warranted.

Comprehensive primary prevention of cardiovascular disease in women.

Atherosclerotic cardiovascular disease (ASCVD) remains the leading cause of mortality in women. Historically, medical research has focused on male patients, and subsequently, there has been decreased awareness of the burden of ASCVD in females until recent years. The biological differences between sexes and differences in societal expectations defined by gender roles contribute to gender differences in ASCVD risk factors. With these differing risk profiles, risk assessment, risk stratification, and primary preventive measures of ASCVD are different in women and men. In this review article, clinicians will understand the risk factors unique to women, such as preeclampsia, gestational diabetes, and those that disproportionately affect them such as autoimmune disorders. With these conditions in mind, the approach to ASCVD risk assessment and stratification in women will be discussed. Furthermore, the literature behind the effects of primary preventive measures in women, including lifestyle modifications, aspirin, statins, and anticoagulation, will be reviewed. The aim of this review article was to ultimately improve ASCVD primary prevention by reducing gender disparities through education of physicians.

Novel biomarkers of coronary microvascular disease.

Coronary microvascular disease in the absence of myocardial diseases has traditionally been diagnosed through coronary reactivity testing in the cardiac catheterization laboratory. Compared with invasive procedures, blood-based biomarkers may have reduced cost, less risk of physical harm and greater accessibility, making them ideal for an outpatient management strategy. There are a variety of biomarkers available with potential utility in the management of microvascular disease; however, none have yet been extensively validated or established in this clinical patient population.