Assessment of right ventricular size and function from cardiovascular magnetic resonance images using artificial intelligence.

BACKGROUND: Theoretically, artificial intelligence can provide an accurate automatic solution to measure right ventricular (RV) ejection fraction (RVEF) from cardiovascular magnetic resonance (CMR) images, despite the complex RV geometry. However, in our recent study, commercially available deep learning (DL) algorithms for RVEF quantification performed poorly in some patients. The current study was designed to test the hypothesis that quantification of RV function could be improved in these patients by using more diverse CMR datasets in addition to domain-specific quantitative performance evaluation metrics during the cross-validation phase of DL algorithm development. METHODS: We identified 100 patients from our prior study who had the largest differences between manually measured and automated RVEF values. Automated RVEF measurements were performed using the original version of the algorithm (DL1), an updated version (DL2) developed from a dataset that included a wider range of RV pathology and validated using multiple domain-specific quantitative performance evaluation metrics, and conventional methodology performed by a core laboratory (CORE). Each of the DL-RVEF approaches was compared against CORE-RVEF reference values using linear regression and Bland-Altman analyses. Additionally, RVEF values were classified into 3 categories: ≤ 35%, 35-50%, and ≥ 50%. Agreement between RVEF classifications made by the DL approaches and the CORE measurements was tested. RESULTS: CORE-RVEF and DL-RVEFs were obtained in all patients (feasibility of 100%). DL2-RVEF correlated with CORE-RVEF better than DL1-RVEF (r = 0.87 vs. r = 0.42), with narrower limits of agreement. As a result, DL2 algorithm also showed increasing accuracy from 0.53 to 0.80 for categorizing RV function. CONCLUSIONS: The use of a new DL algorithm cross-validated on a dataset with a wide range of RV pathology using multiple domain-specific metrics resulted in a considerable improvement in the accuracy of automated RVEF measurements. This improvement was demonstrated in patients whose images were the most challenging and resulted in the largest RVEF errors. These findings underscore the critical importance of this strategy in the development of DL approaches for automated CMR measurements.

AI Based CMR Assessment of Biventricular Function: Clinical Significance of Intervendor Variability and Measurement Errors.

OBJECTIVES: The aim of this study was to determine whether left ventricular ejection fraction (LVEF) and right ventricular ejection fraction (RVEF) and left ventricular mass (LVM) measurements made using 3 fully automated deep learning (DL) algorithms are accurate and interchangeable and can be used to classify ventricular function and risk-stratify patients as accurately as an expert. BACKGROUND: Artificial intelligence is increasingly used to assess cardiac function and LVM from cardiac magnetic resonance images. METHODS: Two hundred patients were identified from a registry of individuals who underwent vasodilator stress cardiac magnetic resonance. LVEF, LVM, and RVEF were determined using 3 fully automated commercial DL algorithms and by a clinical expert (CLIN) using conventional methodology. Additionally, LVEF values were classified according to clinically important ranges: <35%, 35% to 50%, and ≥50%. Both ejection fraction values and classifications made by the DL ejection fraction approaches were compared against CLIN ejection fraction reference. Receiver-operating characteristic curve analysis was performed to evaluate the ability of CLIN and each of the DL classifications to predict major adverse cardiovascular events. RESULTS: Excellent correlations were seen for each DL-LVEF compared with CLIN-LVEF (r = 0.83-0.93). Good correlations were present between DL-LVM and CLIN-LVM (r = 0.75-0.85). Modest correlations were observed between DL-RVEF and CLIN-RVEF (r = 0.59-0.68). A >10% error between CLIN and DL ejection fraction was present in 5% to 18% of cases for the left ventricle and 23% to 43% for the right ventricle. LVEF classification agreed with CLIN-LVEF classification in 86%, 80%, and 85% cases for the 3 DL-LVEF approaches. There were no differences among the 4 approaches in associations with major adverse cardiovascular events for LVEF, LVM, and RVEF. CONCLUSIONS: This study revealed good agreement between automated and expert-derived LVEF and similarly strong associations with outcomes, compared with an expert. However, the ability of these automated measurements to accurately classify left ventricular function for treatment decision remains limited. DL-LVM showed good agreement with CLIN-LVM. DL-RVEF approaches need further refinements.

Hypertension in older adults: Assessment, management, and challenges.

Hypertension in older adults is related to adverse cardiovascular outcomes, such as heart failure, stroke, myocardial infarction, and death. The global burden of hypertension is increasing due to an aging population and increasing prevalence of obesity, and is estimated to affect one third of the world's population by 2025. Adverse outcomes in older adults are compounded by mechanical hemodynamic changes, arterial stiffness, neurohormonal and autonomic dysregulation, and declining renal function. This review highlights the current evidence and summarizes recent guidelines on hypertension, pertaining to older adults. Management strategies for hypertension in older adults must consider the degree of frailty, increasingly complex medical comorbidities, and psycho-social factors, and must therefore be individualized. Non-pharmacological lifestyle interventions should be encouraged to mitigate the risk of developing hypertension, and as an adjunctive therapy to reduce the need for medications. Pharmacological therapy with diuretics, renin-angiotensin system blockers, and calcium channel blockers have all shown benefit on cardiovascular outcomes in older patients. Given the economic and public health burden of hypertension in the United States and globally, it is critical to address lifestyle modifications in younger generations to prevent hypertension with age.

Heart Centers for Women: Historical Perspective on Formation and Future Strategies to Reduce Cardiovascular Disease.

Heart Centers for Women (HCW) developed as a response to the need for improved outcomes for women with cardiovascular disease (CVD). From 1984 until 2012, more women died of CVD every single year in comparison with men. Initially, there was limited awareness and sex-specific research regarding mortality or outcomes in women. HCW played an active role in addressing these disparities, provided focused care for women, and contributed to improvements in these gaps. In 2014 and 2015, death from CVD in women had declined below the level of death from CVD in comparison with men. Even though awareness of CVD in women has increased among the public and healthcare providers and both sex- and gender-specific research is currently required in all research trials, not all women have benefitted equally in mortality reduction. New strategies for HCW need to be developed to address these disparities and expand the current HCW model. The HCW care team needs to direct academic curricula on sex- and gender-specific research and care; expand to include other healthcare professionals and other subspecialties; provide new care models; address diversity; and include more male providers.

Sex Differences in Ischemic Heart Disease: Advances, Obstacles, and Next Steps.

Evolving knowledge of sex-specific presentations, improved recognition of conventional and novel risk factors, and expanded understanding of the sex-specific pathophysiology of ischemic heart disease have resulted in improved clinical outcomes in women. Yet, ischemic heart disease continues to be the leading cause of morbidity and mortality in women in the United States. The important publication by the Institute of Medicine titled "Women's Health Research-Progress, Pitfalls, and Promise," highlights the persistent disparities in cardiovascular disease burden among subgroups of women, particularly women who are socially disadvantaged because of race, ethnicity, income level, and educational attainment. These important health disparities reflect underrepresentation of women in research, with the resultant unfavorable impact on diagnosis, prevention, and treatment strategies in women at risk for cardiovascular disease. Causes of disparities are multifactorial and related to differences in risk factor prevalence, access to care, use of evidence-based guidelines, and social and environmental factors. Lack of awareness in both the public and medical community, as well as existing knowledge gap regarding sex-specific differences in presentation, risk factors, pathophysiology, and response to treatment for ischemic heart disease, further contribute to outcome disparities. There is a critical need for implementation of sex- and gender-specific strategies to improve cardiovascular outcomes. This review is tailored to meet the needs of a busy clinician and summarizes the contemporary trends, characterizes current sex-specific outcome disparities, delineates challenges, and proposes transformative solutions for improvement of the full spectrum of ischemic heart disease clinical care and research in women.

Advances in Cardiovascular Health in Women over the Past Decade: Guideline Recommendations for Practice.

Cardiovascular disease (CVD) remains the number one cause of death in women. It is estimated that 44 million women in the United States are either living with or at risk for heart disease. This article highlights the recent significant progress made in improving care, clinical decision-making, and policy implications for women with CVD. We provide our perspective supported by evidence-based advances in cardiovascular research and clinical care guidelines in seven areas: (1) primary CVD prevention and community heart care, (2) secondary prevention of CVD, (3) stroke, (4) heart failure and cardiomyopathies, (5) ischemia with nonobstructive coronary artery disease, (6) spontaneous coronary artery dissection, and (7) arrhythmias and device therapies. Advances in these fields have improved the lives of women living with and at risk for heart disease. With increase awareness, partnership with national organizations, sex-specific research, and changes in policy, the morbidity and mortality of CVD in women can be further reduced.

Plant-Based Nutrition: An Essential Component of Cardiovascular Disease Prevention and Management.

PURPOSE OF REVIEW: This review aims to summarize and discuss the role of plant-based nutrition as an adjunct to the management of cardiovascular disease (CVD). Discussion of nutrition and the benefits of a plant-based diet should be highlighted during healthcare provider visits as an essential part of the overall CVD prevention and management care plan. RECENT FINDINGS: Evidence from prospective cohort studies indicates that a high consumption of predominantly plant-based foods, such as fruit and vegetables, nuts, and whole grains, is associated with a significantly lower risk of CVD. The protective effects of these foods are likely mediated through their multiple beneficial nutrients, including mono- and polyunsaturated fatty acids, omega-3 fatty acids, antioxidant vitamins, minerals, phytochemicals, fiber, and plant protein. In addition, minimizing intake of animal proteins has been shown to decrease the prevalence of CVD risk factors. Substantial evidence indicates that plant-based diets can play an important role in preventing and treating CVD and its risk factors. Such diets deserve more emphasis in dietary recommendations.