Search

Background: Atherosclerotic cardiovascular diseases (CVDs) are leading causes of death despite effective therapies and result in unnecessary morbidity and mortality throughout the world. We aimed to investigate the cost-effectiveness of polygenic risk scores (PRS) to guide statin therapy for Canadians with intermediate CVD risk and model its economic outlook. Methods: This cost-utility analysis was conducted using UK Biobank prospective cohort study participants, with recruitment from 2006 to 2010, and at least 10 years of follow-up. We included nonrelated white British-descent participants (n=96 116) at intermediate CVD risk with no prior lipid lowering medication or statin-indicated conditions. A coronary artery disease PRS was used to inform decision to use statins. The effects of statin therapy with and without PRS, as well as CVD events were modelled to determine the incremental cost-effectiveness ratio from a Canadian public health care perspective. We discounted future costs and quality-adjusted life-years by 1.5% annually. Results: The optimal economic strategy was when intermediate risk individuals with a PRS in the top 70% are eligible for statins while the lowest 1% are excluded. Base-case analysis at a genotyping cost of $70 produced an incremental cost-effectiveness ratio of $172 906 (143 685 USD) per quality-adjusted life-year. In the probabilistic sensitivity analysis, the intervention has approximately a 50% probability of being cost-effective at $179 100 (148 749 USD) per quality-adjusted life-year. At a $0 genotyping cost, representing individuals with existing genotyping information, PRS-guided strategies dominated standard care when 12% of the lowest PRS individuals were withheld from statins. With improved PRS predictive performance and lower genotyping costs, the incremental cost-effectiveness ratio demonstrates possible cost-effectiveness under thresholds of $150 000 and possibly $50 000 per quality-adjusted life-year. Conclusions: This study suggests that using PRS alongside existing guidelines might be cost-effective for CVD. Stronger predictiveness combined with decreased cost of PRS could further improve cost-effectiveness, providing an economic basis for its inclusion into clinical care.

Background and ObjectivesLow buffy coat mitochondrial DNA copy number (mtDNA-CN) is associated with incident risk of stroke and poststroke mortality; however, its prognostic utility has not been extensively explored. Our goal was to investigate whether low buffy coat mtDNA-CN is a marker and causal determinant of poststroke outcomes using epidemiologic and genetic studies.MethodsFirst, we performed association testing between baseline buffy coat mtDNA-CN measurements and 1-month poststroke outcomes in 3,498 cases of acute, first stroke from 25 countries from the international, multicenter case-control study Importance of Conventional and Emerging Risk Factors of Stroke in Different Regions and Ethnic Groups of the World (INTERSTROKE). Then, we performed 2-sample mendelian randomization analyses to evaluate potential causative effects of low mtDNA-CN on 3-month modified Rankin Scale (mRS) score. Genetic variants associated with mtDNA-CN levels were derived from the UK Biobank study (N = 383,476), and corresponding effects on 3-month mRS score were ascertained from the Genetics of Ischemic Stroke Functional Outcome (GISCOME; N = 6,021) study.ResultsA 1-SD lower mtDNA-CN at baseline was associated with stroke severity (baseline mRS score: odds ratio [OR] 1.27, 95% confidence interval [CI] 1.19–1.36; p = 4.7 × 10−12). Independently of baseline stroke severity, lower mtDNA-CN was associated with increased odds of greater 1-month disability (ordinal mRS score: OR 1.16, 95% CI 1.08–1.24; p = 4.4 × 10−5), poor functional outcome status (mRS score 3–6 vs 0–2: OR 1.21, 95% CI 1.08–1.34; p = 6.9 × 10−4), and mortality (OR 1.35, 95% CI 1.14–1.59; p = 3.9 × 10−4). Subgroup analyses demonstrated consistent effects across stroke type, sex, age, country income level, and education level. In addition, mtDNA-CN significantly improved reclassification of poor functional outcome status (net reclassification index [NRI] score 0.16, 95% CI 0.08–0.23; p = 3.6 × 10−5) and mortality (NRI score 0.31, 95% CI 0.19–0.43; p = 1.7 × 10−7) beyond known prognosticators. With the use of independent datasets, mendelian randomization revealed that a 1-SD decrease in genetically determined mtDNA-CN was associated with increased odds of greater 3-month disability quantified by ordinal mRS score (OR 2.35, 95% CI 1.13–4.90; p = 0.02) and poor functional outcome status (OR 2.68, 95% CI 1.05–6.86; p = 0.04).DiscussionBuffy coat mtDNA-CN is a novel and robust marker of poststroke prognosis that may also be a causal determinant of poststroke outcomes.Classification of EvidenceThis study provides Class II evidence that low buffy coat mtDNA-CN (>1 SD) was associated with worse baseline severity and 1-month outcomes in patients with ischemic or hemorrhagic stroke.

Aims Clinical scoring systems for pulmonary embolism (PE) screening have low specificity and contribute to computed tomography pulmonary angiogram (CTPA) overuse. We assessed whether deep learning models using an existing and routinely collected data modality, electrocardiogram (ECG) waveforms, can increase specificity for PE detection. Methods and results We create a retrospective cohort of 21 183 patients at moderate- to high suspicion of PE and associate 23 793 CTPAs (10.0% PE-positive) with 320 746 ECGs and encounter-level clinical data (demographics, comorbidities, vital signs, and labs). We develop three machine learning models to predict PE likelihood: an ECG model using only ECG waveform data, an EHR model using tabular clinical data, and a Fusion model integrating clinical data and an embedded representation of the ECG waveform. We find that a Fusion model [area under the receiver-operating characteristic curve (AUROC) 0.81 ± 0.01] outperforms both the ECG model (AUROC 0.59 ± 0.01) and EHR model (AUROC 0.65 ± 0.01). On a sample of 100 patients from the test set, the Fusion model also achieves greater specificity (0.18) and performance (AUROC 0.84 ± 0.01) than four commonly evaluated clinical scores: Wells’ Criteria, Revised Geneva Score, Pulmonary Embolism Rule-Out Criteria, and 4-Level Pulmonary Embolism Clinical Probability Score (AUROC 0.50–0.58, specificity 0.00–0.05). The model is superior to these scores on feature sensitivity analyses (AUROC 0.66–0.84) and achieves comparable performance across sex (AUROC 0.81) and racial/ethnic (AUROC 0.77–0.84) subgroups. Conclusion Synergistic deep learning of ECG waveforms with traditional clinical variables can increase the specificity of PE detection in patients at least at moderate suspicion for PE.

Analyses of medical data have been steered to support and justify orthodox systems and graphical models that reproduce the relatively subjective reasoning of experts. Evidence-based decision tree analyses and risk scores are valid tools for clinical decision-making that are widely used in medicine

Objectives This study sought to explore the natural clustering of echocardiographic variables used for assessing left ventricular (LV) diastolic dysfunction (DD) in order to isolate high-risk phenotypic patterns and assess their prognostic significance. Background Assessment of LV DD is important in the management and prognosis of cardiovascular diseases. Data-driven approaches such as cluster analysis may be useful in segregating similar cases without the constraint of an a priori algorithm for risk stratification. Methods The study included a convenience sample of 866 consecutive patients referred for myocardial function assessment (age: 65 ± 17 years; 55.3% women; ejection fraction: 60 ± 9%) for whom echocardiographic parameters of DD assessment were obtained per conventional guideline recommendations. Unsupervised, hierarchical cluster analysis of these parameters was conducted using the Ward linkage method. Major adverse cardiovascular events, hospitalization, and mortality were compared between conventional and cluster-based classifications. Results Clustering algorithms for screening the presence of DD in 559 of 866 patients identified 2 distinct groups and revealed modest agreement with conventional classification (kappa = 0.41, p Conclusions An unsupervised assessment of echocardiographic variables for assessing LV DD revealed unique patterns of grouping. These natural patterns of clustering may better identify patient groups who have similar risk, and their incorporation into clinical practice may help eliminate indeterminate results and improve clinical outcome prediction.

Mitochondrial DNA copy number (mtDNA-CN) is an accessible blood-based measurement believed to capture underlying mitochondrial function. The specific biological processes underpinning its regulation, and whether those processes are causative for disease, is an area of active investigation. We developed a novel method for array-based mtDNA-CN estimation suitable for biobank-scale studies, called “AutoMitoC”. We applied AutoMitoC to 395,781 UKBiobank study participants and performed genome and exome-wide association studies, identifying novel common and rare genetic determinants. Overall, genetic analyses identified 73 loci for mtDNA-CN, which implicated several genes involved in rare mtDNA depletion disorders, dNTP metabolism, and the mitochondrial central dogma. Rare variant analysis identified SAMHD1 mutation carriers as having higher mtDNA-CN (beta=0.23 SDs; 95% CI, 0.18-0.29; P=2.6×10−19), a potential therapeutic target for patients with mtDNA depletion disorders, but at increased risk of breast cancer (OR=1.91; 95% CI, 1.52-2.40; P=2.7×10−8). Finally, Mendelian randomization analyses suggest a causal effect of low mtDNA-CN on dementia risk (OR=1.94 per 1 SD decrease in mtDNA-CN; 95% CI, 1.55-2.32; P=7.5×10−4). Altogether, our genetic findings indicate that mtDNA-CN is a complex biomarker reflecting specific mitochondrial processes related to mtDNA regulation, and that these processes are causally related to human diseases.

Summary Background Angiotensin-converting enzyme 2 (ACE2) is an endogenous counter-regulator of the renin–angiotensin hormonal cascade. We assessed whether plasma ACE2 concentrations were associated with greater risk of death or cardiovascular disease events. Methods We used data from the Prospective Urban Rural Epidemiology (PURE) prospective study to conduct a case-cohort analysis within a subset of PURE participants (from 14 countries across five continents: Africa, Asia, Europe, North America, and South America). We measured plasma concentrations of ACE2 and assessed potential determinants of plasma ACE2 levels as well as the association of ACE2 with cardiovascular events. Findings We included 10 753 PURE participants in our study. Increased concentration of plasma ACE2 was associated with increased risk of total deaths (hazard ratio [HR] 1·35 per 1 SD increase [95% CI 1·29–1·43]) with similar increases in cardiovascular and non-cardiovascular deaths. Plasma ACE2 concentration was also associated with higher risk of incident heart failure (HR 1·27 per 1 SD increase [1·10–1·46]), myocardial infarction (HR 1·23 per 1 SD increase [1·13–1·33]), stroke (HR 1·21 per 1 SD increase [1·10–1·32]) and diabetes (HR 1·44 per 1 SD increase [1·36–1·52]). These findings were independent of age, sex, ancestry, and traditional cardiac risk factors. With the exception of incident heart failure events, the independent relationship of ACE2 with the clinical endpoints, including death, remained robust after adjustment for BNP. The highest-ranked determinants of ACE2 concentrations were sex, geographic ancestry, and body-mass index (BMI). When compared with clinical risk factors (smoking, diabetes, blood pressure, lipids, and BMI), ACE2 was the highest ranked predictor of death, and superseded several risk factors as a predictor of heart failure, stroke, and myocardial infarction. Interpretation Increased plasma ACE2 concentration was associated with increased risk of major cardiovascular events in a global study. Funding Canadian Institute of Health Research, Heart & Stroke Foundation of Canada, and Bayer.

We thank Dr. Kampaktsis and colleagues for their interest in our investigation. Although we agree that the 2016 guidelines may have made diastolic dysfunction (DD) more conceptually simple in a clinical approach; there are 2 problems with this apparent simplification. First, the large number of

Insonation, or the use of ultrasound, has been proposed to be included in the medical school curriculum, both for education and bedside physical examination. It is important to consider what impact insonation should have on medical student education. Increasingly students are exposed to ultrasound use on clinical rotations, but to what extent should ultrasound be an integrated part of the preclinical curriculum in the United States? Ultrasound can serve to augment an existing curriculum in anatomy, physiology, physical examination, and disease assessment and treatment. In addition, the actual performance and interpretation of the insonation component of physical examination in real time may be an emerging skill set to be expected of medical students. Here we describe the utility and challenges of incorporating an ultrasound curriculum into undergraduate medical education, including examples from institutions that have pioneered this innovative curricular change.

Purpose of Review Peripheral artery disease (PAD) affects an estimated 200 million people worldwide and is associated with significant cardiovascular morbidity and mortality. Cardiovascular risk is further increased among individuals with polyvascular disease, where either cerebrovascular or coronary artery disease is present in addition to PAD. In this review, we present common clinical scenarios encountered when managing patients with PAD and provide an evidence-based approach to prescribing optimal antithrombotics in this population. Recent Findings The COMPASS trial recently demonstrated that rivaroxaban 2.5 mg BID + ASA daily significantly reduces major adverse cardiac and limb events in patients with PAD. Despite these advances, morbidity following MALE events remains high. Summary With widespread approval by federal health regulators, the COMPASS regimen should be strongly considered in PAD patients who do not have a high bleeding risk. Implementing the COMPASS regimen in patients with PAD, along with other vascular risk reduction strategies, will have a substantial impact on reducing atherothromboembolic risk in patients with established vascular disease.

Background Machine-learning models may aid cardiac phenotypic recognition by using features of cardiac tissue deformation. Objectives This study investigated the diagnostic value of a machine-learning framework that incorporates speckle-tracking echocardiographic data for automated discrimination of hypertrophic cardiomyopathy (HCM) from physiological hypertrophy seen in athletes (ATH). Methods Expert-annotated speckle-tracking echocardiographic datasets obtained from 77 ATH and 62 HCM patients were used for developing an automated system. An ensemble machine-learning model with 3 different machine-learning algorithms (support vector machines, random forests, and artificial neural networks) was developed and a majority voting method was used for conclusive predictions with further K -fold cross-validation. Results Feature selection using an information gain (IG) algorithm revealed that volume was the best predictor for differentiating between HCM ands. ATH (IG = 0.24) followed by mid-left ventricular segmental (IG = 0.134) and average longitudinal strain (IG = 0.131). The ensemble machine-learning model showed increased sensitivity and specificity compared with early-to-late diastolic transmitral velocity ratio (p 13 mm. In this subgroup analysis, the automated model continued to show equal sensitivity, but increased specificity relative to early-to-late diastolic transmitral velocity ratio, e′, and strain. Conclusions Our results suggested that machine-learning algorithms can assist in the discrimination of physiological versus pathological patterns of hypertrophic remodeling. This effort represents a step toward the development of a real-time, machine-learning–based system for automated interpretation of echocardiographic images, which may help novice readers with limited experience.

This study sought to explore the natural clustering of echocardiographic variables used for assessing left ventricular (LV) diastolic dysfunction (DD) in order to isolate high-risk phenotypic patterns and assess their prognostic significance.Assessment of LV DD is important in the management and prognosis of cardiovascular diseases. Data-driven approaches such as cluster analysis may be useful in segregating similar cases without the constraint of an a priori algorithm for risk stratification.The study included a convenience sample of 866 consecutive patients referred for myocardial function assessment (age 65 ± 17 years; 55.3% women; ejection fraction 60 ± 9%) for whom echocardiographic parameters of DD assessment were obtained per conventional guideline recommendations. Unsupervised, hierarchical cluster analysis of these parameters was conducted using the Ward linkage method. Major adverse cardiovascular events, hospitalization, and mortality were compared between conventional and cluster-based classifications.Clustering algorithms for screening the presence of DD in 559 of 866 patients identified 2 distinct groups and revealed modest agreement with conventional classification (kappa = 0.41, p 0.001). Further cluster analysis in 387 patients with DD helped to classify the severity of DD into 2 groups, with good agreement with conventional classification (kappa = 0.619, p 0.001). Survival analyses of patients assessed by both clustering algorithms for screening and grading DD showed improved prediction of event-free survival by clusters over conventional classification for all-cause mortality and cardiac mortality, even after accounting for a multivariable, balanced propensity score.An unsupervised assessment of echocardiographic variables for assessing LV DD revealed unique patterns of grouping. These natural patterns of clustering may better identify patient groups who have similar risk, and their incorporation into clinical practice may help eliminate indeterminate results and improve clinical outcome prediction.

The estimation of left ventricular (LV) filling pressure from the ratio of transmitral and annular velocities (E/e′) is used commonly for identifying diastolic dysfunction in patients who complain of exertional dyspnea [(1)][1]. We have recently illustrated that LV and left atrial speckle tracking

Limited understanding of the heterogeneity of heart failure with preserved ejection fraction (HFpEF) is a barrier to therapeutics. We studied the clinical and echocardiographic (echo) variations in HFpEF and their effect on clinical outcomes We retrospectively studied 556 HFpEF patients [Age: 66±

Objectives The aim of this study was to investigate whether cluster analysis of left atrial and left ventricular (LV) mechanical deformation parameters provide sufficient information for Doppler-independent assessment of LV diastolic function. Background Medical imaging produces substantial phenotyping data, and superior computational analyses could allow automated classification of repetitive patterns into patient groups with similar behavior. Methods The authors performed a cluster analysis and developed a model of LV diastolic function from an initial exploratory cohort of 130 patients that was subsequently tested in a prospective cohort of 44 patients undergoing cardiac catheterization. Patients in both study groups had standard echocardiographic examination with Doppler-derived assessment of diastolic function. Both the left ventricle and the left atrium were tracked simultaneously using speckle-tracking echocardiography (STE) for measuring simultaneous changes in left atrial and ventricular volumes, volume rates, longitudinal strains, and strain rates. Patients in the validation group also underwent invasive measurements of pulmonary capillary wedge pressure and LV end diastolic pressure immediately after echocardiography. The similarity between STE and conventional 2-dimensional and Doppler methods of diastolic function was investigated in both the exploratory and validation cohorts. Results STE demonstrated strong correlations with the conventional indices and independently clustered the patients into 3 groups with conventional measurements verifying increasing severity of diastolic dysfunction and LV filling pressures. A multivariable linear regression model also allowed estimation of E/e′ and pulmonary capillary wedge pressure by STE in the validation cohort. Conclusions Tracking deformation of the left-sided cardiac chambers from routine cardiac ultrasound images provides accurate information for Doppler-independent phenotypic characterization of LV diastolic function and noninvasive assessment of LV filling pressures.

We would like to thank Dr. Krittanawong and colleagues for the encouraging comment about our work on introducing machine learning for artificial intelligence (AI)–aided interpretation of cardiac imaging. The authors make an interesting proposition through introducing the emerging concept of deep

Unsupervised learning methods can find hidden patterns in data and uncover disease subphenotypes. We investigated unsupervised clustering of echocardiographic variables for grading diastolic dysfunction (DD) and test its concordance and prognostic performance in comparison with expert-guided

Background: Speckle tracking echocardiography (STE) derived left ventricular (LV) mechanical variables can vary based upon the severity LV diastolic dysfunction (DD) and filling pressures (LVFP). We sought to investigate the concordance between 2D-Doppler variables of DD suggested in 2016 American

Medical imaging in the era of precision medicine aims for accurate phenotyping of diseases that can benefit from early targeted therapies. We hypothesize that cardiac biomechanics generate high level of information that can leverage big data analytics and machine-learning frameworks for automated