Abstract
In the recent decade, deep learning, a subset of artificial intelligence and machine learning, has been used to identify patterns in big healthcare datasets for disease phenotyping, event ...predictions, and complex decision making. Public datasets for electrocardiograms (ECGs) have existed since the 1980s and have been used for very specific tasks in cardiology, such as arrhythmia, ischemia, and cardiomyopathy detection. Recently, private institutions have begun curating large ECG databases that are orders of magnitude larger than the public databases for ingestion by deep learning models. These efforts have demonstrated not only improved performance and generalizability in these aforementioned tasks but also application to novel clinical scenarios. This review focuses on orienting the clinician towards fundamental tenets of deep learning, state-of-the-art prior to its use for ECG analysis, and current applications of deep learning on ECGs, as well as their limitations and future areas of improvement.
Aims
Individuals with supranormal left ventricular ejection fraction (snLVEF; LVEF >70%) have increased mortality. However, the genetic and phenotypic profile of snLVEF remains unknown. This study ...aimed to determine the relationship of both snLVEF genetic risk and phenotype with survival and underdiagnosed heart failure (HF).
Methods and results
A snLVEF genetic risk score (GRS) was applied and cases of snLVEF were identified in 486 754 individuals across two population‐based cohorts (BioMe Biobank and UK Biobank). The snLVEF GRS and phenotype were evaluated for association with survival, as well as HF diagnosis, markers, symptoms, and medications. Of 486 754 participants, the median age was 58 years, 20 069 (4.1%) died, and 10 088 (2.1%) had diagnosed HF. Both snLVEF GRS (hazard ratio HR 1.1 for top 10% vs. bottom 10% GRS; p = 0.002) and phenotype (HR 1.4; p = 0.003) were associated with increased all‐cause mortality. Both snLVEF GRS and phenotype were associated with reduced HF diagnosis (odds ratio OR 0.97 and OR 0.63, respectively; both p ≤0.002). However, the snLVEF GRS and phenotype were both associated with elevated brain natriuretic peptide (BNP) levels (146 and 185 pg/ml increase, respectively; p <0.001), including 268 out of 455 (59%) individuals with snLVEF phenotype who had BNP >100 pg/ml. Among 476 666 participants without HF diagnoses, snLVEF GRS and phenotype were associated with increased HF symptoms (e.g. exertional dyspnoea OR 1.4 and OR 1.3; p <0.003) and HF medications (e.g. loop diuretic OR 1.2 and OR 1.03; p <0.02). Associations were consistent in hypertensive individuals without cardiac comorbidities.
Conclusions
Genetic predisposition to and presence of snLVEF are associated with decreased survival and underdiagnosed HF.
Graphical of the study of supranormal left ventricular ejection fraction (snLVEF) in two biobanks. The study assessed the genetic and phenotypic characteristics of snLVEF. Sixteen genetic variants were found in a genome‐wide association study to be associated with snLVEF and were incorporated into a genetic risk score (GRS). Both snLVEF GRS and phenotype were associated with increased hazard ratio (HR) for mortality, including in heart failure (HF) and hypertension subgroups. Both snLVEF GRS and phenotype were associated with reduced odds ratio (OR) for HF diagnosis, but increased brain natriuretic peptide (BNP) levels and increased OR for HF symptoms and medications. Individuals with a genetic predisposition or phenotype of snLVEF have worse survival and may be underdiagnosed for HF. Further study is needed to define snLVEF in clinical guidelines for HF diagnosis and risk stratification.
The potential relevance of blood flow for describing cardiac function has been known for the past 2 decades, but the association of clinical parameters with the complexity of fluid motion is still ...not well understood. Hemodynamic force (HDF) analysis represents a promising approach for the study of blood flow within the ventricular chambers through the exploration of intraventricular pressure gradients. Previous experimental studies reported the significance of invasively measured cardiac pressure gradients in patients with heart failure. Subsequently, advances in cardiovascular imaging allowed noninvasive assessment of pressure gradients during progression and resolution of ventricular dysfunction and in the setting of resynchronization therapy. The HDF analysis can amplify mechanical abnormalities, detect them earlier compared with conventional ejection fraction and strain analysis, and possibly predict the development of cardiac remodeling. Alterations in HDFs provide the earliest signs of impaired cardiac physiology and can therefore transform the existing paradigm of cardiac function analysis once implemented in routine clinical care. Until recently, the HDF investigation was possible only with contrast-enhanced echocardiography and magnetic resonance imaging, precluding its widespread clinical use. A mathematical model, based on the first principle of fluid dynamics and validated using 4-dimensional-flow-magnetic resonance imaging, has allowed HDF analysis through routine transthoracic echocardiography, making it more readily accessible for routine clinical use. This article describes the concept of HDF analysis and reviews the existing evidence supporting its application in several clinical settings. Future studies should address the prognostic importance of HDF assessment in asymptomatic patients and its incorporation into clinical decision pathways.
Background:
A shorter sleep duration has been identified as a risk factor for cardiovascular diseases and increased mortality. It has been hypothesized that a short sleep duration may be linked to ...changes in ghrelin and leptin production, leading to an alteration of stress hormone production. Here, we conducted a systematic review and meta-analysis to investigate the potential relationship between a sleep duration and cardiovascular disease mortality.
Methods:
We conducted a comprehensive search of Ovid Medline In-Process and other non-indexed citations, Ovid MEDLINE, Ovid Embase, Ovid Cochrane Central Register of Controlled Trials, and Scopus from database inception to March 2017. Observational studies were included if the studies reported hazard ratios or odds ratios of the associations between sleep durations (short and long) and cardiovascular disease mortality. Data were extracted by a reviewer and then reviewed by two separate reviewers. Conflicts were resolved through consensus. Using the DerSimonian and Laird random effects models, we calculated pooled hazard ratios and pooled odds ratios with 95% confidence intervals (CI). Subgroup analyses were performed to explore potential sources of heterogeneity. The quality of the included studies and publication bias were assessed.
Results:
In total, our meta-analysis included 19 studies (31 cohorts) with a total of 816,995 individuals with 42,870 cardiovascular disease mortality cases. In pooled analyses, both short (risk ratio 1.19; 95% CI 1.13 to 1.26, P<0.001, I2=30.7, Pheterogeneity=0.034), and long (risk ratio 1.37; 95% CI 1.23 to 1.52, P<0.001, I2=79.75, Pheterogeneity<0.001) sleep durations were associated with a greater risk of cardiovascular disease mortality.
Conclusions:
Both short (<7 hours) and long sleep durations (>9 hours) can increase the risk of overall cardiovascular disease mortality, particularly in Asian populations and elderly individuals. Future epidemiological studies would ideally include objective sleep measurements, rather than self-report measures, and all potential confounders, such as genetic variants.
Abstract Several common misconceptions can make the clinical diagnosis of subacute pericardial tamponade challenging. Widely known physical findings of pericardial tamponade lack sensitivity and ...specificity. Interpretation of echocardiographic signs requires good understanding of pathophysiology. Over-reliance on echocardiography may result in over-utilization of pericardial drainage procedures. Awareness of these misconceptions with an integrative approach to both clinical and imaging data will help clinicians to assess the hemodynamic impact of pericardial effusion and the need for drainage.
Atherosclerotic Burden Argulian, Edgar, MD, MPH
Journal of the American College of Cardiology,
06/2015, Letnik:
65, Številka:
22
Journal Article
Recenzirano
Odprti dostop
In another study of 541 patients with suspected coronary disease undergoing coronary computed tomography (CT) angiography and single-photon emission computed tomography (SPECT) myocardial perfusion ...imaging (MPI), anatomic and functional information was synergistic (2).
It has been believed that most acute coronary events result from the rupture of mildly stenotic plaques, based on studies in which angiographic information was available from many months to years ...before the event. However, serial studies in which angiographic data were available from the past as also within 1 to 3 months of myocardial infarction have clarified that nonobstructive lesions progressively enlarged relatively rapidly before the acute event occurred. Noninvasive computed tomography angiography imaging data have confirmed that lesions that did not progress voluminously over time rarely led to events, regardless of the extent of luminal stenosis or baseline high-risk plaque morphology. Therefore, plaque progression could be proposed as a necessary step between early, uncomplicated atherosclerosis and plaque rupture. On the other hand, it has been convincingly demonstrated that intensive lipid-lowering therapy (to a low-density lipoprotein cholesterol level of <70 mg/dl) halts plaque progression. Given the current ability to noninvasively detect the presence of early atherosclerosis, the importance of plaque progression in the pathogenesis of myocardial infarction, and the efficacy of maximum lipid-lowering therapy, it has been suggested that plaque progression is a modifiable step in the evolution of atherosclerotic plaque. A personalized approach based on the detection of early atherosclerosis can trigger the necessary treatment to prevent plaque progression and hence plaque instability. Therefore, this approach can redefine the traditional paradigm of primary and secondary prevention based on population-derived risk estimates and can potentially improve long-term outcomes.
Display omitted
•The majority of coronary artery events occur as a result of plaque rupture.•Plaque progression is a necessary but modifiable step between subclinical atherosclerosis and plaque rupture.•Subclinical atherosclerosis can be conveniently detected with noninvasive imaging.•Intensive lipid-lowering therapy can halt plaque progression and should reduce events.
Abstract Background Evidence-based and age-appropriate antihypertensive pharmacotherapy in outpatient settings is essential for optimal treatment outcomes. Recent guidelines, although controversial, ...recommended different blood pressure goals using age cutoff of 60 years. We describe recent age-specific national trends in antihypertensive prescribing patterns and blood pressure control in US office-based practices. Methods We analyzed all hypertension-related visits to physician offices from the latest available National Ambulatory Medical Care Survey (2003-2010). We identified trends of antihypertensive prescribing overall and by class, trends of hypertension control, age differences in antihypertensive prescribing patterns and hypertension control, predicted probabilities of hypertension control in subgroups, and correlates of hypertension control. Results There were 16,729 physician office visits included in the analysis. Overall, the prescription of antihypertensive medication increased from 69.2% in 2003-2004 to 78.8% in 2009-2010 ( Ptrend = .001), and the increased trend was consistent in both age groups (<60 and ≥60 years). This was accompanied by an improvement in the overall hypertension control (from 39.1% to 48.8%, Ptrend <.001). Antihypertensive prescribing patterns differ significantly between the 2 age groups. The proportions of visits with β-blocker (from 25.4% to 34.7%, Ptrend <.001) and angiotensin receptor blocker prescriptions (from 17.0% to 22.1%, Ptrend = .042) increased for older patients. The increased trend of β-blocker use persisted after excluding patients with compelling indications. Among treated patients, lower odds of blood pressure control were associated with African American race, presence of comorbidities, younger age, and insufficient insurance coverage. Conclusions In office-based practices, antihypertensive medication prescribing among US adults with hypertension increased significantly in recent years, which was accompanied by improvement in hypertension control. The prescribing patterns differed among younger and older patients, but continuous use of β-blockers without other compelling indications raises concerns.
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.
This study sought to assess the impact of systolic variation of mitral regurgitation (MR) has on discordance between echocardiography and magnetic resonance imaging (MRI).
Studies have shown ...discordance between echocardiography and MRI when assessing the severity of MR. Contributing factors to this discordance may include the systolic variation of MR and the use of the color Doppler jet at a single point in time as the basis of many echocardiographic methods.
This analysis included 117 patients (62 ± 14 years of age; 58% male) with MR who underwent echocardiographic and MRI evaluation. Discordance was defined as the difference between the grades of MR (mild, moderate, or severe) by MRI and echocardiography. For each patient, 2 echocardiographic methods, the continuous wave time index and the color Doppler time index, and 1 MRI method, the systolic variation score (SVS), were measured to quantify systolic variation of MR.
There was absolute agreement between echocardiography and MRI in 47 (40%) patients, a 1-grade difference in 54 (46%) patients, and a 2-grade difference in 16 (14%) patients. Only the SVS significantly differed between patients with and without discordance (0.60 ± 0.23 vs. 0.47 ± 0.21; p = 0.003). On receiver-operating characteristic analysis SVS had moderate predictive power of discordance (area under the curve: 0.67; p = 0.003), with an SVS of 53 having a sensitivity of 61% and a specificity of 65% to predict discordance.
Discordance between MRI and echocardiographic assessment of MR severity is associated with systolic variation of MR as quantified by MRI using the SVS. Continuous wave Doppler and the presence of color Doppler were not correlated with discordance. This study highlights an advantage of MRI. Namely, it does not rely on a single point in time to determine MR severity. Because systolic variation had only moderate sensitivity and specificity for predicting discordance, other factors are also responsible for the discordance between the 2 techniques.
Display omitted