Search

Purpose: Electrocardiography (ECG)-derived machine learning models can predict echocardiography (echo)-derived indices of systolic or diastolic function. However, systolic and diastolic dysfunction frequently coexists, which necessitates an integrated assessment for optimal risk-stratification. We explored an ECG-derived model that emulates an echo-derived model that combines multiple parameters for identifying patient phenogroups at risk for major adverse cardiac events (MACE)., Methods: In this substudy of a prospective, multicenter study, patients from 3 institutions (n=727) formed an internal cohort, and the fourth institution was reserved as an external test set (n=518). A previously validated patient similarity analysis model was used for labeling the patients as low-/high-risk phenogroups. These labels were utilized for training an ECG-derived deep neural network model to predict MACE risk per phenogroup. After 5-fold cross-validation training, the model was tested on the reserved external dataset., Results: Our ECG-derived model showed robust classification of patients, with area under the receiver operating characteristic curve of 0.86 (95% CI: 0.79-0.91) and 0.84 (95% CI: 0.80-0.87), sensitivity of 80% and 76%, and specificity of 88% and 75% for the internal and external test sets, respectively. The ECG-derived model demonstrated an increased probability for MACE in high-risk vs low-risk patients (21% vs 3%; P<0.001), which was similar to the echo-trained model (21% vs 5%; P<0.001), suggesting comparable utility., Conclusions: This novel ECG-derived machine learning model provides a cost-effective strategy for predicting patient subgroups in whom an integrated milieu of systolic and diastolic dysfunction is associated with a high risk of MACE., Competing Interests: Conflicts of Interest Partho Sengupta is a consultant for Kencor Health, Ultromics, and RCE technologies. All other authors have no conflicts of interest to disclose., (© 2022 Aurora Health Care, Inc.)

Objectives: We aimed to assess the in-hospital outcomes in patients with mitral regurgitation treated with percutaneous mitral valve repair (PMVR) among patients with chronic obstructive pulmonary disease (COPD)., Background: There is lack of data on the outcomes of PMVR for mitral regurgitation in patients with COPD., Methods: We analyzed the national inpatient sample (NIS) database from January 2012 to December 2016., Results: A total of 9125 patients underwent PMVR in the period between January 2012 and December 2016, of whom 2,495 (27.3%) patients had concomitant COPD. Comparing COPD patients to non-COPD patients, COPD patients had higher proportion of females (48.3% vs. 46.6%, p = .16), were younger (75.8 ± 10.0 years vs. 76.4 ± 12.2 years; p = .04), had higher prevalence of peripheral vascular disease (17.4% vs. 13.5%; p < .01) and renal failure (39.3% vs. 37%; p < .01). After propensity matching, there was no significant difference in mortality among the COPD group versus non-COPD patients (2.6% vs. 2.9%; p = .6). Patients with COPD had higher proportion of in-hospital morbidities including St-segment elevation myocardial infarction (1.8% vs. 1.0%; p = .02), cardiogenic shock (1.4% vs. 0.4%; p < .01), vascular complications (2% vs. 0.8; p < .01), pneumothorax (1% vs. 0.4%; p < .01), and septic shock (1.2% vs. 0.4%; p < .01). Moreover, surrogates of severe disability (mechanical intubation and non-home discharges), cost of hospitalization, and length of stay were higher in the COPD group., Conclusions: There was no difference in mortality between the COPD and non-COPD patients after PMVR. Moreover, we observed higher rates of in-hospital morbidities, surrogates of severe disability, and higher resources utilization by the COPD group., (© 2020 Wiley Periodicals, Inc.)

In this current digital landscape, artificial intelligence (AI) has established itself as a powerful tool in the commercial industry and is an evolving technology in healthcare. Cutting-edge imaging modalities outputting multi-dimensional data are becoming increasingly complex. In this era of data explosion, the field of cardiovascular imaging is undergoing a paradigm shift toward machine learning (ML) driven platforms. These diverse algorithms can seamlessly analyze information and automate a range of tasks. In this review article, we explore the role of ML in the field of cardiovascular imaging., Competing Interests: PS was a consultant for HeartSciences and Ultromics. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2020 Seetharam, Brito, Farjo and Sengupta.)

Background: Cardiovascular disease is the major cause of mortality in end stage renal disease (ESRD) patients on dialysis and myocardial infarction constitutes almost 20% of such deaths. We assessed the trends, characteristics and in-hospital outcomes in patients with ESRD., Methods: We used national inpatient sample (NIS) to identify patients with ESRD presenting with ST-segment elevation myocardial infarction (STEMI) for calendar years 2012-2016. Multiple logistic regression analysis and propensity matched data was used to compare outcomes for the purpose of our study., Results: Patients on dialysis who presented with STEMI were less likely to be treated with emergent reperfusion therapies including percutaneous coronary intervention, bypass graft surgery and thrombolytics with in first 24 h. In propensity-matched cohort, the mortality was nearly double in patients who have ESRD compared to patients without ESRD (29.7% vs. 15.9%, p < 0.01). In-patient morbidity such as utilization of tracheostomy, mechanical ventilation and feeding tubes was also more prevalent in propensity matched ESRD cohort. In multivariate regression analysis, ESRD remains a strong predictor of increased mortality in STEMI patients (OR 2.65, 95% CI, 2.57-2.75, p < 0.01)., Conclusion: Our study showed low utilization of evidence-based prompt reperfusion therapies in ESRD patients with STEMI along with concomitant increased poor outcomes and resource utilization. Future research specifically targeting this extremely high-risk patient population is needed to identify the role of prompt reperfusion therapies in improving outcomes in these patients., Competing Interests: Declaration of competing interest No disclosures., (Copyright © 2020 Elsevier Inc. All rights reserved.)

Aims: Coronary artery calcium (CAC) scoring is an established tool for cardiovascular risk stratification. However, the lack of widespread availability and concerns about radiation exposure have limited the universal clinical utilization of CAC. In this study, we sought to explore whether machine learning (ML) approaches can aid cardiovascular risk stratification by predicting guideline recommended CAC score categories from clinical features and surface electrocardiograms., Methods and Results: In this substudy of a prospective, multicentre trial, a total of 534 subjects referred for CAC scores and electrocardiographic data were split into 80% training and 20% testing sets. Two binary outcome ML logistic regression models were developed for prediction of CAC scores equal to 0 and ≥400. Both CAC = 0 and CAC ≥400 models yielded values for the area under the curve, sensitivity, specificity, and accuracy of 84%, 92%, 70%, and 75%, and 87%, 91%, 75%, and 81%, respectively. We further tested the CAC ≥400 model to risk stratify a cohort of 87 subjects referred for invasive coronary angiography. Using an intermediate or higher pretest probability (≥15%) to predict CAC ≥400, the model predicted the presence of significant coronary artery stenosis ( P  = 0.025), the need for revascularization ( P  < 0.001), notably bypass surgery ( P  = 0.021), and major adverse cardiovascular events ( P  = 0.023) during a median follow-up period of 2 years., Conclusion: ML techniques can extract information from electrocardiographic data and clinical variables to predict CAC score categories and similarly risk-stratify patients with suspected coronary artery disease., (© The Author(s) 2020. Published by Oxford University Press on behalf of the European Society of Cardiology.)

Background: Left ventricular (LV) diastolic dysfunction is recognized as playing a major role in the pathophysiology of heart failure; however, clinical tools for identifying diastolic dysfunction before echocardiography remain imprecise., Objectives: This study sought to develop machine-learning models that quantitatively estimate myocardial relaxation using clinical and electrocardiography (ECG) variables as a first step in the detection of LV diastolic dysfunction., Methods: A multicenter prospective study was conducted at 4 institutions in North America enrolling a total of 1,202 subjects. Patients from 3 institutions (n = 814) formed an internal cohort and were randomly divided into training and internal test sets (80:20). Machine-learning models were developed using signal-processed ECG, traditional ECG, and clinical features and were tested using the test set. Data from the fourth institution was reserved as an external test set (n = 388) to evaluate the model generalizability., Results: Despite diversity in subjects, the machine-learning model predicted the quantitative values of the LV relaxation velocities (e') measured by echocardiography in both internal and external test sets (mean absolute error: 1.46 and 1.93 cm/s; adjusted R 2 = 0.57 and 0.46, respectively). Analysis of the area under the receiver operating characteristic curve (AUC) revealed that the estimated e' discriminated the guideline-recommended thresholds for abnormal myocardial relaxation and diastolic and systolic dysfunction (LV ejection fraction) the internal (area under the curve [AUC]: 0.83, 0.76, and 0.75) and external test sets (0.84, 0.80, and 0.81), respectively. Moreover, the estimated e' allowed prediction of LV diastolic dysfunction based on multiple age- and sex-adjusted reference limits (AUC: 0.88 and 0.94 in the internal and external sets, respectively)., Conclusions: A quantitative prediction of myocardial relaxation can be performed using easily obtained clinical and ECG features. This cost-effective strategy may be a valuable first clinical step for assessing the presence of LV dysfunction and may potentially aid in the early diagnosis and management of heart failure patients., (Copyright © 2020 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.)

Uncontrolled type II diabetes mellitus (DM) using single point hemoglobin A1c levels has been associated with poor cardiovascular outcomes. However, methods to quantify the effect of uncontrolled DM over time have been inconsistent. To quantify hyperglycemia over time and assess its cardiovascular effects we developed and tested a DM burden score which accounts for time in years prior to DM diagnosis, diagnostic HbA1c, and aggregate HbA1c levels thereafter. A retrospective cohort study was performed with patients (n = 188) from a single academic center with type II DM and no prior cardiac disease history. Patient scores were calculated from diagnosis until the year 2015 and were grouped into low (<5.3%; n = 55), moderate (5.3% to 5.5%; n = 80), and high (>5.5%; n = 53) DM burden score cohorts. At 48 months, the cohort with high DM burden scores correlated with significantly worse major adverse cardiovascular events (hazard ratio [HR] 3.07, p = 0.012), myocardial infarction (HR 12.78, p = 0.015), coronary revascularization (HR 4.53, p = 0.019), cardiovascular hospitalizations (HR 4.20, p = 0.005), and all-cause hospitalizations (HR 2.57, p = 0.01). Cardiovascular and all-cause mortality showed significant difference between groups in log-rank testing. Also, a multivariate regression model showed DM burden score (p = 0.045) to be an independent predictor of major adverse cardiovascular events (HR 9.38, p = 0.045). In conclusion, this study provides evidence that DM control over time impacts cardiovascular outcomes., (Copyright © 2020 Elsevier Inc. All rights reserved.)

A strategy of complete revascularization (CR) versus infarct-related artery revascularization (IRA) in patients with ST-elevation myocardial infarction (STEMI) continues to be a subject of debate. We performed an updated meta-analysis to compare the 2 strategies. Outcomes of interest included major adverse cardiovascular events (MACE), cardiovascular mortality, all-cause mortality, stroke, repeat revascularization, myocardial infarction, and contrast-induced nephropathy. Ten randomized trials including 7,423 patients (CR = 3,574 and IRA = 3,849), with a follow-up of 2.0 ± 0.8 years were included. There was a significant reduction in MACE with CR versus IRA (10.7% vs 18.6%, relative risk [RR] 0.64, 95% confidence interval [CI] 0.51 to 0.81, p = 0.002, I 2  = 66%), with higher risk reduction with immediate versus stages revascularization (RR 0.40, 95% CI 0.32 to 0.5 vs RR 0.69, 95% CI 0.54 to 0.89, P-interaction = 0.002). Complete revascularization was associated with lower rates of repeat revascularization (4.0% vs 11.7%, RR 0.44, 95% CI 0.28 to 0.70, p <0.0001, I 2  = 81%), and a nonsignificant trend toward lower cardiovascular mortality (2.8% vs 3.7%, RR 0.78, 95% CI 0.60 to 1.03, p = 0.08, I 2  = 0%). However, there was no difference between the 2 strategies in all-cause mortality (4.6% vs 4.8%, RR 0.90, 95% CI 0.73 to 1.12, p = 0.36, I 2  = 0%), myocardial infarction (5.2% vs 6.5%, RR 0.73, 95% CI, 0.58 to 1.08, p = 0.08, I 2  = 30%), stroke (1.5% vs 1.2%, RR 1.14, 95% CI 0.56 to 2.29, p = 0.33, I 2  = 14%), or contrast-induced nephropathy (1.6% vs 1.2%, RR 1.35, 95% CI 0.85 to 2.15, p = 0.78, I 2  = 0%). In conclusion, CR in patients with STEMI is associated with significant reduction in MACE compared with IRA. This reduction is derived mainly by the low rates of repeat revascularization in the CR group., (Copyright © 2019 Elsevier Inc. All rights reserved.)

There is still a debate about the safety and efficacy of an aspirin free strategy after percutaneous coronary intervention (PCI). Hence, we performed a meta-analysis comparing aspirin free strategy to dual antiplatlets therapy (DAPT). Randomized trials (RCTs) comparing aspirin free strategy to DAPT in patients who received PCI were included. The primary outcome of interest was bleeding, defined per the Bleeding Academic Research Consortium (BARC). Secondary outcomes included major adverse cardiovascular and cerebrovascular events (MACE); defined as all-cause mortality, myocardial infarction or stroke, the individual component of MACE and stent thrombosis. A total of 4 RCTs with 29,089 patients were included. There was significant reduction in BARC 2,3 or 5 bleeding events in patients who were treated with aspirin free strategy versus DAPT (HR 0.61, 95% CI 0.39-, p = 0.03, I 2  = 89%). Moreover, although there was a trend of reduced major bleeding (BARC 3 or 5) outcomes in the aspirin free strategy group compared to the DAPT group, this did not achieve statistical significance (HR 0.63, 95% CI 0.37-1.06, p = 0.08, I 2  = 795). Additionally, there was no difference between the aspirin free strategy and DAPT in term of MACE (HR 0.92, 95% CI 0.82-1.03, p = 0.13, I 2  = 0%), all-cause mortality (HR 0.89, 95% CI 0.77-1.04, p = 0.15, I 2  = 0%), MI (HR 0.89, 95% CI 0.74-1.08, p = 0.24, I 2  = 0%), stroke (HR 1.13, 95% CI 0.65-1.99, p = 0.66, I 2  = 60%) or stent thrombosis (HR 0.1.01, 95% CI 0.83-1.22, p = 0.93, I 2  = 0%). Aspirin free strategy is as effective as DAPT in reducing MACE with better safety profile in term of bleeding.

Heart failure with preserved ejection fraction (HFpEF) is a complex clinical entity that is poorly understood yet present in up to 5.5% of the general population. Proven therapies for this disorder are lacking, even though it has a similar prognosis to that of heart failure with reduced ejection fraction (HFrEF). Innovative imaging techniques have provided in-depth understanding of the unique pattern of left ventricular mechanics in patients with HFpEF who progress through preclinical (Stages A to B) and clinical (Stages C to D) American College of Cardiology/American Heart Association heart failure stages. This review highlights the mechanical basis of this disorder from the cellular and myofiber level to chamber dysfunction. As each chamber of the heart is examined, specific biomarkers and echocardiographic parameters with diagnostic and prognostic values are discussed. Finally, novel phenotyping methods including machine learning are reviewed that integrate these mechanics into clinical groups to advise and treat patients., (Copyright © 2020 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.)