rECHOmmend: An ECG-Based Machine Learning Approach for Identifying Patients at Increased Risk of Undiagnosed Structural Heart Disease Detectable by Echocardiography.

BACKGROUND: Timely diagnosis of structural heart disease improves patient outcomes, yet many remain underdiagnosed. While population screening with echocardiography is impractical, ECG-based prediction models can help target high-risk patients. We developed a novel ECG-based machine learning approach to predict multiple structural heart conditions, hypothesizing that a composite model would yield higher prevalence and positive predictive values to facilitate meaningful recommendations for echocardiography. METHODS: Using 2 232 130 ECGs linked to electronic health records and echocardiography reports from 484 765 adults between 1984 to 2021, we trained machine learning models to predict the presence or absence of any of 7 echocardiography-confirmed diseases within 1 year. This composite label included the following: moderate or severe valvular disease (aortic/mitral stenosis or regurgitation, tricuspid regurgitation), reduced ejection fraction <50%, or interventricular septal thickness >15 mm. We tested various combinations of input features (demographics, laboratory values, structured ECG data, ECG traces) and evaluated model performance using 5-fold cross-validation, multisite validation trained on 1 site and tested on 10 independent sites, and simulated retrospective deployment trained on pre-2010 data and deployed in 2010. RESULTS: Our composite rECHOmmend model used age, sex, and ECG traces and had a 0.91 area under the receiver operating characteristic curve and a 42% positive predictive value at 90% sensitivity, with a composite label prevalence of 17.9%. Individual disease models had area under the receiver operating characteristic curves from 0.86 to 0.93 and lower positive predictive values from 1% to 31%. Area under the receiver operating characteristic curves for models using different input features ranged from 0.80 to 0.93, increasing with additional features. Multisite validation showed similar results to cross-validation, with an aggregate area under the receiver operating characteristic curve of 0.91 across our independent test set of 10 clinical sites after training on a separate site. Our simulated retrospective deployment showed that for ECGs acquired in patients without preexisting structural heart disease in the year 2010, 11% were classified as high risk and 41% (4.5% of total patients) developed true echocardiography-confirmed disease within 1 year. CONCLUSIONS: An ECG-based machine learning model using a composite end point can identify a high-risk population for having undiagnosed, clinically significant structural heart disease while outperforming single-disease models and improving practical utility with higher positive predictive values. This approach can facilitate targeted screening with echocardiography to improve underdiagnosis of structural heart disease.

Deep Neural Networks Can Predict New-Onset Atrial Fibrillation From the 12-Lead ECG and Help Identify Those at Risk of Atrial Fibrillation-Related Stroke.

BACKGROUND: Atrial fibrillation (AF) is associated with substantial morbidity, especially when it goes undetected. If new-onset AF could be predicted, targeted screening could be used to find it early. We hypothesized that a deep neural network could predict new-onset AF from the resting 12-lead ECG and that this prediction may help identify those at risk of AF-related stroke. METHODS: We used 1.6 M resting 12-lead digital ECG traces from 430 000 patients collected from 1984 to 2019. Deep neural networks were trained to predict new-onset AF (within 1 year) in patients without a history of AF. Performance was evaluated using areas under the receiver operating characteristic curve and precision-recall curve. We performed an incidence-free survival analysis for a period of 30 years following the ECG stratified by model predictions. To simulate real-world deployment, we trained a separate model using all ECGs before 2010 and evaluated model performance on a test set of ECGs from 2010 through 2014 that were linked to our stroke registry. We identified the patients at risk for AF-related stroke among those predicted to be high risk for AF by the model at different prediction thresholds. RESULTS: The area under the receiver operating characteristic curve and area under the precision-recall curve were 0.85 and 0.22, respectively, for predicting new-onset AF within 1 year of an ECG. The hazard ratio for the predicted high- versus low-risk groups over a 30-year span was 7.2 (95% CI, 6.9-7.6). In a simulated deployment scenario, the model predicted new-onset AF at 1 year with a sensitivity of 69% and specificity of 81%. The number needed to screen to find 1 new case of AF was 9. This model predicted patients at high risk for new-onset AF in 62% of all patients who experienced an AF-related stroke within 3 years of the index ECG. CONCLUSIONS: Deep learning can predict new-onset AF from the 12-lead ECG in patients with no previous history of AF. This prediction may help identify patients at risk for AF-related strokes.

Routinely reported ejection fraction and mortality in clinical practice: where does the nadir of risk lie?

AIMS: We investigated the relationship between clinically assessed left ventricular ejection fraction (LVEF) and survival in a large, heterogeneous clinical cohort. METHODS AND RESULTS: Physician-reported LVEF on 403 977 echocardiograms from 203 135 patients were linked to all-cause mortality using electronic health records (1998-2018) from US regional healthcare system. Cox proportional hazards regression was used for analyses while adjusting for many patient characteristics including age, sex, and relevant comorbidities. A dataset including 45 531 echocardiograms and 35 976 patients from New Zealand was used to provide independent validation of analyses. During follow-up of the US cohort, 46 258 (23%) patients who had undergone 108 578 (27%) echocardiograms died. Overall, adjusted hazard ratios (HR) for mortality showed a u-shaped relationship for LVEF with a nadir of risk at an LVEF of 60-65%, a HR of 1.71 [95% confidence interval (CI) 1.64-1.77] when ≥70% and a HR of 1.73 (95% CI 1.66-1.80) at LVEF of 35-40%. Similar relationships with a nadir at 60-65% were observed in the validation dataset as well as for each age group and both sexes. The results were similar after further adjustments for conditions associated with an elevated LVEF, including mitral regurgitation, increased wall thickness, and anaemia and when restricted to patients reported to have heart failure at the time of the echocardiogram. CONCLUSION: Deviation of LVEF from 60% to 65% is associated with poorer survival regardless of age, sex, or other relevant comorbidities such as heart failure. These results may herald the recognition of a new phenotype characterized by supra-normal LVEF.

Frequency of coronary angiography and revascularization among men and women with myocardial infarction and their relationship to mortality at one year: an analysis of the Geisinger myocardial infarction cohort.

OBJECTIVES: To determine sex bias in the selection of strategies to evaluate patients with acute myocardial infarction (AMI), and determine if the choice of strategy influences survival. BACKGROUND: Controversy exists regarding the role of female sex in the use of invasive evaluation for AMI and its possible effect on adverse outcomes. METHODS: Electronic health record data from the Geisinger Acute Myocardial Infarction Cohort (GAMIC) was analyzed which included 1,968 men and 1,047 women admitted to the Geisinger Medical Center between January 2001 and December 2006 with acute myocardial infarction (AMI).Multivariate logistic regression analyses were used to determine independent correlates of an invasive evaluation. Multivariate logistic regression modeling stratified on sex was used to determine when invasive evaluation was done and whether there was a correlation with mortality. RESULTS: In unadjusted analyses, male sex was a significant predictor for the use of invasive evaluation (odds ratio = 1.71, 95% CI = [1.46, 2.00]). Adjusted for baseline differences (like age, renal function, co-morbid conditions) multivariate analyses found no significant relationship between male sex and invasive evaluation (OR = 1.02, 95% CI = [0.82, 1.23]). Females in the STEMI group were found to be less revascularized. No difference was observed in the one-year mortality between women and men regardless of invasive evaluation or revascularization. CONCLUSIONS: Sex was not independently associated with the occurrence of an invasive evaluation of a MI. Females in the STEMI group were less revascularized. There was no strong gender effect on survival irrespective of the performance on an invasive evaluation or revascularization.

P2Y12 antagonists in acute coronary syndrome: in whom should they be started, and when?

Acute coronary syndromes reflect a spectrum of disease related, most commonly, to the sudden reduction in blood flow to a portion of myocardium. The underlying pathogenesis of the reduction in coronary flow is related to the sudden rupture of an atherosclerotic plaque, with subsequent thrombus formation leading to either vascular occlusion or microembolization. Clinicians combat this process with antithrombotic therapy, which typically includes both anticoagulant and antiplatelet therapy, and mechanical therapies, such as percutaneous coronary interventions, nearly always using stents. This review focuses on P2Y12 antagonists as one component of our armamentarium of antiplatelet therapies, specifically on data addressing in whom, when, which agent, and in what dose such agents should be administered.

Deep-learning-assisted analysis of echocardiographic videos improves predictions of all-cause mortality.

Machine learning promises to assist physicians with predictions of mortality and of other future clinical events by learning complex patterns from historical data, such as longitudinal electronic health records. Here we show that a convolutional neural network trained on raw pixel data in 812,278 echocardiographic videos from 34,362 individuals provides superior predictions of one-year all-cause mortality. The model's predictions outperformed the widely used pooled cohort equations, the Seattle Heart Failure score (measured in an independent dataset of 2,404 patients with heart failure who underwent 3,384 echocardiograms), and a machine learning model involving 58 human-derived variables from echocardiograms and 100 clinical variables derived from electronic health records. We also show that cardiologists assisted by the model substantially improved the sensitivity of their predictions of one-year all-cause mortality by 13% while maintaining prediction specificity. Large unstructured datasets may enable deep learning to improve a wide range of clinical prediction models.

Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network.

The electrocardiogram (ECG) is a widely used medical test, consisting of voltage versus time traces collected from surface recordings over the heart1. Here we hypothesized that a deep neural network (DNN) can predict an important future clinical event, 1-year all-cause mortality, from ECG voltage-time traces. By using ECGs collected over a 34-year period in a large regional health system, we trained a DNN with 1,169,662 12-lead resting ECGs obtained from 253,397 patients, in which 99,371 events occurred. The model achieved an area under the curve (AUC) of 0.88 on a held-out test set of 168,914 patients, in which 14,207 events occurred. Even within the large subset of patients (n = 45,285) with ECGs interpreted as 'normal' by a physician, the performance of the model in predicting 1-year mortality remained high (AUC = 0.85). A blinded survey of cardiologists demonstrated that many of the discriminating features of these normal ECGs were not apparent to expert reviewers. Finally, a Cox proportional-hazard model revealed a hazard ratio of 9.5 (P < 0.005) for the two predicted groups (dead versus alive 1 year after ECG) over a 25-year follow-up period. These results show that deep learning can add substantial prognostic information to the interpretation of 12-lead resting ECGs, even in cases that are interpreted as normal by physicians.

A Machine Learning Approach to Management of Heart Failure Populations.

BACKGROUND: Heart failure is a prevalent, costly disease for which new value-based payment models demand optimized population management strategies. OBJECTIVES: This study sought to generate a strategy for managing populations of patients with heart failure by leveraging large clinical datasets and machine learning. METHODS: Geisinger electronic health record data were used to train machine learning models to predict 1-year all-cause mortality in 26,971 patients with heart failure who underwent 276,819 clinical episodes. There were 26 clinical variables (demographics, laboratory test results, medications), 90 diagnostic codes, 41 electrocardiogram measurements and patterns, 44 echocardiographic measurements, and 8 evidence-based "care gaps": flu vaccine, blood pressure of <130/80 mm Hg, A1c of <8%, cardiac resynchronization therapy, and active medications (active angiotensin-converting enzyme inhibitor/angiotensin II receptor blocker/angiotensin receptor-neprilysin inhibitor, aldosterone receptor antagonist, hydralazine, and evidence-based beta-blocker) were collected. Care gaps represented actionable variables for which associations with all-cause mortality were modeled from retrospective data and then used to predict the benefit of prospective interventions in 13,238 currently living patients. RESULTS: Machine learning models achieved areas under the receiver-operating characteristic curve (AUCs) of 0.74 to 0.77 in a split-by-year training/test scheme, with the nonlinear XGBoost model (AUC: 0.77) outperforming linear logistic regression (AUC: 0.74). Out of 13,238 currently living patients, 2,844 were predicted to die within a year, and closing all care gaps was predicted to save 231 of these lives. Prioritizing patients for intervention by using the predicted reduction in 1-year mortality risk outperformed all other priority rankings (e.g., random selection or Seattle Heart Failure risk score). CONCLUSIONS: Machine learning can be used to priority-rank patients most likely to benefit from interventions to optimize evidence-based therapies. This approach may prove useful for optimizing heart failure population health management teams within value-based payment models.

Predicting Survival From Large Echocardiography and Electronic Health Record Datasets: Optimization With Machine Learning.

OBJECTIVES: The goal of this study was to use machine learning to more accurately predict survival after echocardiography. BACKGROUND: Predicting patient outcomes (e.g., survival) following echocardiography is primarily based on ejection fraction (EF) and comorbidities. However, there may be significant predictive information within additional echocardiography-derived measurements combined with clinical electronic health record data. METHODS: Mortality was studied in 171,510 unselected patients who underwent 331,317 echocardiograms in a large regional health system. The authors investigated the predictive performance of nonlinear machine learning models compared with that of linear logistic regression models using 3 different inputs: 1) clinical variables, including 90 cardiovascular-relevant International Classification of Diseases, Tenth Revision, codes, and age, sex, height, weight, heart rate, blood pressures, low-density lipoprotein, high-density lipoprotein, and smoking; 2) clinical variables plus physician-reported EF; and 3) clinical variables and EF, plus 57 additional echocardiographic measurements. Missing data were imputed with a multivariate imputation by using a chained equations algorithm (MICE). The authors compared models versus each other and baseline clinical scoring systems by using a mean area under the curve (AUC) over 10 cross-validation folds and across 10 survival durations (6 to 60 months). RESULTS: Machine learning models achieved significantly higher prediction accuracy (all AUC >0.82) over common clinical risk scores (AUC = 0.61 to 0.79), with the nonlinear random forest models outperforming logistic regression (p < 0.01). The random forest model including all echocardiographic measurements yielded the highest prediction accuracy (p < 0.01 across all models and survival durations). Only 10 variables were needed to achieve 96% of the maximum prediction accuracy, with 6 of these variables being derived from echocardiography. Tricuspid regurgitation velocity was more predictive of survival than LVEF. In a subset of studies with complete data for the top 10 variables, multivariate imputation by chained equations yielded slightly reduced predictive accuracies (difference in AUC of 0.003) compared with the original data. CONCLUSIONS: Machine learning can fully utilize large combinations of disparate input variables to predict survival after echocardiography with superior accuracy.

Primary Purulent Pericarditis with Cardiac Tamponade due to Oropharyngeal Polymicrobial Infection: A Case Report and Literature Review.

Cardiac tamponade due to purulent pericarditis with a characteristic greenish fluid is rare in this antibiotic era. It is highly fatal despite early diagnosis and advanced treatment. Gram-positive cocci are the leading cause of purulent pericarditis, which usually results from a direct or hematogenous spread of organisms to the pericardium from the primary foci of infection. We describe an index case of rapidly developing pericardial tamponade caused by oropharyngeal polymicrobial infection in the absence of a primary source of infection in a 62-year-old man, who was successfully managed with emergency large-volume pericardiocentesis followed by pericardiectomy.

Is there a clinically significant interaction between calcium channel antagonists and clopidogrel?: results from the Clopidogrel for the Reduction of Events During Observation (CREDO) trial.

BACKGROUND: Clopidogrel is an inactive prodrug; it is converted to its active metabolite through the cytochrome P450 (CYP3A4) pathway, which also metabolizes calcium channel blockers (CCBs). Several studies have reported that CCBs reduce the ability of clopidogrel to inhibit platelet aggregability; one suggested that CCBs reduce the efficacy of clopidogrel. METHODS AND RESULTS: We performed a post hoc analysis of the Clopidogrel for the Reduction of Events During Observation (CREDO) study to compare the treatment effect of clopidogrel in patients on CCBs versus not on CCBs. In CREDO, 2116 patients were randomly assigned to pretreatment with 300 mg clopidogrel 3-24 hours before a planned percutaneous coronary intervention followed by 1 year of 75 mg/d clopidogrel, versus 75 mg clopidogrel at the time of the procedure and continued for 28 days only. The primary end points were a combined end point of death, myocardial infarction, and stroke at 28 days and 1 year. Among the 580 patients (27%) on CCBs at enrollment, at 28 days, the combined end point was reached in 17 patients (6%) on clopidogrel versus 28 (9%) on placebo (hazard ratio [HR], 0.71; 95% confidence interval [CI], 0.39-1.29). At 1 year, the combined end point was reached in 27 patients (10%) on clopidogrel versus 46 (15%) on placebo (HR, 0.68; 95% CI, 0.42-1.09). The treatment effect of clopidogrel was similar in patients not on CCBs at 1 year (HR, 0.78; 95% CI, 0.56-1.09). After adjustment for differences between patients on and not on CCB, there was still no evidence of an interaction between clopidogrel treatment and CCB (HR for patients not on CCBs, 0.87; 95% CI, 0.62-1.23; HR for patients on CCBs, 0.74; 95% CI, 0.45-1.21). CONCLUSIONS: In CREDO, there was no evidence that CCBs decrease the efficacy of clopidogrel.

Feasibility and safety of ad hoc percutaneous coronary intervention in the modern era.

BACKGROUND: The frequency of ad hoc percutaneous coronary intervention (PCI) varies among institutions and regions of the country. It is unclear what factors limit use of the ad hoc strategy. OBJECTIVE: To define factors which limit the use of the ad hoc strategy. METHODS: All patients who underwent PCI at our center in 2004 were reviewed. Patients who had emergent PCI for ST-elevation myocardial infarction (n = 188), those who had undergone diagnostic coronary angiography at a referring facility (n = 54), and those who had a repeat PCI after a previous ad hoc PCI (n = 19) were excluded. PCIs performed the same day as diagnostic angiography were considered "ad hoc"; all others were designated "staged". Demographic and procedural factors through hospital discharge were prospectively recorded. Logistic regression analysis was performed to identify correlates of ad hoc PCI, PCI success, and PCI complications. RESULTS: Of the 580 PCI procedures eligible for analysis, 557 (96%) were ad hoc and 23 (4%) were staged. Patients undergoing staged PCI had more lesions treated, a higher rate of no-reflow and periprocedural myocardial infarction, and higher contrast volumes and fluoroscopic times. Logistic regression analysis revealed that patients with history of heart failure, renal insufficiency and a recent myocardial infarction were more likely to undergo a staged PCI. Patients undergoing a staged PCI and those who had previous bypass surgery were more likely to have an unsuccessful PCI procedure. CONCLUSION: Most PCI procedures can be performed safely and effectively on the same day as diagnostic coronary angiography.