Clinical Trial Participation and COVID-19: a Descriptive Analysis from the American Heart Association's Get With The Guidelines Registry.

As COVID-19 cases begin to decrease in the USA, learning from the pandemic experience will provide insights regarding disparities of care delivery. We sought to determine if specific populations hospitalized with COVID-19 are equally likely to be enrolled in clinical trials. We examined patients hospitalized with COVID-19 at centers participating in the American Heart Association's COVID-19 CVD Registry. The primary outcome was odds of enrollment in a clinical trial, according to sex, race, and ethnicity. Among 14,397 adults hospitalized with COVID-19, 9.5% (n = 1,377) were enrolled in a clinical trial. The proportion of enrolled patients was the lowest for Black patients (8%); in multivariable analysis, female and Black patients were less likely to be enrolled in a clinical trial related to COVID-19 compared to men and other racial groups, respectively. Determination of specific reasons for the disparities in trial participation related to COVID-19 in these populations should be further investigated.

Relationships between 2018 UNOS heart policy and transplant outcomes in metropolitan, micropolitan, and rural settings.

BACKGROUND: In 2018, United Network for Organ Sharing (UNOS) extended the radius for which a heart transplant candidate can match with a donor, and outcomes across population densities are unknown. We sought to determine whether the policy change was associated with differences in heart transplant waitlist time or death post-transplant for patients from rural, micropolitan, and metropolitan settings. METHODS: Using the Scientific Registry of Transplant Recipients, we evaluated U.S. adult patients listed for heart transplant from Janurary 2017 to September 2019 with follow-up through March 2020. Patients were stratified by home zip-codes to either metropolitan, micropolitan, or rural settings. Fine and Gray and Cox models were respectively used to estimate Sub-distribution hazard ratios (SHR) of heart transplant with death or removal from transplant list as a competing event, and HR of death post-transplant within population densities after versus before the UNOS policy change date, October 18, 2018. Analyses were adjusted for demographics, comorbidities, and labs. RESULTS: Among 8,747 patients listed for heart transplant, 84.7% were from metropolitan, 8.6% micropolitan, and 6.6% rural settings. The 2018 UNOS policy was associated with earlier receipt of heart transplant for metropolitan [SHR 1.56 (95% CI: 1.46-1.66)] and micropolitan [SHR 1.48 (95% CI: 1.21-1.82)] populations, but not significantly for rural [SHR 1.20 (95% CI: 0.93-1.54)]; however, the interaction between policy and densities was not significant (p = .14). Policy changes were not associated with risk of death post-transplant [metropolitan: HR 1.04 (95% CI: 0.80-1.34); micropolitan: HR 1.10 (95% CI: 0.55-2.23); rural: HR 1.04 (95% CI: 0.52-2.08); interaction p = .99]. CONCLUSIONS: The 2018 UNOS heart transplant policy was associated with earlier receipt of heart transplant and no difference in post-transplant survival within population densities. Additional follow-up is needed to determine whether improvements are sustained.

An explainable artificial intelligence approach for predicting cardiovascular outcomes using electronic health records.

Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children's Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyses.

Utilizing Artificial Intelligence to Enhance Health Equity Among Patients with Heart Failure.

Patients with heart failure (HF) are heterogeneous with various intrapersonal and interpersonal characteristics contributing to clinical outcomes. Bias, structural racism, and social determinants of health have been implicated in unequal treatment of patients with HF. Through several methodologies, artificial intelligence (AI) can provide models in HF prediction, prognostication, and provision of care, which may help prevent unequal outcomes. This review highlights AI as a strategy to address racial inequalities in HF; discusses key AI definitions within a health equity context; describes the current uses of AI in HF, strengths and harms in using AI; and offers recommendations for future directions.

Information Extraction From Electronic Health Records to Predict Readmission Following Acute Myocardial Infarction: Does Natural Language Processing Using Clinical Notes Improve Prediction of Readmission?

Background Social risk factors influence rehospitalization rates yet are challenging to incorporate into prediction models. Integration of social risk factors using natural language processing (NLP) and machine learning could improve risk prediction of 30-day readmission following an acute myocardial infarction. Methods and Results Patients were enrolled into derivation and validation cohorts. The derivation cohort included inpatient discharges from Vanderbilt University Medical Center between January 1, 2007, and December 31, 2016, with a primary diagnosis of acute myocardial infarction, who were discharged alive, and not transferred from another facility. The validation cohort included patients from Dartmouth-Hitchcock Health Center between April 2, 2011, and December 31, 2016, meeting the same eligibility criteria described above. Data from both sites were linked to Centers for Medicare & Medicaid Services administrative data to supplement 30-day hospital readmissions. Clinical notes from each cohort were extracted, and an NLP model was deployed, counting mentions of 7 social risk factors. Five machine learning models were run using clinical and NLP-derived variables. Model discrimination and calibration were assessed, and receiver operating characteristic comparison analyses were performed. The 30-day rehospitalization rates among the derivation (n=6165) and validation (n=4024) cohorts were 15.1% (n=934) and 10.2% (n=412), respectively. The derivation models demonstrated no statistical improvement in model performance with the addition of the selected NLP-derived social risk factors. Conclusions Social risk factors extracted using NLP did not significantly improve 30-day readmission prediction among hospitalized patients with acute myocardial infarction. Alternative methods are needed to capture social risk factors.

Bimodal distribution of atrial fibrillation burden in 3 distinct cohorts: What is 'paroxysmal' atrial fibrillation?

BACKGROUND: Burden of atrial fibrillation (AF), as a continuous measure, is an emerging alternative classification often assumed to increase linearly with progression of disease. Yet there are no descriptions of AF burden distributions across populations. METHODS: We examined patterns of AF burden (% time in AF) across 3 different cohorts: outpatients with AF undergoing Holter monitoring in a national registry (ORBIT-AF II), routine outpatients undergoing Holter monitoring in a tertiary healthcare system (UHealth), and patients >= 65 years with cardiac implantable electronic devices (Merlin.netTM linked to Medicare). RESULTS: We included 2,058 ORBIT-AF II patients, 4,537 UHealth patients, and 39,710 from Merlin.net. Mean age ranged from 56 to 77 years, sex ranged from 40% to 61% male, and mean CHA2DS2-VASc scores ranged from 2.2 to 4.9. Across all cohorts, AF burden demonstrated skewed frequency towards the extremes, with the vast majority of patients having either very low or very high AF burden. This bimodal distribution was consistent across cohorts, across clinically-documented AF types (paroxysmal v persistent), patients with or without a known AF diagnosis, and among patients with different types of cardiac implantable electronic devices. CONCLUSIONS: Across 3 broad, diverse cohorts with continuous monitoring, distribution of AF burden was consistently skewed towards the extremes without an even, linear distribution or progression. As AF burden is increasingly recognized as a descriptor and potential risk-stratifier, these findings have important implications for future research and patient care.

Repeated cross-sectional analysis of hydroxychloroquine deimplementation in the AHA COVID-19 CVD Registry.

There is little data describing trends in the use of hydroxychloroquine for COVID-19 following publication of randomized trials that failed to demonstrate a benefit of this therapy. We identified 13,957 patients admitted for active COVID-19 at 85 U.S. hospitals participating in a national registry between March 1 and August 31, 2020. The overall proportion of patients receiving hydroxychloroquine peaked at 55.2% in March and April and decreased to 4.8% in May and June and 0.8% in July and August. At the hospital-level, median use was 59.4% in March and April (IQR 48.5-71.5%, range 0-100%) and decreased to 0.3% (IQR 0-5.4%, range 0-100%) by May and June and 0% (IQR 0-1.3%, range 0-36.4%) by July and August. The rate and hospital-level uniformity in deimplementation of this ineffective therapy for COVID-19 reflects a rapid response to evolving clinical information and further study may offer strategies to inform deimplementation of ineffective clinical care.

Adaptation of an NLP system to a new healthcare environment to identify social determinants of health.

Social determinants of health (SDoH) are increasingly important factors for population health, healthcare outcomes, and care delivery. However, many of these factors are not reliably captured within structured electronic health record (EHR) data. In this work, we evaluated and adapted a previously published NLP tool to include additional social risk factors for deployment at Vanderbilt University Medical Center in an Acute Myocardial Infarction cohort. We developed a transformation of the SDoH outputs of the tool into the OMOP common data model (CDM) for re-use across many potential use cases, yielding performance measures across 8 SDoH classes of precision 0.83 recall 0.74 and F-measure of 0.78.

Regional Systems of Care in ST Elevation Myocardial Infarction.

ST-segment elevation myocardial infarction is a medical emergency with significant health care delivery challenges to ensure rapid triage and treatment. Several developments over the past decades have led to improved care delivery, decreased time to reperfusion, and decreased mortality. Still, significant challenges remain to further optimize the delivery of care for this patient population.

Association of Wearable Device Use With Pulse Rate and Health Care Use in Adults With Atrial Fibrillation.

Importance: Increasingly, individuals with atrial fibrillation (AF) use wearable devices (hereafter wearables) that measure pulse rate and detect arrhythmia. The associations of wearables with health outcomes and health care use are unknown. Objective: To characterize patients with AF who use wearables and compare pulse rate and health care use between individuals who use wearables and those who do not. Design, Setting, and Participants: This retrospective, propensity-matched cohort study included 90 days of follow-up of patients in a tertiary care, academic health system. Included patients were adults with at least 1 AF-specific International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10) code from 2017 through 2019. Electronic medical records were reviewed to identify 125 individuals who used wearables and had adequate pulse-rate follow-up who were then matched using propensity scores 4 to 1 with 500 individuals who did not use wearables. Data were analyzed from June 2020 through February 2021. Exposure: Using commercially available wearables with pulse rate or rhythm evaluation capabilities. Main Outcomes and Measures: Mean pulse rates from measures taken in the clinic or hospital and a composite health care use score were recorded. The composite outcome included evaluation and management, ablation, cardioversion, telephone encounters, and number of rate or rhythm control medication orders. Results: Among 16 320 patients with AF included in the analysis, 348 patients used wearables and 15 972 individuals did not use wearables. Prior to matching, patients using wearables were younger (mean [SD] age, 64.0 [13.0] years vs 70.0 [13.8] years; P < .001) and healthier (mean [SD] CHA2DS2-VASc [congestive heart failure, hypertension, age ≥ 65 years or 65-74 years, diabetes, prior stroke/transient ischemic attack, vascular disease, sex] score, 3.6 [2.0] vs 4.4 [2.0]; P < .001) compared with individuals not using wearables, with similar gender distribution (148 [42.5%] women vs 6722 women [42.1%]; P = .91). After matching, mean pulse rate was similar between 125 patients using wearables and 500 patients not using wearables (75.01 [95% CI, 72.74-77.27] vs 75.79 [95% CI, 74.68-76.90] beats per minute [bpm]; P = .54), whereas mean composite use score was higher among individuals using wearables (3.55 [95% CI, 3.31-3.80] vs 3.27 [95% CI, 3.14-3.40]; P = .04). Among measures in the composite outcome, there was a significant difference in use of ablation, occurring in 22 individuals who used wearables (17.6%) vs 37 individuals who did not use wearables (7.4%) (P = .001). In the regression analyses, mean composite use score was 0.28 points (95% CI, 0.01 to 0.56 points) higher among individuals using wearables compared with those not using wearables and mean pulse was similar, with a -0.79 bpm (95% CI -3.28 to 1.71 bpm) difference between the groups. Conclusions and Relevance: This study found that follow-up health care use among individuals with AF was increased among those who used wearables compared with those with similar pulse rates who did not use wearables. Given the increasing use of wearables by patients with AF, prospective, randomized, long-term evaluation of the associations of wearable technology with health outcomes and health care use is needed.

Quality of Life in Patients With Heart Failure With Recovered Ejection Fraction.

Importance: Heart failure with recovered ejection fraction (HFrecEF) is a recently recognized phenotype of patients with a history of reduced left ventricular ejection fraction (LVEF) that has subsequently normalized. It is unknown whether such LVEF improvement is associated with improvements in health status. Objective: To examine changes in health-related quality of life in patients with heart failure with reduced ejection fraction (HFrEF) whose LVEF normalized, compared with those whose LVEF remains reduced and those with HF with preserved EF (HFpEF). Design, Setting, and Participants: This prospective cohort study was conducted at a tertiary care hospital from November 2016 to December 2018. Consecutive patients seen in a heart failure clinic who completed patient-reported outcome assessments were included. Clinical data were abstracted from the electronic health record. Data analysis was completed from February to December 2020. Main Outcomes and Measures: Changes in Kansas City Cardiomyopathy Questionnaire overall summary score, Visual Analog Scale score, and Patient-Reported Outcomes Measurement Information System domain scores on physical function, fatigue, depression, and satisfaction with social roles over 1-year follow-up. Results: The study group included 319 patients (mean [SD] age, 60.4 [15.5] years; 120 women [37.6%]). At baseline, 212 patients (66.5%) had HFrEF and 107 (33.5%) had HFpEF. At a median follow-up of 366 (interquartile range, 310-421) days, LVEF had increased to 50% or more in 35 patients with HFrEF (16.5%). Recovery of systolic function was associated with heart failure-associated quality-of-life improvement, such that for each 10% increase in LVEF, the Kansas City Cardiomyopathy Questionnaire score improved by an mean (SD) of 4.8 (1.6) points (P = .003). Recovery of LVEF was also associated with improvement of physical function, satisfaction with social roles, and a reduction in fatigue. Conclusions and Relevance: Among patients with HFrEF in this study, normalization of left ventricular systolic function was associated with a significant improvement in health-related quality of life.

Management of Women With Acquired Cardiovascular Disease From Pre-Conception Through Pregnancy and Postpartum: JACC Focus Seminar 3/5.

Acquired cardiovascular conditions are a leading cause of maternal morbidity and mortality. A growing number of pregnant women have acquired and heritable cardiovascular conditions and cardiovascular risk factors. As the average age of childbearing women increases, the prevalence of acute coronary syndromes, cardiomyopathy, and other cardiovascular complications in pregnancy are also expected to increase. This document, the third of a 5-part series, aims to provide practical guidance on the management of such conditions encompassing pre-conception through acute management and considerations for delivery.

The Effects of Using a Clinical Prediction Rule to Prioritize Diagnostic Testing on Transmission and Hospital Burden: A Modeling Example of Early Severe Acute Respiratory Syndrome Coronavirus 2.

BACKGROUND: Prompt identification of infections is critical for slowing the spread of infectious diseases. However, diagnostic testing shortages are common in emerging diseases, low resource settings, and during outbreaks. This forces difficult decisions regarding who receives a test, often without knowing the implications of those decisions on population-level transmission dynamics. Clinical prediction rules (CPRs) are commonly used tools to guide clinical decisions. METHODS: Using early severe acute respiratory syndrome coronavirus disease 2 (SARS-CoV-2) as an example, we used data from electronic health records to develop a parsimonious 5-variable CPR to identify those who are most likely to test positive. To consider the implications of gains in daily case detection at the population level, we incorporated testing using the CPR into a compartmentalized model of SARS-CoV-2. RESULTS: We found that applying this CPR (area under the curve, 0.69; 95% confidence interval, .68-.70) to prioritize testing increased the proportion of those testing positive in settings of limited testing capacity. We found that prioritized testing led to a delayed and lowered infection peak (ie, "flattens the curve"), with the greatest impact at lower values of the effective reproductive number (such as with concurrent community mitigation efforts), and when higher proportions of infectious persons seek testing. In addition, prioritized testing resulted in reductions in overall infections as well as hospital and intensive care unit burden. CONCLUSION: We highlight the population-level benefits of evidence-based allocation of limited diagnostic capacity.SummaryWhen the demand for diagnostic tests exceeds capacity, the use of a clinical prediction rule to prioritize diagnostic testing can have meaningful impact on population-level outcomes, including delaying and lowering the infection peak, and reducing healthcare burden.

Robust Testing in Outpatient Settings to Explore COVID-19 Epidemiology: Disparities in Race/Ethnicity and Age, Salt Lake County, Utah, 2020.

OBJECTIVE: US-based descriptions of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection have focused on patients with severe disease. Our objective was to describe characteristics of a predominantly outpatient population tested for SARS-CoV-2 in an area receiving comprehensive testing. METHODS: We extracted data on demographic characteristics and clinical data for all patients (91% outpatient) tested for SARS-CoV-2 at University of Utah Health clinics in Salt Lake County, Utah, from March 10 through April 24, 2020. We manually extracted data on symptoms and exposures from a subset of patients, and we calculated the adjusted odds of receiving a positive test result by demographic characteristics and clinical risk factors. RESULTS: Of 17 662 people tested, 1006 (5.7%) received a positive test result for SARS-CoV-2. Hispanic/Latinx people were twice as likely as non-Hispanic White people to receive a positive test result (adjusted odds ratio [aOR] = 2.0; 95% CI, 1.3-3.1), although the severity at presentation did not explain this discrepancy. Young people aged 0-19 years had the lowest rates of receiving a positive test result for SARS-CoV-2 (<4 cases per 10 000 population), and adults aged 70-79 and 40-49 had the highest rates of hospitalization per 100 000 population among people who received a positive test result (16 and 11, respectively). CONCLUSIONS: We found disparities by race/ethnicity and age in access to testing and in receiving a positive test result among outpatients tested for SARS-CoV-2. Further research and public health outreach on addressing racial/ethnic and age disparities will be needed to effectively combat the coronavirus disease 2019 pandemic in the United States.

Development of Electronic Health Record-Based Prediction Models for 30-Day Readmission Risk Among Patients Hospitalized for Acute Myocardial Infarction.

Importance: In the US, more than 600 000 adults will experience an acute myocardial infarction (AMI) each year, and up to 20% of the patients will be rehospitalized within 30 days. This study highlights the need for consideration of calibration in these risk models. Objective: To compare multiple machine learning risk prediction models using an electronic health record (EHR)-derived data set standardized to a common data model. Design, Setting, and Participants: This was a retrospective cohort study that developed risk prediction models for 30-day readmission among all inpatients discharged from Vanderbilt University Medical Center between January 1, 2007, and December 31, 2016, with a primary diagnosis of AMI who were not transferred from another facility. The model was externally validated at Dartmouth-Hitchcock Medical Center from April 2, 2011, to December 31, 2016. Data analysis occurred between January 4, 2019, and November 15, 2020. Exposures: Acute myocardial infarction that required hospital admission. Main Outcomes and Measures: The main outcome was thirty-day hospital readmission. A total of 141 candidate variables were considered from administrative codes, medication orders, and laboratory tests. Multiple risk prediction models were developed using parametric models (elastic net, least absolute shrinkage and selection operator, and ridge regression) and nonparametric models (random forest and gradient boosting). The models were assessed using holdout data with area under the receiver operating characteristic curve (AUROC), percentage of calibration, and calibration curve belts. Results: The final Vanderbilt University Medical Center cohort included 6163 unique patients, among whom the mean (SD) age was 67 (13) years, 4137 were male (67.1%), 1019 (16.5%) were Black or other race, and 933 (15.1%) were rehospitalized within 30 days. The final Dartmouth-Hitchcock Medical Center cohort included 4024 unique patients, with mean (SD) age of 68 (12) years; 2584 (64.2%) were male, 412 (10.2%) were rehospitalized within 30 days, and most of the cohort were non-Hispanic and White. The final test set AUROC performance was between 0.686 to 0.695 for the parametric models and 0.686 to 0.704 for the nonparametric models. In the validation cohort, AUROC performance was between 0.558 to 0.655 for parametric models and 0.606 to 0.608 for nonparametric models. Conclusions and Relevance: In this study, 5 machine learning models were developed and externally validated to predict 30-day readmission AMI hospitalization. These models can be deployed within an EHR using routinely collected data.

Shedding Light on the Black Box: Explaining Deep Neural Network Prediction of Clinical Outcomes.

Deep neural network models are emerging as an important method in healthcare delivery, following the recent success in other domains such as image recognition. Due to the multiple non-linear inner transformations, deep neural networks are viewed by many as black boxes. For practical use, deep learning models require explanations that are intuitive to clinicians. In this study, we developed a deep neural network model to predict outcomes following major cardiovascular procedures, using temporal image representation of past medical history as input. We created a novel explanation for the prediction of the model by defining impact scores that associate clinical observations with the outcome. For comparison, a logistic regression model was fitted to the same dataset. We compared the impact scores and log odds ratios by calculating three types of correlations, which provided a partial validation of the impact scores. The deep neural network model achieved an area under the receiver operating characteristics curve (AUC) of 0.787, compared to 0.746 for the logistic regression model. Moderate correlations were found between the impact scores and the log odds ratios. Impact scores generated by the explanation algorithm has the potential to shed light on the "black box" deep neural network model and could facilitate its adoption by clinicians.

Maternal cardiovascular complications at the time of delivery and subsequent re-hospitalization in the USA, 2010-16.

AIMS: Cardiovascular (CV) complications are the leading cause of maternal morbidity and mortality. The objective was to estimate trends in the incidence of peripartum CV complications in the USA between 2010 and 2016. METHODS AND RESULTS: This was a retrospective analyses using data from the Healthcare Cost and Utilization Project. We included women with delivery codes consistent with delivery, weighted to a national estimate. The primary outcome was the age-adjusted incidence of CV complications among all deliveries, including complications that occurred during re-hospitalizations. Complications were identified using International Classification of Diseases (ICD) codes. Joinpoint regression was used to evaluate time trends and complications were stratified by type. The secondary outcome was in-hospital maternal death among women with a CV complication. We identified a weighted estimate of 27 408 652 women hospitalized for delivery from 2010 to 2016. Including all years, the complication incidence was 7.36/1000 births [95% confidence interval (CI) 7.18-7.54], with an estimated annual percentage change of 5.8% (95% CI 3.7-7.8%). Cardiac dysrhythmia was the most common complication [3.98/1000 births (95% CI 3.88-4.08)] and acute myocardial infarction was the least common complication [0.11/1000 births (95% CI 0.10-0.11)]. The incidence of hypertension, acute myocardial infarction, and cardiac arrest increased over time, the incidence of congestive heart failure and acute cerebrovascular disease remained stable, the incidence of pulmonary heart disease increased from 2015 onward, and the incidence of cardiac dysrhythmia decreased in 2016. Complications during re-hospitalization accounted for 13.6% (95% CI 13.2-14.1%) of all complications and was highest for acute myocardial infarction [28.1% (95% CI 23.2-33.1)]. Among women with any complication, the mortality rate was 1.20 (95% CI 1.11-1.29) per 100 complications. CONCLUSION: Our analyses suggest the rate of peripartum CV complications are increasing in the USA, which highlights the need for active efforts in research and prevention.