Validated, Electronic Health Record Deployable Prediction Models for Assessing Patient Risk of 30-Day Rehospitalization and Mortality in Older Heart Failure Patients

Predicting the risk of 1-year mortality among patients hospitalized for acute heart failure in China

BACKGROUND

We aimed to develop and validate a model to predict 1-year mortality risk among patients hospitalized for acute heart failure (AHF), build a risk score and interpret its application in clinical decision making.

METHODS

By using data from China Patient-Centred Evaluative Assessment of Cardiac Events Prospective Heart Failure Study, which prospectively enrolled patients hospitalized for AHF in 52 hospitals across 20 provinces, we used multivariate Cox proportional hazard model to develop and validate a model to predict 1-year mortality.

RESULTS

There were 4,875 patients included in the study, 857 (17.58%) of them died within 1-year following discharge of index hospitalization. A total of 13 predictors were selected to establish the prediction model, including age, medical history of chronic obstructive pulmonary disease and hypertension, systolic blood pressure, Kansas City Cardiomyopathy Questionnaire-12 score, angiotensin converting enzyme inhibitor or angiotensin receptor blocker at discharge, discharge symptom, N-terminal pro-brain natriuretic peptide, high-sensitivity troponin T, serum creatine, albumin, blood urea nitrogen, and highly sensitive C-reactive protein. The model showed a high performance on discrimination (C-index was 0.759 [95% confidence interval: 0.739, 0.778] in development cohort and 0.761 [95% confidence interval: 0.731, 0.791] in validation cohort), accuracy, calibration, and outperformed than several existed risk scores. A point-based risk score was built to stratify low- (0-12), intermediate- (13-16), and high-risk group (≥17) among patients.

CONCLUSIONS

A prediction model using readily available predictors was developed and internal validated to predict 1-year mortality risk among patients hospitalized for AHF. It may serve as a useful tool for individual risk stratification and informing decision making to improve clinical care.

PRecision Event Monitoring for PatienTs with Heart Failure using HeartLogic (PREEMPT-HF) study design and enrolment

AIMS

The HeartLogic multisensor index has been found to be a sensitive predictor of worsening heart failure (HF). However, there is limited data on this index's association and its constituent sensors with HF readmissions.

METHODS AND RESULTS

The PREEMPT-HF study is a global, multicentre, prospective, observational, single-arm, post-market study. HF patients with an implantable defibrillator device or cardiac resynchronization therapy with defibrillator with HeartLogic capabilities were eligible if sensor data collection was turned on and the HeartLogic feature was not enabled. Thus, the HeartLogic Index/alert and heart sounds sensor trends were unavailable via the LATITUDE remote monitoring system to clinicians (blinded). Evaluation of subject medical records at 6 months and a final in-clinic visit at 12 months was required for collection of all-cause hospitalizations and HF outpatient visits. The purpose of this study is exploratory, no formal hypothesis tests are planned, and no adjustment for multiple testing will be performed. A total of 2183 patients were enrolled at 103 sites between June 2018 and June 2020. A significant proportion of the patients were implanted with implantable defibrillator devices (39%) versus cardiac resynchronization therapy with defibrillator (61%); were female (27%); over 65 (61%); New York Heart Association class I (13%), II (53%), and III (33%); ejection fraction < 25% (21%); ischaemic (50%); and with a history of renal dysfunction (23%).

CONCLUSIONS

The PREEMPT study will provide clinical data and blinded sensor trends for the characterization of sensor changes with HF readmission, tachyarrhythmias, and event subgroups. These data may help to refine the clinical use of HeartLogic and to improve patient outcomes.

Predictors of 30-Day Readmission in Patients Hospitalized With Heart Failure as a Primary Versus Secondary Diagnosis

Short-term rehospitalizations are common, costly, and detrimental to patients with heart failure (HF). Current research and policy have focused primarily on 30-day readmissions for patients with HF as a primary diagnosis at index hospitalization, whereas a much larger population of patients are admitted with HF as a secondary diagnosis. This study aims to compare patients initially hospitalized for HF as either a primary or a secondary diagnosis, and to identify the most important factors in predicting 30-day readmission. Patients admitted with HF between 2014 and 2016 in the Nationwide Readmissions Database were included and divided into 2 cohorts: those admitted with a primary and secondary diagnosis of HF. Multivariable logistic regression was performed to predict 30-day readmission. Statistically significant predictors in multivariable logistic regression were used for dominance analysis to rank these factors by relative importance. Co-morbidities were the major driver of increased risk of 30-day readmission in both groups. Individual Elixhauser co-morbidities and the Elixhauser co-morbidity indexes were significantly associated with an increase in 30-day readmission. The 5 most important predictors of 30-day readmission according to dominance analysis were age, Elixhauser co-morbidity indexes of co-morbidity complications and readmission, number of diagnoses, and renal failure. These 5 factors accounted for 68% of the 30-day readmission risk. Measures of patient co-morbidities were among the strongest predictors of readmission risk. This study highlights the importance of expanding predictive models to include a broader set of clinical measures to create better-performing models of readmission risk for HF patients.

Risk prediction with imperfect survival outcome information from electronic health records

Readily available proxies for the time of disease onset such as the time of the first diagnostic code can lead to substantial risk prediction error if performing analyses based on poor proxies. Due to the lack of detailed documentation and labor intensiveness of manual annotation, it is often only feasible to ascertain for a small subset the current status of the disease by a follow-up time rather than the exact time. In this paper, we aim to develop risk prediction models for the onset time efficiently leveraging both a small number of labels on the current status and a large number of unlabeled observations on imperfect proxies. Under a semiparametric transformation model for onset and a highly flexible measurement error model for proxy onset time, we propose the semisupervised risk prediction method by combining information from proxies and limited labels efficiently. From an initially estimator solely based on the labeled subset, we perform a one-step correction with the full data augmenting against a mean zero rank correlation score derived from the proxies. We establish the consistency and asymptotic normality of the proposed semisupervised estimator and provide a resampling procedure for interval estimation. Simulation studies demonstrate that the proposed estimator performs well in a finite sample. We illustrate the proposed estimator by developing a genetic risk prediction model for obesity using data from Mass General Brigham Healthcare Biobank.

Pulmonary Congestion on Lung Ultrasound Predicts Increased Risk of 30-Day Readmission in Heart Failure Patients

OBJECTIVES

Heart failure exacerbations are a common cause of hospitalizations with a high readmission rate. There are few validated predictors of readmission after treatment for acute decompensated heart failure (ADHF). Lung ultrasound (LUS) is sensitive and specific in the assessment of pulmonary congestion; however, it is not frequently utilized to assess for congestion before discharge. This study assessed the association between number of B-lines, on LUS, at patient discharge and risk of 30-day readmission in patients hospitalized for acute decompensated heart failure (ADHF).

METHODS

This was a single-center prospective study of adults admitted to a quaternary care center with a diagnosis of ADHF. At the time of discharge, the patient received an 8-zone LUS exam to evaluate for the presence of B-lines. A zone was considered positive if ≥3 B-lines was present. We assessed the risk of 30-day readmission associated with the number of lung zones positive for B-lines using a log-binomial regression model.

RESULTS

Based on data from 200 patients, the risk of 30-day readmission in patients with 2-3 positive lung zones was 1.25 times higher (95% CI: 1.08-1.45), and in patients with 4-8 positive lung zones was 1.50 times higher (95% CI: 1.23-1.82, compared with patients with 0-1 positive zones, after adjusting for discharge blood urea nitrogen, creatinine, and hemoglobin.

CONCLUSION

Among patients admitted with ADHF, the presence of B-lines at discharge was associated with a significantly increased risk of 30-day readmission, with greater number of lung zones positive for B-lines corresponding to higher risk.

Associations between continuity of care, perceived control and self-care and their impact on health-related quality of life and hospital readmission-A structural equation model

AIM

The aim of this study is to examine whether a conceptual model including the associations between continuity of care, perceived control and self-care could explain variations in health-related quality of life and hospital readmissions in people with chronic cardiac conditions after hospital discharge.

DESIGN

Correlational design based on cross-sectional data from a multicentre survey study.

METHODS

People hospitalized due to angina, atrial fibrillation, heart failure or myocardial infarction were included at four hospitals using consecutive sampling procedures during 2017-2019. Eligible people received questionnaires by regular mail 4-6 weeks after discharge. A tentative conceptual model describing the relationship between continuity of care, self-care, perceived control, health-related quality of life and readmission was developed and evaluated using structural equation modelling.

RESULTS

In total, 542 people (mean age 75 years, 37% females) were included in the analyses. According to the structural equation model, continuity of care predicted self-care, which in turn predicted health-related quality of life and hospital readmission. The association between continuity of care and self-care was partly mediated by perceived control. The model had an excellent model fit: RMSEA = 0.06, 90% CI, 0.05-0.06; CFI = 0.90; TLI = 0.90.

CONCLUSION

Interventions aiming to improve health-related quality of life and reduce hospital readmission rates should focus on enhancing continuity of care, perceived control and self-care.

IMPACT

This study reduces the knowledge gap on how central factors after hospitalization, such as continuity of care, self-care and perceived control, are associated with improved health-related quality of life and hospital readmission in people with cardiac conditions. The results suggest that these factors together predicted the quality of life and readmissions in this sample. This knowledge is relevant to researchers when designing interventions or predicting health-related quality of life and hospital readmission. For clinicians, it emphasizes that enhancing continuity of care, perceived control and self-care positively impacts clinical outcomes.

PATIENT OR PUBLIC CONTRIBUTION

People and healthcare personnel evaluated content validity and were included in selecting items for the short version.

Machine learning and LACE index for predicting 30-day readmissions after heart failure hospitalization in elderly patients

Machine learning (ML) techniques may improve readmission prediction performance in heart failure (HF) patients. This study aimed to assess the ability of ML algorithms to predict unplanned all-cause 30-day readmissions in HF elderly patients, and to compare them with conventional LACE (Length of hospitalization, Acuity, Comorbidities, Emergency department visits) index. All patients aged ≥ 65 years discharged alive between 2010 and 2019 after a hospitalization for acute HF were included in this retrospective cohort study. We applied MICE (Multivariate Imputation via Chained Equations) method to obtain a balanced, fully valued dataset and LASSO (Least Absolute Shrinkage and Selection Operator) algorithm to get the most significant features. Training (80% of records) and test (20%) cohorts were randomly selected. Study population: 3079 patients, 394 (12.8%) presented at least one readmission within 30 days, and 2685 (87.2%) did not. In the test cohort AUCs (IC95%) of XGBoost, Ada Boost Classifier, Random forest, and Gradient Boosting, and LACE Index were: 0.803 (0.734-0.872), 0.782 (0.711-0.854), 0.776 (0.703-0.848), 0.786 (0.715-0.857), and 0.504 (0.414-0.594), respectively, for predicting readmissions. A SHAP analysis was performed to offer a breakdown of the ML variables associated with readmission. Positive and negative predicting values estimates of the different ML models and LACE index were also provided, for several values of readmission rate prevalence. Among elderly patients, the rate of all-cause unplanned 30-day readmissions after hospitalization due to an acute HF was high. ML models performed better than the conventional LACE index for predicting readmissions. ML models can be proposed as promising tools for the identification of subjects at high risk of hospitalization in this clinical setting, enabling care teams to target interventions for improving overall clinical outcomes.

Combining adult with pediatric patient data to develop a clinical decision support tool intended for children: leveraging machine learning to model heterogeneity

Background

Clinical decision support (CDS) tools built using adult data do not typically perform well for children. We explored how best to leverage adult data to improve the performance of such tools. This study assesses whether it is better to build CDS tools for children using data from children alone or to use combined data from both adults and children.

Methods

Retrospective cohort using data from 2017 to 2020. Participants include all individuals (adults and children) receiving an elective surgery at a large academic medical center that provides adult and pediatric services. We predicted need for mechanical ventilation or admission to the intensive care unit (ICU). Predictor variables included demographic, clinical, and service utilization factors known prior to surgery. We compared predictive models built using machine learning to regression-based methods that used a pediatric or combined adult-pediatric cohort. We compared model performance based on Area Under the Receiver Operator Characteristic.

Results

While we found that adults and children have different risk factors, machine learning methods are able to appropriately model the underlying heterogeneity of each population and produce equally accurate predictive models whether using data only from pediatric patients or combined data from both children and adults. Results from regression-based methods were improved by the use of pediatric-specific data.

Conclusions

CDS tools for children can successfully use combined data from adults and children if the model accounts for underlying heterogeneity, as in machine learning models.

Clinical risk prediction model for 30-day all-cause re-hospitalisation or mortality in patients hospitalised with heart failure

BACKGROUND

This study aimed to develop a risk prediction model (AUS-HF model) for 30-day all-cause re-hospitalisation or death among patients admitted with acute heart failure (HF) to inform follow-up after hospitalisation. The model uses routinely collected measures at point of care.

METHODS

We analyzed pooled individual-level data from two cohort studies on acute HF patients followed for 30-days after discharge in 17 hospitals in Victoria, Australia (2014-2017). A set of 58 candidate predictors, commonly recorded in electronic medical records (EMR) including demographic, medical and social measures were considered. We used backward stepwise selection and LASSO for model development, bootstrap for internal validation, C-statistic for discrimination, and calibration slopes and plots for model calibration.

RESULTS

The analysis included 1380 patients, 42.1% female, median age 78.7 years (interquartile range = 16.2), 60.0% experienced previous hospitalisation for HF and 333 (24.1%) were re-hospitalised or died within 30 days post-discharge. The final risk model included 10 variables (admission: eGFR, and prescription of anticoagulants and thiazide diuretics; discharge: length of stay>3 days, systolic BP, heart rate, sodium level (<135 mmol/L), >10 prescribed medications, prescription of angiotensin converting enzyme inhibitors or angiotensin receptor blockers, and anticoagulants prescription. The discrimination of the model was moderate (C-statistic = 0.684, 95%CI 0.653, 0.716; optimism estimate = 0.062) with good calibration.

CONCLUSIONS

The AUS-HF model incorporating routinely collected point-of-care data from EMRs enables real-time risk estimation and can be easily implemented by clinicians. It can predict with moderate accuracy risk of 30-day hospitalisation or mortality and inform decisions around the intensity of follow-up after hospital discharge.

Development and Validation of a Prediction Model for Irreversible Worsened Cardiac Function in Patients With Acute Decompensated Heart Failure

Background: Irreversible worsening of cardiac function is an adverse event associated with significant morbidity among patients with acute decompensated heart failure (ADHF). We aimed to develop a parsimonious model which is simple to use in clinical settings for the prediction of the risk of irreversible worsening of cardiac function. Methods: A total of 871 ADHF patients were enrolled in this study. Data for each patient were collected from the medical records. Irreversible worsening of cardiac function included cardiac death within 30-days of patient hospitalization, implantation of a left ventricular assistance device, or emergency heart transplantation. We performed LASSO regression for variable selection to derive a multivariable logistic regression model. Five candidate predictors were selected to derive the final prediction model. The prediction model was verified using C-statistics, calibration curve, and decision curve. Results: Irreversible worsening of cardiac function occurred in 7.8% of the patients. Advanced age, NYHA class, high blood urea nitrogen, hypoalbuminemia, and vasopressor use were its strongest predictors. The prediction model showed good discrimination C-statistic value, 0.866 (95% CI, 0.817-0.907), which indicated good identical calibration and clinical efficacy. Conclusion: In this study, we developed a prediction model and nomogram to estimate the risk of irreversible worsening of cardiac function among ADHF patients. The findings may provide a reference for clinical physicians for detection of irreversible worsening of cardiac function and enable its prompt management.

Mortality and Readmission Rates After Heart Failure: A Systematic Review and Meta-Analysis

Objective

The current work aimed to examine the rates of and risk factors for mortality and readmission after heart failure (HF).

Setting

A systematic search was carried out in PubMed, the Cochrane Library, and EMBASE to identify eligible reports. The random-effects model was utilized to evaluate the pooled results.

Participants

A total of 27 studies with 515,238 participants were finally meta-analysed. The HF patients had an average age of 76.3 years, with 51% of the sample being male, in the pooled analysis.

Primary and Secondary Outcome Measures

The outcome measures were 30-day and 1-year readmission rates, mortality, and risk factors for readmission and mortality.

Results

The effect sizes for readmission and mortality were estimated as the mean and 95% confidence interval (CI). The estimated 30-day and 1-year all-cause readmission rates were 0.19 (95% CI 0.14-0.23) and 0.53 (95% CI 0.46-0.59), respectively, while the all-cause mortality rates were 0.14 (95% CI 0.10-0.18) and 0.29 (95% CI 0.25-0.33), respectively. Comorbidities were highly prevalent in individuals with HF.

Conclusion

Heart failure hospitalization is followed by high readmission and mortality rates.

Rationale and design of the comparison of outcomes and access to care for heart failure (COACH) trial: A stepped wedge cluster randomized trial

BACKGROUND

Heart failure (HF) is an ambulatory care sensitive condition and a leading reason for emergency department (ED) visits and hospitalizations. Improved decision-making and care may enhance safety and efficiency for patients presenting to the ED with acute HF.

OBJECTIVES

We will evaluate an intervention comprised of 2 complementary components: (1) the Emergency Heart Failure Mortality Risk Grade simultaneous 7- and 30-day (EHMRG30-ST) risk scores, which will inform admission-discharge decisions, and (2) a rapid outpatient follow-up (RAPID-HF) clinic for low-to-intermediate risk patients on cardiovascular readmissions or death.

STUDY DESIGN

Stepped wedge cluster randomized trial with cross-sectional measurement at 10 acute care hospitals in Ontario, Canada. Patients presenting during control and intervention periods are eligible if they have a primary ED diagnosis of HF. In the intervention periods, access to the EHMRG30-ST web calculator will become available to hospitals' internet protocol (IP) addresses, and referral to the RAPID-HF clinic will be facilitated by a study nurse navigator. Patients with a high risk EHMRG30-ST score will be admitted to hospital. The RAPID-HF clinic will accept referrals for patients: (1) with low risk 7- and 30-day EHMRG30-ST scores who are discharged directly from the ED, or (2) intermediate risk patients with hospital length of stay < 72 hours. The RAPID-HF clinic, staffed by a nurse-clinician and cardiologist, will provide care during the 30-day transition after hospital separation.

CONCLUSION

This trial will determine whether novel risk stratification coupled with rapid ambulatory care achieves better outcomes than conventional decision-making and care for patients with HF.

Prediction Model Using Machine Learning for Mortality in Patients with Heart Failure

Heart Failure (HF) is a major cause of morbidity and mortality in the US. With aging of the US population, the public health burden of HF is enormous. We aimed to develop an ensemble prediction model for 30-day mortality after discharge using machine learning. Using an electronic medical records (EMR) database, all patients with a non-elective HF admission over 10 years (January 2001 - December 2010) within the Montefiore Medical Center (MMC) health system, in the Bronx, New York, were included. We developed an ensemble model for 30-day mortality after discharge and employed discrimination, range of prediction, Brier index and explained variance as metrics in assessing model performance. A total of 7,516 patients were included. The discrimination achieved by the ensemble model was higher 0.83 (95% CI: 0.80 to 0.87) compared to the benchmark model 0.79 (95% CI: 0.75 to 0.84). The ensemble model also exhibited a better range of prediction as well as a favorable profile with respect to the other metrics employed. In conclusion, an ensemble machine learning approach exhibited an improvement in performance compared to the benchmark logistic model in predicting all-cause mortality among HF patients within 30-days of discharge. Machine learning is a promising alternative approach for risk profiling of HF patients, and it enhances individualized patient management.

Published models that predict hospital readmission: a critical appraisal

INTRODUCTION

The number of readmission risk prediction models available has increased rapidly, and these models are used extensively for health decision-making. Unfortunately, readmission models can be subject to flaws in their development and validation, as well as limitations in their clinical usefulness.

OBJECTIVE

To critically appraise readmission models in the published literature using Delphi-based recommendations for their development and validation.

METHODS

We used the modified Delphi process to create Critical Appraisal of Models that Predict Readmission (CAMPR), which lists expert recommendations focused on development and validation of readmission models. Guided by CAMPR, two researchers independently appraised published readmission models in two recent systematic reviews and concurrently extracted data to generate reference lists of eligibility criteria and risk factors.

RESULTS

We found that published models (n=81) followed 6.8 recommendations (45%) on average. Many models had weaknesses in their development, including failure to internally validate (12%), failure to account for readmission at other institutions (93%), failure to account for missing data (68%), failure to discuss data preprocessing (67%) and failure to state the model's eligibility criteria (33%).

CONCLUSIONS

The high prevalence of weaknesses in model development identified in the published literature is concerning, as these weaknesses are known to compromise predictive validity. CAMPR may support researchers, clinicians and administrators to identify and prevent future weaknesses in model development.

Clinical Outcome Predictions for the VerICiguaT Global Study in Subjects With Heart Failure With Reduced Ejection Fraction (VICTORIA) Trial

BACKGROUND

The prediction of outcomes in patients with heart failure (HF) may inform prognosis, clinical decisions regarding treatment selection, and new trial planning. The VerICiguaT Global Study in Subjects With Heart Failure With Reduced Ejection Fraction included high-risk patients with HF with reduced ejection fraction and a recent worsening HF event. The study participants had a high event rate despite the use of contemporary guideline-based therapies. To provide generalizable predictive data for a broad population with a recent worsening HF event, we focused on risk prognostication in the placebo group.

METHODS AND RESULTS

Data from 2524 participants randomized to placebo with chronic HF (New York Heart Association functional class II-IV) and an ejection fraction of less than 45% were studied and backward variable selection was used to create Cox proportional hazards models for clinical end points, selecting from 66 candidate predictors. Final model results were produced, accounting for missing data, and nonlinearities. Optimism-corrected c-indices were calculated using 200 bootstrap samples. Over a median follow-up of 10.4 months, the primary outcome of HF hospitalization or cardiovascular death occurred in 972 patients (38.5%). Independent predictors of increased risk for the primary end point included HF characteristics (longer HF duration and worse New York Heart Association functional class), medical history (prior myocardial infarction), and laboratory values (higher N-terminal pro-hormone B-type natriuretic peptide, bilirubin, urate; lower chloride and albumin). Optimism-corrected c-indices were 0.68 for the HF hospitalization/cardiovascular death model, 0.68 for HF hospitalization/all-cause death, 0.72 for cardiovascular death, and 0.73 for all-cause death.

CONCLUSIONS

Predictive models developed in a large diverse clinical trial with comprehensive clinical and laboratory baseline data-including novel measures-performed well in high-risk patients with HF who were receiving excellent guideline-based clinical care.

CLINICAL TRIAL REGISTRATION

Clinicaltrials.gov identifier, NCT02861534.Lay Summary: Patients with heart failure may benefit from tools that help clinicians to better understand a patient's risk for future events like hospitalization. Relatively few risk models have been created after the worsening of heart failure in a contemporary cohort. We provide insights on the risk factors for clinical events from a recent, large, global trial of patients with worsening heart failure to help clinicians better understand and communicate prognosis and select treatment options.

Machine Learning Applications in Heart Failure Disease Management: Hype or Hope?

Purpose of the review

Machine learning (ML) approaches have emerged as powerful tools in medicine. This review focuses on the use ML to assess risk of events in patients with heart failure (HF). It provides an overview of the ML process, challenges in developing risk scores, and strategies to mitigate problems.

Recent findings

Risk scores developed using standard statistical methods have limited accuracy, particularly when they are applied to populations other than the one in which they were developed. Computerized ML algorithms which identify correlations between descriptive variables in complex, non-linear, multi-dimensional systems provide an alternative approach to predicting risk of events. The MARKER-HF mortality risk score was developed using data from the electronic health record of HF patients followed at a large academic medical center. The risk score, which uses eight commonly available variables, proved to be highly accurate in predicting mortality across the spectrum of risk. It retained accuracy in independent populations and was superior to other risk scores.

Summary

Machine learning approaches can be used to develop risk scores that are superior to ones based on standard statistical methods. Careful attention to detail in curating data, selecting covariates, and trouble-shooting the process is required to optimize results.

Derivation and validation of a two-variable index to predict 30-day outcomes following heart failure hospitalization

Background

The LACE index—length of stay (L), acuity (A), Charlson co‐morbidities (C), and emergent visits (E)—predicts 30‐day outcomes following heart failure (HF) hospitalization but is complex to score. A simpler LE index (length of stay and emergent visits) could offer a practical advantage in point‐of‐care risk prediction.

Methods and results

This was a sub‐study of the patient‐centred care transitions in HF (PACT‐HF) multicentre trial. The derivation cohort comprised patients hospitalized for HF, enrolled in the trial, and followed prospectively. External validation was performed retrospectively in a cohort of patients hospitalized for HF. We used log‐binomial regression models with LACE or LE as the predictor and either 30‐day composite all‐cause readmission or death or 30‐day all‐cause readmission as the outcomes, adjusting only for post‐discharge services. There were 1985 patients (mean [SD] age 78.1 [12.1] years) in the derivation cohort and 378 (mean [SD] age 73.1 [13.2] years) in the validation cohort. Increments in the LACE and LE indices were associated with 17% (RR 1.17; 95% CI 1.12, 1.21; C‐statistic 0.64) and 21% (RR 1.21; 95% CI 1.15, 1.26; C‐statistic 0.63) increases, respectively, in 30‐day composite all‐cause readmission or death; and 16% (RR 1.16; 95% CI 1.11, 1.20; C‐statistic 0.64) and 18% (RR 1.18; 95% CI 1.13, 1.24; C‐statistic 0.62) increases, respectively, in 30‐day all‐cause readmission. The LE index provided better risk discrimination for the 30‐day outcomes than did the LACE index in the external validation cohort.

Conclusions

The LE index predicts 30‐day outcomes following HF hospitalization with similar or better performance than the more complex LACE index.

Prediction of short-term mortality in acute heart failure patients using minimal electronic health record data

Background

Acute heart failure (AHF) is associated with significant morbidity and mortality. Effective patient risk stratification is essential to guiding hospitalization decisions and the clinical management of AHF. Clinical decision support systems can be used to improve predictions of mortality made in emergency care settings for the purpose of AHF risk stratification. In this study, several models for the prediction of seven-day mortality among AHF patients were developed by applying machine learning techniques to retrospective patient data from 236,275 total emergency department (ED) encounters, 1881 of which were considered positive for AHF and were used for model training and testing. The models used varying subsets of age, sex, vital signs, and laboratory values. Model performance was compared to the Emergency Heart Failure Mortality Risk Grade (EHMRG) model, a commonly used system for prediction of seven-day mortality in the ED with similar (or, in some cases, more extensive) inputs. Model performance was assessed in terms of area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity.

Results

When trained and tested on a large academic dataset, the best-performing model and EHMRG demonstrated test set AUROCs of 0.84 and 0.78, respectively, for prediction of seven-day mortality. Given only measurements of respiratory rate, temperature, mean arterial pressure, and FiO₂, one model produced a test set AUROC of 0.83. Neither a logistic regression comparator nor a simple decision tree outperformed EHMRG.

Conclusions

A model using only the measurements of four clinical variables outperforms EHMRG in the prediction of seven-day mortality in AHF. With these inputs, the model could not be replaced by logistic regression or reduced to a simple decision tree without significant performance loss. In ED settings, this minimal-input risk stratification tool may assist clinicians in making critical decisions about patient disposition by providing early and accurate insights into individual patient’s risk profiles.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13040-021-00255-w.

"Get with the Guidelines Heart Failure Risk Score" for mortality prediction in patients undergoing MitraClip

BACKGROUND

Reliable risk scores in patients undergoing transcatheter edge-to-edge mitral valve repair (TMVR) are lacking. Heart failure is common in these patients, and risk scores derived from heart failure populations might help stratify TMVR patients.

METHODS

Consecutive patients from three Heart Centers undergoing TMVR were enrolled to investigate the association of the "Get with the Guidelines Heart Failure Risk Score" (comprising the variables systolic blood pressure, urea nitrogen, blood sodium, age, heart rate, race, history of chronic obstructive lung disease) with all-cause mortality.

RESULTS

Among 815 patients with available data 177 patients died during a median follow-up time of 365 days. Estimated 1-year mortality by quartiles of the score (0-37; 38-42, 43-46 and more than 46 points) was 6%, 10%, 23% and 30%, respectively (p < 0.001), with good concordance between observed and predicted mortality rates (goodness of fit test p = 0.46). Every increase of one score point was associated with a 9% increase in the hazard of mortality (95% CI 1.06-1.11%, p < 0.001). The score was associated with long-term mortality independently of left ventricular ejection fraction, NYHA class and NTproBNP, and was equally predictive in primary and secondary mitral regurgitation.

CONCLUSION

The "Get with the Guidelines Heart Failure Risk Score" showed a strong association with mortality in patients undergoing TMVR with additive information beyond traditional risk factors. Given the routinely available variables included in this score, application is easy and broadly possible.

External validation of the ACUTE HF score in patients hospitalized for acute decompensated heart failure

OBJECTIVE

Recently, the ACUTE HF score has been developed as a new tool for predicting short and long term mortality in patients with acute heart failure (AHF). However, this. score has not yet been validated externally. The present study aimed to investigate the prognostic value of ACUTE HF score in a different patient cohort.

METHODS

We retrospectively enrolled all consecutive adult patients hospitalized due to AHF between January 2016 and January 2019. The ACUTE HF score is calculated by 7 different variables including age, creatinine, non-invasive ventilation, history of stroke or transient ischemic attack, left ventricular systolic function, mitral regurgitation and history of hospitalization.The primary endpoint of the study was in-hospital mortality.

RESULTS

A total of 418 AHF patients (mean age 70.2 ± 11.3 years, 52% male) were included, and 26 (6.2%) patients died during the in-hospital course. Patients in the study were divided into three groups according to ACUTE HF score: low-risk (<1.5, n = 210), intermediate-risk (1.5-3, n = 50), and high-risk groups (>3, n = 158). The multivariate analysis showed that the ACUTE HF score was an independent predictor of in-hospital mortality(OR: 2.15; 95% CI, 0.94-4.34; p < 0.001).

CONCLUSION

The ACUTE HF score was a useful prognostic score for the prediction of in-hospital mortality in patients with AHF. Further validation studies in different regions of the world and with different AHF populations are needed to determine its generalisability.

Excess 30-Day Heart Failure Readmissions and Mortality in Black Patients Increases With Neighborhood Deprivation

BACKGROUND

Longstanding racial disparities in heart failure (HF) outcomes exist in the United States, in part, due to social determinants of health. We examined whether neighborhood environment modifies the disparity in 30-day HF readmissions and mortality between Black and White patients in the Southeastern United States.

METHODS

We created a geocoded retrospective cohort of patients hospitalized for acute HF within Emory Healthcare from 2010 to 2018. Quartiles of the Social Deprivation Index characterized neighborhood deprivation at the census tract level. We estimated the relative risk of 30-day readmission and 30-day mortality following an index hospitalization for acute HF. Excess readmissions and mortality were estimated as the absolute risk difference between Black and White patients within each Social Deprivation Index quartile, adjusted for geographic clustering, demographic, clinical, and hospital characteristics.

RESULTS

The cohort included 30 630 patients, mean age 66 years, 48% female, 53% Black. Compared with White patients, Black patients were more likely to reside in deprived census tracts and have higher comorbidity scores. From 2010 to 2018, 29.4% of Black and 23.0% of White patients experienced either a 30-day HF readmission or 30-day death (P<0.001). Excess in composite 30-day HF readmissions and mortality for Black patients ranged from 3.9% (95% CI, 1.5%-6.3%; P=0.0002) to 6.8% (95% CI, 4.1%-9.5%; P<0.0001) across Social Deprivation Index quartiles. Accounting for traditional risk factors did not eliminate the Black excess in combined 30-day HF readmissions or mortality in any of the neighborhood quartiles.

CONCLUSIONS

Excess 30-day HF readmissions and mortality are present among Black patients in every neighborhood strata and increase with progressive neighborhood socioeconomic deprivation.

Machine learning prediction of the adverse outcome for nontraumatic subarachnoid hemorrhage patients

Objective

Subarachnoid hemorrhage (SAH) is often devastating with increased early mortality, particularly in those with presumed delayed cerebral ischemia (DCI). The ability to accurately predict survival for SAH patients during the hospital course would provide valuable information for healthcare providers, patients, and families. This study aims to utilize electronic health record (EHR) data and machine learning approaches to predict the adverse outcome for nontraumatic SAH adult patients.

Methods

The cohort included nontraumatic SAH patients treated with vasopressors for presumed DCI from a large EHR database, the Cerner Health Facts^® EMR database (2000–2014). The outcome of interest was the adverse outcome, defined as death in hospital or discharged to hospice. Machine learning‐based models were developed and primarily assessed by area under the receiver operating characteristic curve (AUC).

Results

A total of 2467 nontraumatic SAH patients (64% female; median age [interquartile range]: 56 [47–66]) who were treated with vasopressors for presumed DCI were included in the study. 934 (38%) patients died or were discharged to hospice. The model achieved an AUC of 0.88 (95% CI, 0.84–0.92) with only the initial 24 h EHR data, and 0.94 (95% CI, 0.92–0.96) after the next 24 h.

Interpretation

EHR data and machine learning models can accurately predict the risk of the adverse outcome for critically ill nontraumatic SAH patients. It is possible to use EHR data and machine learning techniques to help with clinical decision‐making.

Predictors of Heart Failure Readmission in a High-Risk Primarily Hispanic Population in a Rural Setting

BACKGROUND

High risk for readmission in patients with heart failure (HF) is associated with Hispanic ethnicity, multimorbidity, smaller hospitals, and hospitals serving low-socioeconomic or heavily Hispanic regions and those with limited cardiac services. Information for hospitals caring primarily for such high-risk patients is lacking.

OBJECTIVE

The aim of this study was to identify factors associated with 30-day HF readmission after HF hospitalization in a rural, primarily Hispanic, low-socioeconomic, and underserved region.

METHODS

Electronic medical records for all HF admissions within a 2-year period to a 107-bed hospital near the California-Mexico border were reviewed. Logistic regression was used to identify independent predictors of readmission.

RESULTS

A total of 189 unique patients had 30-day follow-up data. Patients were primarily Hispanic (71%), male (58%), and overweight or obese (82.5%) with 4 or more chronic conditions (83%) and a mean age of 68 years. The 30-day HF readmission rate was 5.3%. Early readmission was associated with history of HF, more previous emergency department (ED) and hospital visits, higher diastolic blood pressure and hypokalemia at presentation, shorter length of stay, and higher heart rate, diastolic blood pressure, and atrial fibrillation (AF) at discharge. Using logistic regression, previous 6-month ED visits (odds ratio, 1.5; P = .009) and AF at discharge (odds ratio, 5.7; P = .039) were identified as independent predictors of 30-day HF readmission.

CONCLUSIONS

Previous ED use and AF at discharge predicted early HF readmission in a high-risk, primarily Hispanic, rural population in a low-socioeconomic region.

Assessing the impact of social determinants of health on predictive models for potentially avoidable 30-day readmission or death

OBJECTIVES

Early hospital readmissions or deaths are key healthcare quality measures in pay-for-performance programs. Predictive models could identify patients at higher risk of readmission or death and target interventions. However, existing models usually do not incorporate social determinants of health (SDH) information, although this information is of great importance to address health disparities related to social risk factors. The objective of this study is to examine the impact of social determinants of health on predictive models for potentially avoidable 30-day readmission.

METHODS

We extracted electronic health record data for 19,941 hospital admissions between January 2015 and November 2017 at an academic medical center in New York City. We applied the Simplified HOSPITAL score model to predict potentially avoidable 30-day readmission or death and examined if incorporating individual- and community-level SDH could improve the prediction using cross-validation. We calculated the C-statistic for discrimination, Brier score for accuracy, and Hosmer-Lemeshow test for calibration for each model using logistic regression. Analysis was conducted for all patients and three subgroups that may be disproportionately affected by social risk factors, namely Medicaid patients, patients who are 65 or older, and obese patients.

RESULTS

The Simplified HOSPITAL score model achieved similar performance in our sample compared to previous studies. Adding SDH did not improve the prediction among all patients. However, adding individual- and community-level SDH at the US census tract level significantly improved the prediction for all three subgroups. Specifically, C-statistics improved from 0.70 to 0.73 for Medicaid patients, from 0.66 to 0.68 for patients 65 or older, and from 0.70 to 0.73 for obese patients.

CONCLUSIONS

Patients from certain subgroups may be more likely to be affected by social risk factors. Incorporating SDH into predictive models may be helpful to identify these patients and reduce health disparities associated with vulnerable social conditions.

Comparative Effectiveness of Primary Prevention Implantable Cardioverter-Defibrillators in Older Heart Failure Patients With Diabetes Mellitus

Background

There are conflicting data regarding the benefit of primary prevention implantable cardioverter‐defibrillators (ICDs) in patients with diabetes mellitus and heart failure (HF) with reduced ejection fraction. We aimed to assess the comparative effectiveness of ICD placement in patients with diabetes mellitus and HF with reduced ejection fraction.

Methods and Results

Data were obtained from the Get With the Guidelines–Health Failure registry, linked with claims from the Centers for Medicare & Medicaid Services. We used a Cox proportional hazards model censored at 5 years with propensity score matching. Of the 17 186 patients with HF with reduced ejection fraction from the Centers for Medicare & Medicaid Services claims database (6540 with diabetes mellitus; 38%), 1677 (646 with diabetes mellitus; 39%) received an ICD during their index HF hospitalization or were prescribed an ICD at discharge. Patients with diabetes mellitus and an ICD (n=646), as compared with those without an ICD (n=1031), were more likely to be younger (74 versus 78 years of age) and have coronary artery disease (68% versus 60%). After propensity matching, ICD use among patients with diabetes mellitus, as compared with those without an ICD, was associated with a reduced risk of all‐cause mortality at 5 years after HF discharge (54% versus 59%; multivariable hazard ratio, 0.73; 95% CI, 0.64–0.82; P<0.0001). Ischemic heart disease did not modify the association between ICD use and all‐cause mortality (P=0.95 for interaction). Similar results were seen in patients without diabetes mellitus.

Conclusions

Primary prevention ICD use among older patients with HF with reduced ejection fraction and diabetes mellitus was associated with a reduced risk of all‐cause mortality. Our analysis supports current guideline recommendations for implantation of primary prevention ICDs among older patients with diabetes mellitus and HF with reduced ejection fraction.

PredischaRge initiation of Ivabradine in the ManagEment of Heart Failure: Results of the PRIME-HF Trial

BACKGROUND

Ivabradine is guideline-recommended to reduce heart failure (HF) hospitalization in patients with stable chronic HF with reduced ejection fraction (EF). Ivabradine initiation following acute HF has had limited evaluation, and there are few randomized data in US patients. The PredischaRge initiation of Ivabradine in the ManagEment of Heart Failure (PRIME-HF) study was conducted to address predischarge ivabradine initiation in stabilized acute HF patients.

METHODS

PRIME-HF was an investigator-initiated, randomized, open-label study of predischarge initiation of ivabradine versus usual care. Eligible patients were hospitalized for acute HF but stabilized, with EF ≤35%, on maximally tolerated β-blocker and in sinus rhythm with heart rate ≥70 beats/min. Ivabradine was acquired per routine care. The primary end point was the proportion of patients on ivabradine at 180 days. Additional end points included heart rate change, patient-reported outcomes, β-blocker use/dose, and safety events (symptomatic bradycardia and hypotension).

RESULTS

Overall, 104 patients (36% women, 64% African American) were randomized, and the study was terminated early because of funding limitations. At 180 days, 21 of 52 (40.4%) of patients randomized to predischarge initiation were treated with ivabradine compared with 6 of 52 (11.5%) randomized to usual care (odds ratio 5.19, 95% CI 1.88-14.33, P = .002). The predischarge initiation group experienced greater reduction in heart rate through 180 days (mean -10.0 beats/min, 95% CI -15.7 to -4.3 vs 0.7 beats/min, 95% CI -5.4 to 6.7, P = .011). Patient-reported outcomes, β-blocker use/dose, and safety events were similar (all P > .05).

CONCLUSIONS

Ivabradine initiation prior to discharge among stabilized HF patients increased ivabradine use at 180 days and lowered heart rates without reducing β-blockers or increasing adverse events. As the trial did not achieve the planned enrollment, additional studies are needed.

Association between depression and readmission of heart failure: A national representative database study

INTRODUCTION

Depression is a recognized predictor of adverse outcomes in patients with heart failure (HF) and is associated with poor quality of life, functional limitation, increased morbidity and mortality, decreased adherence to treatment, and increased rehospitalization. To understand the impact of depression on HF readmission, we conducted a retrospective cohort study using the Nationwide Readmission Database (NRD) 2010-2014.

METHODS

We identified all patients with the primary discharge diagnosis of HF by ICD-9-CM codes. The primary outcome of the study was to identify 30-day all-cause readmission and causes of readmission in patients with and without depression. Multivariate Cox regression analysis was used to estimate the adjusted hazard ratio for the primary and secondary outcomes.

RESULTS

Among, 3,500,570 patients admitted with HF, 9.7% had concomitant depression. Patients with depression were more likely to be readmitted within 30 days (19.7% vs. 18.5%; P < 0.001). Concomitant depression was associated with higher risk of all-cause readmissions within 30 days and 90 days [P < 0.001] but was not associated with increased readmissions due to cardiovascular (CV) cause at 30 days and 90 days. The hazard of psychiatric causes of readmission was higher in patients with depression, both at 30 days [P < 0.001], and 90 days [P < 0.001]. Most of the readmissions were due to CV causes, with HF being the most common cause.

CONCLUSION

Among patients hospitalized with HF, the presence of depression is associated with increased all-cause readmission driven mainly by psychiatric causes but not CV-related readmission. Standard interventions targeted toward HF are unlikely to modify this portion of all-cause readmission.

Evaluating risk prediction models for adults with heart failure: A systematic literature review

Background

The ability to predict risk allows healthcare providers to propose which patients might benefit most from certain therapies, and is relevant to payers’ demands to justify clinical and economic value. To understand the robustness of risk prediction models for heart failure (HF), we conducted a systematic literature review to (1) identify HF risk-prediction models, (2) assess statistical approach and extent of validation, (3) identify common variables, and (4) assess risk of bias (ROB).

Methods

Literature databases were searched from March 2013 to May 2018 to identify risk prediction models conducted in an out-of-hospital setting in adults with HF. Distinct risk prediction variables were ranked according to outcomes assessed and incorporation into the studies. ROB was assessed using Prediction model Risk Of Bias ASsessment Tool (PROBAST).

Results

Of 4720 non-duplicated citations, 40 risk-prediction publications were deemed relevant. Within the 40 publications, 58 models assessed 55 (co)primary outcomes, including all-cause mortality (n = 17), cardiovascular death (n = 9), HF hospitalizations (n = 15), and composite endpoints (n = 14). Few publications reported detail on handling missing data (n = 11; 28%). The discriminatory ability for predicting all-cause mortality, cardiovascular death, and composite endpoints was generally better than for HF hospitalization. 105 distinct predictor variables were identified. Predictors included in >5 publications were: N-terminal prohormone brain-natriuretic peptide, creatinine, blood urea nitrogen, systolic blood pressure, sodium, NYHA class, left ventricular ejection fraction, heart rate, and characteristics including male sex, diabetes, age, and BMI. Only 11/58 (19%) models had overall low ROB, based on our application of PROBAST. In total, 26/58 (45%) models discussed internal validation, and 14/58 (24%) external validation.

Conclusions

The majority of the 58 identified risk-prediction models for HF present particular concerns according to ROB assessment, mainly due to lack of validation and calibration. The potential utility of novel approaches such as machine learning tools is yet to be determined.

Registration number

The SLR was registered in Prospero (ID: CRD42018100709).

The Three Rs for Preventing Heart Failure Readmission: Review, Reassess, and Reeducate

Despite improvements in heart failure therapies, hospitalization readmission rates remain high. Nationally, increasing attention has been directed toward reducing readmission rates and thus identifying patients with the highest risk for readmission. This article summarizes the evidence related to decreasing readmission for patients with heart failure within 30 days after discharge, focusing on the acute setting. Each patient requires an individualized plan for successful transition from hospital to home and preventing readmission. Nurses must review the patient's current plan of care and adherence to it and look for clues to failure of the plan that could lead to readmission to the hospital. In addition, nurses must reassess the current plan with the patient and family to ensure that the plan continues to meet the patient's needs. Finally, nurses must continually reeducate patients about their plan of care, their plan for self-management, and strategies to prevent hospital readmission for heart failure.

Designing risk prediction models for ambulatory no-shows across different specialties and clinics

Objective

As available data increases, so does the opportunity to develop risk scores on more refined patient populations. In this paper we assessed the ability to derive a risk score for a patient no-showing to a clinic visit.

Methods

Using data from 2 264 235 outpatient appointments we assessed the performance of models built across 14 different specialties and 55 clinics. We used regularized logistic regression models to fit and assess models built on the health system, specialty, and clinic levels. We evaluated fits based on their discrimination and calibration.

Results

Overall, the results suggest that a relatively robust risk score for patient no-shows could be derived with an average C-statistic of 0.83 across clinic level models and strong calibration. Moreover, the clinic specific models, even with lower training set sizes, often performed better than the more general models. Examination of the individual models showed that risk factors had different degrees of predictability across the different specialties. Implementation of optimal modeling strategies would lead to capturing an additional 4819 no-shows per-year.

Conclusion

Overall, this work highlights both the opportunity for and the importance of leveraging the available electronic health record data to develop more refined risk models.

Risk Prediction in Transition: MAGGIC Score Performance at Discharge and Incremental Utility of Natriuretic Peptides

BACKGROUND

Risk stratification for hospitalized patients with heart failure (HF) remains a critical need. The Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC) score is a robust model derived from patients with ambulatory HF. Its validity at the time of discharge and the incremental value of natriuretic peptides (NPs) in this setting is unclear.

METHODS

This was a single-center study examining a total of 4138 patients with HF from 2 groups; hospital discharge patients from administrative data (n = 2503, 60.5%) and a prospective registry of patients with ambulatory HF (n = 1635, 39.5%). The ambulatory registry patients underwent N-terminal pro-B-type NP (BNP) measurement at enrollment, and in the hospitalize discharge cohort clinical BNP levels were abstracted. The primary endpoint was all-cause mortality within 1 year. MAGGIC score performance was compared between cohorts utilizing Cox regression and calibration plots. The incremental value of NPs was assessed using calculated area under the curve and net reclassification improvement (NRI).

RESULTS

The hospitalized and ambulatory cohorts differed with respect to primary outcome (777 and 100 deaths, respectively), sex (52.1% vs 41.7% female) and race (35% vs 49.5% African American). The MAGGIC score showed poor discrimination of mortality risk in the hospital discharge (C statistic: 0.668, hazard ratio [HR]: 1.1 per point, 95% confidence interval [CI]: 0.652, 0.684) but fair discrimination in the ambulatory cohorts (C statistic: 0.784, HR: 1.16 per point, 95% CI: 0.74, 0.83), respectively, a difference that was statistically significant (P = .001 for C statistic, 0.002 for HR). Calibration assessment indicated that the slope and intercept (of MAGGIC-predicted to observed mortality) did not statistically differ from ideal in either cohort and did not differ between the cohorts (all P > .1). NP levels did not significantly improve prediction in the hospitalized cohort (P = .127) but did in the ambulatory cohort (C statistic: 0.784 [95% CI: 0.74, 0.83] vs 0.82 [95% CI: 0.78, 0.85]; P = .018) with a favorable NRI of 0.354 (95% CI: 0.202-0.469; P = .002).

CONCLUSION

The MAGGIC score showed poor discrimination when used in patients with HF at hospital discharge, which was inferior to its performance in patients with ambulatory HF. Discrimination within the hospital discharge group was not improved by including hospital NP levels.

Impact on Readmission Reduction Among Heart Failure Patients Using Digital Health Monitoring: Feasibility and Adoptability Study

Background

Heart failure (HF) is a condition that affects approximately 6.2 million people in the United States and has a 5-year mortality rate of approximately 42%. With the prevalence expected to exceed 8 million cases by 2030, projections estimate that total annual HF costs will increase to nearly US $70 billion. Recently, the advent of remote monitoring technology has significantly broadened the scope of the physician’s reach in chronic disease management.

Objective

The goal of our program, named the Heart Health Program, was to examine the feasibility of using digital health monitoring in real-world home settings, ascertain patient adoption, and evaluate impact on 30-day readmission rate.

Methods

A digital medicine software platform developed at Mount Sinai Health System, called RxUniverse, was used to prescribe a digital care pathway including the HealthPROMISE digital therapeutic and iHealth mobile apps to patients’ personal smartphones. Vital sign data, including blood pressure (BP) and weight, were collected through an ambulatory remote monitoring system that comprised a mobile app and complementary consumer-grade Bluetooth-connected smart devices (BP cuff and digital scale) that send data to the provider care teams. Care teams were alerted via a Web-based dashboard of abnormal patient BP and weight change readings, and further action was taken at the clinicians’ discretion. We used statistical analyses to determine risk factors associated with 30-day all-cause readmission.

Results

Overall, the Heart Health Program included 58 patients admitted to the Mount Sinai Hospital for HF. The 30-day hospital readmission rate was 10% (6/58), compared with the national readmission rates of approximately 25% and the Mount Sinai Hospital’s average of approximately 23%. Single marital status (P=.06) and history of percutaneous coronary intervention (P=.08) were associated with readmission. Readmitted patients were also less likely to have been previously prescribed angiotensin-converting enzyme inhibitors or angiotensin II receptor blockers (P=.02). Notably, readmitted patients utilized the BP and weight monitors less than nonreadmitted patients, and patients aged younger than 70 years used the monitors more frequently on average than those aged over 70 years, though these trends did not reach statistical significance. The percentage of the 58 patients using the monitors at least once dropped from 83% (42/58) in the first week after discharge to 46% (23/58) in the fourth week.

Conclusions

Given the increasing burden of HF, there is a need for an effective and sustainable remote monitoring system for HF patients following hospital discharge. We identified clinical and social factors as well as remote monitoring usage trends that identify targetable patient populations that could benefit most from integration of daily remote monitoring. In addition, we demonstrated that interventions driven by real-time vital sign data may greatly aid in reducing hospital readmissions and costs while improving patient outcomes.

The Impact of Transitions of Care Pharmacist Services and Identification of Risk Predictors in Heart Failure Readmission

BACKGROUND

Heart failure (HF) is a prevalent and costly disease state for adult Americans, with 30-day readmissions rates for patients with HF utilized to limit hospital compensation.

OBJECTIVE

To determine the impact of the transitions of care (TOC) service at our institution on 30-day all-cause and HF readmissions and identify predictive risk factors for 30-day all-cause readmission.

METHODS

Retrospective chart review of patients aged 18 years and older admitted with HF and all subsequent readmissions between October 1, 2015, and September 30, 2017. A weighted logistic regression model was developed to determine risk factors for 30-day all-cause readmission.

RESULTS

There were no significant differences in all-cause or HF readmission rates analyzed by TOC service involvement. Significant risk predictors for 30-day all-cause readmission included discharge to a rehabilitation facility (odds ratio [OR] = 9.3) or home with home health (OR = 1.6) versus home with self-care. Comorbidities associated with an increased risk of 30-day all-cause readmission included diabetes, coronary artery disease, and aortic stenosis. Use of angiotensin-converting enzyme inhibitors, angiotensin-receptor blockers, and spironolactone was associated with decreased risk of 30-day all-cause readmission.

CONCLUSION

Identified predictors in the patient population with HF at our institution may be used to target patients at increased risk of all-cause readmission within 30 days.

Outpatient Worsening Heart Failure as a Target for Therapy: A Review

Importance

Hospitalizations for worsening heart failure (WHF) represent an enormous public health and financial burden, with physicians, health systems, and payers placing increasing emphasis on hospitalization prevention. In addition, maximizing time out of the hospital is an important patient-centered outcome. In this review, we discuss the concept of outpatient WHF, highlight the rationale and data for the outpatient treatment of WHF as an alternative to hospitalization, and examine opportunities and strategies for developing outpatient "interceptive" therapies for treatment of worsening symptoms and prevention of hospitalization.

Observations

Worsening heart failure has traditionally been synonymous with an episode of in-hospital care for worsening symptoms. While WHF often leads to hospitalization, many patients experience WHF in the outpatient setting and carry a similarly poor prognosis. These findings support WHF as a distinct condition, independent of location of care. For those that are hospitalized, most patients have an uncomplicated clinical course, with diuretics as the only intravenous therapy. Although complicated scenarios exist, it is conceivable that improved tools for outpatient management of clinical congestion would allow a greater proportion of hospitalized patients to receive comparable care outside the hospital. Most patients with WHF have a gradual onset of congestive signs and symptoms, offering a potential window in which effective therapy may abort continued worsening and obviate the need for hospitalization. To date, outpatient WHF has received minimal attention in randomized clinical trials, but this high-risk group possesses key features that favor effective clinical trial investigation.

Conclusions and Relevance

As the public health and economic burdens of heart failure continue to grow, recognizing the entity of outpatient WHF is critical. Efforts to reduce heart failure hospitalization should include developing effective therapies and care strategies for outpatient WHF. The outpatient WHF population represents a major opportunity for therapeutic advancements that could fundamentally change heart failure care delivery.

The American Heart Association Heart Failure Summit, Bethesda, April 12, 2017

The American Heart Association convened a meeting to summarize the changing landscape of heart failure (HF), anticipate upcoming challenges and opportunities to achieve coordinated identification and treatment, and to recommend areas in need of focused efforts. The conference involved representatives from clinical care organizations, governmental agencies, researchers, patient advocacy groups, and public and private healthcare partners, demonstrating the breadth of stakeholders interested in improving care and outcomes for patients with HF. The main purposes of this meeting were to foster dialog and brainstorm actions to close gaps in identifying people with or at risk for HF and reduce HF-related morbidity, mortality, and hospitalizations. This report highlights the key topics covered during the meeting, including (1) identification of patients with or at risk for HF, (2) tracking patients once diagnosed, (3) application of population health approaches to HF, (4) improved strategies for reducing HF hospitalization (not just rehospitalization), and (5) promoting HF self-management.

TACIT (High Sensitivity Troponin T Rules Out Acute Cardiac Insufficiency Trial)

BACKGROUND

Identifying low-risk acute heart failure patients safe for discharge from the emergency department is a major unmet need.

METHODS AND RESULTS

A prospective, observational, multicenter pilot study targeting lower risk acute heart failure patients to determine whether hsTnT (high-sensitivity troponin T) identifies emergency department acute heart failure patients at low risk for rehospitalization and mortality. hsTnT was drawn at baseline and 3 hours. Phone follow-up occurred at 30 and 90 days. The primary end point composite of all-cause mortality, rehospitalization, and emergency department visits at 90 days (changed from 30 days because of lack of mortality events), analyzed using logistic regression. Secondary end points: 30- and 90-day all-cause mortality. hsTnT values less than the 99th percentile were defined as low hsTnT. Out of 527 enrolled patients, 499 comprised the initial analysis set. Of these, 332 had both 0- and 3-hour hsTnT drawn, of whom 319 completed 30 day follow-up. The average age was 62, 60% male, and 57% black. Median hsTnT was 26.4 ng/L (interquartile range, 15.1-44.3). There were 99 (21%) 30-day composite events, 13 (2.7%) deaths at 30 days, and 25 deaths (8.2%) at 90 days. Serial hsTnT values below the 99th percentile were not associated with a lower risk for the 90-day primary composite end point (odds ratio, 0.79; 95% CI, 0.42-1.50; P=0.4736). However, no deaths occurred in the low hsTnT group at 30 days with 1 death at 90 days.

CONCLUSIONS

hsTnT did not identify patients at low risk for the primary outcome of rehospitalization, emergency department visits, and mortality at 90 days.

CLINICAL TRIAL REGISTRATION

URL: https://www.clinicaltrials.gov . Unique identifier: NCT02592135.

Trends in Noncardiovascular Comorbidities Among Patients Hospitalized for Heart Failure: Insights From the Get With The Guidelines-Heart Failure Registry

BACKGROUND

The increase in medical complexity among patients hospitalized with heart failure (HF) may be reflected by an increase in concomitant noncardiovascular comorbidities. Among patients hospitalized with HF, the temporal trends in the prevalence of noncardiovascular comorbidities have not been well described.

METHODS AND RESULTS

We used data from 207 984 patients in the Get With The Guidelines-Heart Failure registry (from 2005 to 2014) to evaluate the prevalence and trends of noncardiovascular comorbidities (chronic obstructive pulmonary disorder/asthma, anemia, diabetes mellitus, obesity [body mass index ≥30 kg/m²], and renal impairment) among patients hospitalized with HF. Medicare beneficiaries aged ≥65 years were used to assess 30-day mortality. The prevalence of 0, 1, 2, and ≥3 noncardiovascular comorbidities was 18%, 30%, 27%, 25%, respectively. From 2005 to 2014, there was a decline in patients with 0 noncardiovascular comorbidities (22%-16%; P<0.0001) and an increase in patients with ≥3 noncardiovascular comorbidities (18%-29%; P<0.0001). Among Medicare beneficiaries, there was an increased 30-day adjusted mortality risk among patients with 1 noncardiovascular comorbidity (hazard ratio, 1.16; 95% confidence interval, 1.09-1.24; P<0.0001), 2 noncardiovascular comorbidities (hazard ratio, 1.34; 95% confidence interval, 1.25-1.44; P<0.0001), and ≥3 noncardiovascular comorbidities (hazard ratio, 1.63; 95% confidence interval, 1.51-1.75; P<0.0001). Similar trends were seen for in-hospital mortality.

CONCLUSIONS

Patients admitted in hospital for HF have an increasing number of noncardiovascular comorbidities over time, which are associated with worse outcomes. Strategies addressing the growing burden of noncardiovascular comorbidities may represent an avenue to improve outcomes and should be included in the delivery of in-hospital HF care.

Performance of the Meta-Analysis Global Group in Chronic Heart Failure Score in Black Patients Compared With Whites

BACKGROUND

Risk stratification is critical in heart failure (HF) and the Meta-Analysis Global Group in Chronic HF (MAGGIC) score is a validated tool derived from ~40,000 patients. However, few of these patients self-identified as black, raising uncertainty regarding performance in blacks with HF.

METHODS AND RESULTS

This study analyzed a racially diverse group of 4046 patients (1646 black and 2400 white) from a single center from 2007 to 2015. Baseline characteristics were collected to tabulate MAGGIC score and test its discrimination and calibration within race groups. The primary end point was all-cause mortality. Death was detected using system records and the social security death master file. Discrimination was tested using Cox models of MAGGIC score stratified by race, and combined analysis including MAGGIC, race, and MAGGIC×race. Calibration was assessed using linear regression models and plots of observed versus predicted data. Overall, 901 (21%) patients died during 1-year follow-up. MAGGIC score discrimination was similar in both race groups in terms of C statistic (0.707±0.027 versus 0.725±0.014, for black versus white; P=0.556) and the hazard ratio (HR) per MAGGIC point was 1.12 in black patients (95% CI, 1.10-1.14) and 1.13 in white patients (95% CI, 1.12-1.14). Race was a significant correlate of survival, with better survival in black patients compared with white (HR, 0.66; 95% CI, 0.56-0.78), but the interaction of MAGGIC×race was not significant (β=-0.013; P=0.16), and adding race to the model did not improve discrimination (C statistic for MAGGIC versus MAGGIC+race, 0.721 versus 0.722; P=0.79). In calibration testing, the slope was not significantly different from 1 in either group, but the groups differed from each other, and it was closer to unity among black patients (0.94 versus 1.4; P=0.004).

CONCLUSIONS

These data support the use of the MAGGIC score to risk stratify black patients with HF.

Clinical and Socioeconomic Predictors of Heart Failure Readmissions: A Review of Contemporary Literature

Heart failure represents a clinical syndrome that results from a constellation of disease processes affecting myocardial function. Although recent studies have suggested a declining or stable incidence of heart failure, patients with heart failure continue to have high hospitalization and readmission rates, resulting in a substantial economic and public health burden. We searched PubMed and Google Scholar to identify published literature from 1998 through 2018 using the following keywords: heart failure, readmissions, predictors, prediction models, and interventions. Cited references were also used to identify relevant literature. Developments in the diagnosis and management of patients with heart failure have improved hospitalization and readmission rates in the past few decades. However, heart failure remains the most common cause of hospitalization in persons older than 65 years. As a result, given the enormous clinical and financial burden associated with heart failure readmissions on health care, there has been growing interest in the investigation of mechanisms aimed at improving outcomes and curtailing associated costs of care. Herein, we review the current literature on clinical and socioeconomic predictors of heart failure readmissions, briefly discussing limitations of existing strategies and providing an overview of current technology aimed at reducing hospitalizations.

Do Hospital and Physician Volume Thresholds for the Volume-Outcome Relationship in Heart Failure Exist?

BACKGROUND

Although volume-outcome relationships have been explored for various procedures and interventions, limited information is available concerning the effect of hospital and physician volume on heart failure mortality. Most importantly, little is known about whether there are optimal hospital and physician volume thresholds to reduce heart failure mortality.

OBJECTIVES

We used nationwide population-based data to identify the optimal hospital and physician volume thresholds to achieve optimum mortality and to examine the relative and combined effects of the volume thresholds on heart failure mortality.

METHODS

We analyzed all 20,178 heart failure patients admitted in 2012 through Taiwan's National Health Insurance Research Database. Restricted cubic splines and multilevel logistic regression were used to identify whether there are optimal hospital and physician volume thresholds and to assess the relative and combined relationships of the volume thresholds to 30-day mortality, adjusted for patient, physician, and hospital characteristics.

RESULTS

Hospital and physician volume thresholds of 40 cases and 15 cases a year, respectively, were identified, under which there was an increased risk of 30-day mortality. Patients treated by physicians with previous annual volumes <15 cases had higher 30-day mortality compared with those with previous annual volumes ≥15 cases, and the relationship was stronger in hospitals with previous annual volumes <40 cases.

CONCLUSIONS

This is the first study to identify both the hospital and physician volume thresholds that lead to decreases in heart failure mortality. Identifying the hospital and physician volume thresholds could be applied to quality improvement and physician training.

Predicting Future Cardiovascular Events in Patients With Peripheral Artery Disease Using Electronic Health Record Data

BACKGROUND

Patients with peripheral artery disease (PAD) are at risk of major adverse cardiac and cerebrovascular events. There are no readily available risk scores that can accurately identify which patients are most likely to sustain an event, making it difficult to identify those who might benefit from more aggressive intervention. Thus, we aimed to develop a novel predictive model-using machine learning methods on electronic health record data-to identify which PAD patients are most likely to develop major adverse cardiac and cerebrovascular events.

METHODS AND RESULTS

Data were derived from patients diagnosed with PAD at 2 tertiary care institutions. Predictive models were built using a common data model that allowed for utilization of both structured (coded) and unstructured (text) data. Only data from time of entry into the health system up to PAD diagnosis were used for modeling. Models were developed and tested using nested cross-validation. A total of 7686 patients were included in learning our predictive models. Utilizing almost 1000 variables, our best predictive model accurately determined which PAD patients would go on to develop major adverse cardiac and cerebrovascular events with an area under the curve of 0.81 (95% CI, 0.80-0.83).

CONCLUSIONS

Machine learning algorithms applied to data in the electronic health record can learn models that accurately identify PAD patients at risk of future major adverse cardiac and cerebrovascular events, highlighting the great potential of electronic health records to provide automated risk stratification for cardiovascular diseases. Common data models that can enable cross-institution research and technology development could potentially be an important aspect of widespread adoption of newer risk-stratification models.

Design and rationale of the B-lines lung ultrasound guided emergency department management of acute heart failure (BLUSHED-AHF) pilot trial

BACKGROUND

Medical treatment for acute heart failure (AHF) has not changed substantially over the last four decades. Emergency department (ED)-based evidence for treatment is limited. Outcomes remain poor, with a 25% mortality or re-admission rate within 30days post discharge. Targeting pulmonary congestion, which can be objectively assessed using lung ultrasound (LUS), may be associated with improved outcomes.

METHODS

BLUSHED-AHF is a multicenter, randomized, pilot trial designed to test whether a strategy of care that utilizes a LUS-driven treatment protocol outperforms usual care for reducing pulmonary congestion in the ED. We will randomize 130 ED patients with AHF across five sites to, a) a structured treatment strategy guided by LUS vs. b) a structured treatment strategy guided by usual care. LUS-guided care will continue until there are ≤15 B-lines on LUS or 6h post enrollment. The primary outcome is the proportion of patients with B-lines ≤ 15 at the conclusion of 6 h of management. Patients will continue to undergo serial LUS exams during hospitalization, to better understand the time course of pulmonary congestion. Follow up will occur through 90days, exploring days-alive-and-out-of-hospital between the two arms. The study is registered on ClinicalTrials.gov (NCT03136198).

CONCLUSION

If successful, this pilot study will inform future, larger trial design on LUS driven therapy aimed at guiding treatment and improving outcomes in patients with AHF.

Predictive models for identifying risk of readmission after index hospitalization for heart failure: A systematic review

Aims:

Readmission rates for patients with heart failure have consistently remained high over the past two decades. As more electronic data, computing power, and newer statistical techniques become available, data-driven care could be achieved by creating predictive models for adverse outcomes such as readmissions. We therefore aimed to review models for predicting risk of readmission for patients admitted for heart failure. We also aimed to analyze and possibly group the predictors used across the models.

Methods:

Major electronic databases were searched to identify studies that examined correlation between readmission for heart failure and risk factors using multivariate models. We rigorously followed the review process using PRISMA methodology and other established criteria for quality assessment of the studies.

Results:

We did a detailed review of 334 papers and found 25 multivariate predictive models built using data from either health system or trials. A majority of models was built using multiple logistic regression followed by Cox proportional hazards regression. Some newer studies ventured into non-parametric and machine learning methods. Overall predictive accuracy with C-statistics ranged from 0.59 to 0.84. We examined significant predictors across the studies using clinical, administrative, and psychosocial groups.

Conclusions:

Complex disease management and correspondingly increasing costs for heart failure are driving innovations in building risk prediction models for readmission. Large volumes of diverse electronic data and new statistical methods have improved the predictive power of the models over the past two decades. More work is needed for calibration, external validation, and deployment of such models for clinical use.

An integrative review of the literature on in-hospital worsening heart failure

A subset of patients hospitalized for acute exacerbation of chronic heart failure develop in-hospital worsening heart failure. The objective of this paper is to present an integrative review of in-hospital worsening heart failure, including definitions, incidence, prevalence, mechanisms, treatments, outcomes, and early identification by providers. A search of electronic databases was conducted from January 2000-August 2017 using multiple search terms. Papers were reviewed for relevance; retained papers were abstracted and data were reported in a narrative synthesis. Twenty papers were selected. Many papers were observational data from in-hospital events that occurred during research trials. There was great variability in in-hospital worsening heart failure definition, incidence, prevalence, and treatments offered. Despite rescue therapies, in-hospital worsening heart failure was associated with increased risk for longer hospital stays, higher readmission rates, and death. To date, there are no therapies that target the underlying mechanisms or minimize its occurrence.