Predicting High-Risk Patients and High-Risk Outcomes in Heart Failure

Echocardiography-Derived Forward Left Ventricular Output Improves Risk Prediction in Systolic Heart Failure

BACKGROUND

Although it is widely used to classify patients with heart failure (HF), the prognostic role of left ventricular ejection fraction (LVEF) is debated. The aim of this study was to test the hypothesis that echocardiographic measures of forward left ventricular (LV) output, being more representative of cardiac hemodynamics, might improve risk prediction in a large cohort of patients with HF with systolic dysfunction.

METHODS

Consecutive stable patients with HF with LVEF <50% on guideline-recommended therapies undergoing echocardiography including the evaluation of forward LV output (i.e., LV outflow tract [LVOT] velocity-time integral [VTI], stroke volume index [SVi], and cardiac index) over a 6-year period were selected and followed for the end point of cardiac and all-cause death.

RESULTS

Among the 1,509 patients analyzed (mean age, 71 ± 12 years; 75% men; mean LVEF, 35 ± 9%), 328 (22%) died during a median follow-up period of 28 months (interquartile range, 14-40 months), 165 (11%) of cardiac causes. On multivariable regression analysis, LVOT VTI (P < .001), SVi (P < .001), and cardiac index (P < .001), but not LVEF (P > .05), predicted cardiac and all-cause death. The optimal prognostic cutoffs for LVOT VTI, SVi, and cardiac index were 15 cm, 38 mL/m2, and 2 L/min/m2, respectively. Adding each of these measures to a multivariable risk model (including clinical, biohumoral, and echocardiographic markers) improved risk prediction (P < .001). Among the different measures of forward LV output, cardiac index was less accurate than LVOT VTI and SVi.

CONCLUSIONS

The echocardiographic evaluation of forward LV output improves risk prediction in patients with HF across a wide LVEF spectrum over other well-established clinical, biohumoral, and echocardiographic prognostic markers.

Recent advancements and applications of deep learning in heart failure: Α systematic review

BACKGROUND

Heart failure (HF), a global health challenge, requires innovative diagnostic and management approaches. The rapid evolution of deep learning (DL) in healthcare necessitates a comprehensive review to evaluate these developments and their potential to enhance HF evaluation, aligning clinical practices with technological advancements.

OBJECTIVE

This review aims to systematically explore the contributions of DL technologies in the assessment of HF, focusing on their potential to improve diagnostic accuracy, personalize treatment strategies, and address the impact of comorbidities.

METHODS

A thorough literature search was conducted across four major electronic databases: PubMed, Scopus, Web of Science and IEEE Xplore, yielding 137 articles that were subsequently categorized into five primary application areas: cardiovascular disease (CVD) classification, HF detection, image analysis, risk assessment, and other clinical analyses. The selection criteria focused on studies utilizing DL algorithms for HF assessment, not limited to HF detection but extending to any attempt in analyzing and interpreting HF-related data.

RESULTS

The analysis revealed a notable emphasis on CVD classification and HF detection, with DL algorithms showing significant promise in distinguishing between affected individuals and healthy subjects. Furthermore, the review highlights DL's capacity to identify underlying cardiomyopathies and other comorbidities, underscoring its utility in refining diagnostic processes and tailoring treatment plans to individual patient needs.

CONCLUSIONS

This review establishes DL as a key innovation in HF management, highlighting its role in advancing diagnostic accuracy and personalized care. The insights provided advocate for the integration of DL in clinical settings and suggest directions for future research to enhance patient outcomes in HF care.

Performance of risk models to predict mortality risk for patients with heart failure: evaluation in an integrated health system

BACKGROUND

Referral of patients with heart failure (HF) who are at high mortality risk for specialist evaluation is recommended. Yet, most tools for identifying such patients are difficult to implement in electronic health record (EHR) systems.

OBJECTIVE

To assess the performance and ease of implementation of Machine learning Assessment of RisK and EaRly mortality in Heart Failure (MARKER-HF), a machine-learning model that uses structured data that is readily available in the EHR, and compare it with two commonly used risk scores: the Seattle Heart Failure Model (SHFM) and Meta-Analysis Global Group in Chronic (MAGGIC) Heart Failure Risk Score.

DESIGN

Retrospective, cohort study.

PARTICIPANTS

Data from 6764 adults with HF were abstracted from EHRs at a large integrated health system from 1/1/10 to 12/31/19.

MAIN MEASURES

One-year survival from time of first cardiology or primary care visit was estimated using MARKER-HF, SHFM, and MAGGIC. Discrimination was measured by the area under the receiver operating curve (AUC). Calibration was assessed graphically.

KEY RESULTS

Compared to MARKER-HF, both SHFM and MAGGIC required a considerably larger amount of data engineering and imputation to generate risk score estimates. MARKER-HF, SHFM, and MAGGIC exhibited similar discriminations with AUCs of 0.70 (0.69-0.73), 0.71 (0.69-0.72), and 0.71 (95% CI 0.70-0.73), respectively. All three scores showed good calibration across the full risk spectrum.

CONCLUSIONS

These findings suggest that MARKER-HF, which uses readily available clinical and lab measurements in the EHR and required less imputation and data engineering than SHFM and MAGGIC, is an easier tool to identify high-risk patients in ambulatory clinics who could benefit from referral to a HF specialist.

Association between performance measures and clinical outcomes in patients with heart failure in China: Results from the HERO study

BACKGROUND

There is great heterogeneity in the quality of care among hospitals in China, but studies on the performance measures and prognosis of patients with heart failure (HF) are still deficient.

HYPOTHESIS

Performance measures have been used as a guideline to clinicans, however, the association between them and outcomes among HF patients in China remains unclear.

METHODS

We analyzed 4497 patients with HF from the Heart Failure Registry of Patient Outcomes study. Performance measures were determined according to the guidelines, and the patients were divided into four groups based on a composite performance score. Multiple imputation and Cox proportional-hazard regression models were used to assess the association between the performance measures and clinical outcomes.

RESULTS

Overall, only 12.5% of patients met the top 25% of the performance measures, whereas 33.5% of patients met the bottom 25% of the measures. A total of 992 (22.2%) patients died within 1 year, involving a larger proportion of patients who had met only the bottom 25% of the performance measures than had met the top 25% (27.0% vs. 16.3%, respectively). The patients who met the top 25% of the measures had a lower 1-year mortality rate (adjusted hazard ratio: 0.78, 95% confidence interval: 0.61-0.98).

CONCLUSIONS

The association between performance measures and mortality appeared to follow a dose-response pattern with a larger degree of compliance with performance measures being associated with a lower mortality rate in patients with HF. Accordingly, the quality of care for patients with HF in China needs to be further improved.

Body composition, lipid profile and clinical parameters are predictors of prognosis in patients with heart failure: Two-year follow-up

BACKGROUND

Heart failure (HF) is a complex syndrome that leads to changes in body composition and eventually results in unfavorable outcomes.

AIM

This study aimed to evaluate body composition, lipid profiles and clinical parameters of patients with HF, and their associations with both survival and unfavorable clinical outcomes.

METHODS

This prospective cohort study included 94 adults and older people with HF. Body composition was assessed by bioelectrical impedance analysis (BIA). Anthropometric variables and lipid profile were also evaluated. Electronic medical records were checked to collect information on clinical outcomes (mortality and hospitalization), considering a follow-up period of 24 months. Survival was calculated using the Kaplan-Meier estimate, and the curves compared using Log-Rank. The death risk rate (Hazard Ratio, HR) was calculated using Cox's univariate models.

RESULTS

Mean age was 55.1 (13.9) years and there was a higher frequency of males. There was a predominance of HF with reduced ejection fraction, and ischemic etiology. Patients with New York Heart Association (NYHA) functional classification I/II had a better overall survival rate at 24 months than those with NYHA III/IV (univariate HR 4.93 (1.76-13.82); p = 0.001). Greater survival rates were found in patients without chronic kidney disease (CKD) (univariate HR 2.93 (1.59-5.39); p = 0.01). In the multivariate analyses, both dyslipidemia (adjusted HR 3.84 (1.22-12.00); p = 0.021) and increased fat mass index (FMI) were associated with overall survival rate (adjusted HR 3.59 (1, 10-11.74); p = 0.034).

CONCLUSION

The severity of HF symptoms and the presence of chronic kidney disease are associated with higher mortality. Increased fat mass index and dyslipidemia are predictors of favorable outcomes in this population.

Heart failure diagnosis in the general community - Who, how and when? A clinical consensus statement of the Heart Failure Association (HFA) of the European Society of Cardiology (ESC)

A significant proportion of patients experience delays in the diagnosis of heart failure due to the non-specific signs and symptoms of the syndrome. Diagnostic tools such as measurement of natriuretic peptide concentrations are fundamentally important when screening for heart failure, yet are frequently under-utilized. This clinical consensus statement provides a diagnostic framework for general practitioners and non-cardiology community-based physicians to recognize, investigate and risk-stratify patients presenting in the community with possible heart failure.

Long-Term Trajectories of Biomarkers, Functional, and Echocardiographic Parameters in Patients with Chronic Heart Failure from Dilated or Ischaemic Cardiomyopathy

INTRODUCTION

The long-term evolution of clinical, echocardiographic, and laboratory parameters of cardiac function in patients with chronic heart failure (HF) with either reduced (HFrEF) or mildly reduced (HFmrEF) left ventricular ejection fraction (LVEF) is incompletely characterised.

METHODS

We identified patients with chronic stable HF who presented at least twice to a university HF outpatient clinic between 1995 and 2021. Trajectories of NYHA functional class, LVEF, left ventricular internal end-diastolic diameter (LVIDD), NT-proBNP concentrations, and HF treatment over 10 years of follow-up were analysed using fractional polynomials. Analyses were repeated after stratifying patients according to aetiology (ischaemic vs. dilated) or HF category (HFrEF vs. HFmrEF).

RESULTS

A total of 2,132 patients were included, of whom 51% had ischaemic and 49% had dilated HF. Eighty six percent and 14% were classified as HFrEF and HFmrEF, respectively. Mean LVEF was 28 ± 10%, and median NT-proBNP and estimated glomerular filtration rate values were 1,170 (385-3,176) pmol/L and 81 (62-100) mL/min/1.73 m2, respectively. Median follow-up was 5.2 (2.6-9.2) years. Overall, NYHA functional class and LVIDD trajectories were U-shaped, whereas LVEF and NT-proBNP concentrations markedly improved during the first year and remained stable thereafter. However, the evolution of HF parameters significantly differed with respect to HF category and aetiology, with greater improvements seen in patients with HFrEF of non-ischaemic origin. Improvements in HF variables were associated with optimization of HF therapy, notably with initiation and up-titration of renin-angiotensin-system blockers.

CONCLUSION

This study provides insights into the natural history of HF in a large cohort of well-treated chronic HF outpatients with respect to subgroups of HF and different aetiologists.

Update on the Practical Role of Echocardiography in Selection, Implantation, and Management of Patients Requiring Left Ventricular Assist Device Therapy

PURPOSE OF REVIEW

Echocardiography is a valuable tool for management of patients with a left ventricular assist device (LVAD). We present an updated review on the practical applications of the role of echocardiography for pre- and postoperative evaluation of patients selected.

RECENT FINDINGS

The LVAD is a temporary or permanent option for patients with advanced heart failure who are unresponsive to other therapy. Use of the device has its own risks, and implantation remains a complex procedure. Transthoracic and transesophageal echocardiography are useful tools for patient evaluation and monitoring both peri- and postoperatively, as we previously presented. Assessment of left and right ventricular function, complications such as thrombus formation or intracardiac shunting, and valvular disease are all important in this assessment. This also aids in predicting postoperative complications. Placement of the device is confirmed intraoperatively, and subsequent ramp studies are used to determine optimal device settings. Right ventricular (RV) failure is the most common postoperative complication and preoperative evaluation of its function is crucial. Studies suggest that tricuspid annular plane systolic excursion, RV fractional area change, and RV global longitudinal strain are strong predictors of RV failure; LV ejection fraction, size, and end-diastolic diameter are also important markers. Aortic regurgitation and mitral stenosis must always be corrected prior to LVAD placement. However, direct visualization before and after implantation, especially to rule out potential contraindications such as thrombi, cannot be overemphasized. Ramp studies remain an integral part of device optimization and may result in greater myocardial recovery than previously realized.

Remotely Monitored Cardiac Implantable Electronic Device Data Predict All-Cause and Cardiovascular Unplanned Hospitalization

Background Unplanned hospitalizations are common in patients with cardiovascular disease. The "Triage Heart Failure Risk Status" (Triage-HFRS) algorithm in patients with cardiac implantable electronic devices uses data from up to 9 device-derived physiological parameters to stratify patients as low/medium/high risk of 30-day heart failure (HF) hospitalization, but its use to predict all-cause hospitalization has not been explored. We examined the association between Triage-HFRS and risk of all-cause, cardiovascular, or HF hospitalization. Methods and Results A prospective observational study of 435 adults (including patients with and without HF) with a Medtronic Triage-HFRS-enabled cardiac implantable electronic device (cardiac resynchronization therapy device, implantable cardioverter-defibrillator, or pacemaker). Cox proportional hazards models explored association between Triage-HFRS and time to hospitalization; a frailty term at the patient level accounted for repeated measures. A total of 274 of 435 patients (63.0%) transmitted ≥1 high HFRS transmission before or during the study period. The remaining 161 patients never transmitted a high HFRS. A total of 153 (32.9%) patients had ≥1 unplanned hospitalization during the study period, totaling 356 nonelective hospitalizations. A high HFRS conferred a 37.3% sensitivity and an 86.2% specificity for 30-day all-cause hospitalization; and for HF hospitalizations, these numbers were 62.5% and 85.6%, respectively. Compared with a low Triage-HFRS, a high HFRS conferred a 4.2 relative risk of 30-day all-cause hospitalization (8.5% versus 2.0%), a 5.0 relative risk of 30-day cardiovascular hospitalization (3.6% versus 0.7%), and a 7.7 relative risk of 30-day HF hospitalization (2.0% versus 0.3%). Conclusions In patients with cardiac implantable electronic devices, remotely monitored Triage-HFRS data discriminated between patients at high and low risk of all-cause hospitalization (cardiovascular or noncardiovascular) in real time.

Advances in Machine Learning Approaches to Heart Failure with Preserved Ejection Fraction

Heart failure with preserved ejection fraction (HFpEF) represents a prototypical cardiovascular condition in which machine learning may improve targeted therapies and mechanistic understanding of pathogenesis. Machine learning, which involves algorithms that learn from data, has the potential to guide precision medicine approaches for complex clinical syndromes such as HFpEF. It is therefore important to understand the potential utility and common pitfalls of machine learning so that it can be applied and interpreted appropriately. Although machine learning holds considerable promise for HFpEF, it is subject to several potential pitfalls, which are important factors to consider when interpreting machine learning studies.

Liver stiffness for predicting adverse cardiac events in chinese patients with heart failure: a two-year prospective study

BACKGROUND

To investigate whether liver stiffness (LS) can predict adverse cardiac events in Chinese patients with heart failure (HF).

METHODS

A total of 53 hospitalized patients with HF were enrolled, and LS and tricuspid annual plane systolic excursion (TAPSE) were determined with Fibroscan® and echocardiography before discharge. They were divided into two groups: high LS group (LS > 6.9 Kpa, n = 23) and low LS group (LS ≤ 6.9 Kpa, n = 30). Patients were followed up for 24 months at an interval of 3 months. The endpoint of follow-up was death or rehospitalization for HF.

RESULTS

All patients were followed up for 24 months or until the endpoint. Patients in the high LS group had lower platelet count (P = 0.014), lower creatine clear rate (P = 0.014), higher level of B-type natriuretic peptide at discharge (P = 0.012), and lower TAPSE (P < 0.001) than those in the low LS group. During 24 months of follow-up, 3 (5.7%) deaths and 21 (39.6%) hospitalizations for HF were observed. Patients in the high LS group had a higher rate of death/rehospitalization than those in the low LS group (Hazard ratio 4.81; 95% confidence interval 1.69-13.7, P = 0.003) after adjustment for age, sex, platelet count, creatine clear rate, and B-type natriuretic peptide level. Moreover, TAPSE ≤ 16 could predict adverse cardiac events with an HR of 6.63 (95% confidence interval 1.69-13.7, P = 0.004) after adjustment for age, sex, platelet count, creatine clear rate, and B-type natriuretic peptide level.

CONCLUSION

LS and TAPSE could be used to predict worse outcomes in patients with HF.

Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19

As predicting the trajectory of COVID-19 is challenging, machine learning models could assist physicians in identifying high-risk individuals. This study compares the performance of 18 machine learning algorithms for predicting ICU admission and mortality among COVID-19 patients. Using COVID-19 patient data from the Mass General Brigham (MGB) Healthcare database, we developed and internally validated models using patients presenting to the Emergency Department (ED) between March-April 2020 (n = 3597) and further validated them using temporally distinct individuals who presented to the ED between May-August 2020 (n = 1711). We show that ensemble-based models perform better than other model types at predicting both 5-day ICU admission and 28-day mortality from COVID-19. CRP, LDH, and O2 saturation were important for ICU admission models whereas eGFR <60 ml/min/1.73 m2, and neutrophil and lymphocyte percentages were the most important variables for predicting mortality. Implementing such models could help in clinical decision-making for future infectious disease outbreaks including COVID-19.

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.