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

Development and Validation of a Protein Risk Score for Mortality in Heart Failure : A Community Cohort Study

BACKGROUND

Heart failure (HF) is a complex clinical syndrome with high mortality. Current risk stratification approaches lack precision. High-throughput proteomics could improve risk prediction. Its use in clinical practice to guide the management of patients with HF depends on validation and evidence of clinical benefit.

OBJECTIVE

To develop and validate a protein risk score for mortality in patients with HF.

DESIGN

Community-based cohort.

SETTING

Southeast Minnesota.

PARTICIPANTS

Patients with HF enrolled between 2003 and 2012 and followed through 2021.

MEASUREMENTS

A total of 7289 plasma proteins in 1351 patients with HF were measured using the SomaScan Assay (SomaLogic). A protein risk score was derived using least absolute shrinkage and selection operator regression and temporal validation in patients enrolled between 2003 and 2007 (development cohort) and 2008 and 2012 (validation cohort). Multivariable Cox regression was used to examine the association between the protein risk score and mortality. The performance of the protein risk score to predict 5-year mortality risk was assessed using calibration plots, decision curves, and relative utility analyses and compared with a clinical model, including the Meta-Analysis Global Group in Chronic Heart Failure mortality risk score and N-terminal pro-B-type natriuretic peptide.

RESULTS

The development (n = 855; median age, 78 years; 50% women; 29% with ejection fraction <40%) and validation cohorts (n = 496; median age, 76 years; 45% women; 33% with ejection fraction <40%) were mostly similar. In the development cohort, 38 unique proteins were selected for the protein risk score. Independent of ejection fraction, the protein risk score demonstrated good calibration, reclassified mortality risk particularly at the extremes of the risk distribution, and showed greater clinical utility compared with the clinical model.

LIMITATION

Participants were predominantly of European ancestry, potentially limiting the generalizability of the findings to different patient populations.

CONCLUSION

Validation of the protein risk score demonstrated good calibration and evidence of predicted benefits to stratify the risk for death in HF superior to that of clinical methods. Further studies are needed to prospectively evaluate the score's performance in diverse populations and determine risk thresholds for interventions.

PRIMARY FUNDING SOURCE

Division of Intramural Research at the National Heart, Lung, and Blood Institute of the National Institutes of Health.

An update on utilising brain natriuretic peptide for risk stratification, monitoring and guiding therapy in heart failure

INTRODUCTION

Heart failure (HF) is a dominant health problem with an overall poor prognosis. Natriuretic peptides (NPs) are upregulated in HF as a compensatory mechanism. They have extensively been used for diagnosis and risk stratification.

AREAS COVERED

This review addresses the history and physiology of NPs in order to understand their current role in clinical practice. It further provides a detailed and updated narrative review on the utility of those biomarkers for risk stratification, monitoring, and guiding therapy in HF.

EXPERT OPINION

NPs show excellent predictive ability in heart failure patients, both in acute and chronic settings. Understanding their pathophysiology and their modifications in specific situations is key for an adequate interpretation in specific clinical scenarios in which their prognostic value may be weaker or less well evaluated. To better promote risk stratification in HF, NPs should be integrated with other predictive tools to develop multiparametric risk models. Both inequalities of access to NPs and evidence caveats and limitations will need to be addressed by future research in the coming years.

Validation of the Meta-Analysis Global Group in Chronic Heart Failure risk score for the prediction of 1-year mortality in a Chinese cohort

BACKGROUND

The Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC) risk score was developed in 2013 to predict survival in heart failure (HF) patients. However, it has yet to be validated in a Chinese population. Our study aimed to investigate the ability of the score to predict 1-year mortality in a Chinese population.

METHODS

Consecutive patients with HF were retrospectively selected from the inpatient electronic medical records of the cardiology department in a regional hospital in China. A total integer score was calculated for each enrolled patient based on the value of each risk factor in the MAGGIC scoring system. Each enrolled patient was followed for at least 1 year. The observational endpoint of this study was all-cause mortality. The predictive ability of the MAGGIC score was assessed by comparing observed and predicted mortality within 1 year.

RESULTS

Between January 2018 and December 2020, a total of 635 patients were included in the study: 57 (9.0%) of whom died within 1 year after discharge. The average age of all patients was 74.6 ± 11.2 years, 264 of them (41.6%) were male, and the average left ventricular ejection fraction was 50.7% ± 13.2%. The area under the receiver operating characteristic curve was 0.840 (95% confidence interval: 0.779, 0.901), which indicated a fair discriminatory ability of the score. The Hosmer-Lemeshow test result ( χ2  = 12.902, degree of freedom = 8, P   =  0.115) indicated that the MAGGIC score had good calibration. The decision curve analysis showed that the MAGGIC score yielded a good clinical net benefit and net reduction in interventions.

CONCLUSIONS

This validation of the MAGGIC score showed that it has a good ability to predict 1-year mortality in Chinese patients with HF after discharge. Due to regional and inter-hospital differences, external validation studies need to be further confirmed in other centers.

Performance of current risk stratification models for predicting mortality in patients with heart failure: a systematic review and meta-analysis

AIMS

There are several risk scores designed to predict mortality in patients with heart failure (HF). This study aimed to assess performance of risk scores validated for mortality prediction in patients with acute HF (AHF) and chronic HF.

METHODS AND RESULTS

MEDLINE and Scopus were searched from January 2015 to January 2021 for studies which internally or externally validated risk models for predicting all-cause mortality in patients with AHF and chronic HF. Discrimination data were analysed using C-statistics, and pooled using generic inverse-variance random-effects model. Nineteen studies (n = 494 156 patients; AHF: 24 762; chronic HF mid-term mortality: 62 000; chronic HF long-term mortality: 452 097) and 11 risk scores were included. Overall, discrimination of risk scores was good across the three subgroups: AHF mortality [C-statistic: 0.76 (0.68-0.83)], chronic HF mid-term mortality [1 year; C-statistic: 0.74 (0.68-0.79)], and chronic HF long-term mortality [≥2 years; C-statistic: 0.71 (0.69-0.73)]. MEESSI-AHF [C-statistic: 0.81 (0.80-0.83)] and MARKER-HF [C-statistic: 0.85 (0.80-0.89)] had an excellent discrimination for AHF and chronic HF mid-term mortality, respectively, whereas MECKI had good discrimination [C-statistic: 0.78 (0.73-0.83)] for chronic HF long-term mortality relative to other models. Overall, risk scores predicting short-term mortality in patients with AHF did not have evidence of poor calibration (Hosmer-Lemeshow P > 0.05). However, risk models predicting mid-term and long-term mortality in patients with chronic HF varied in calibration performance.

CONCLUSIONS

The majority of recently validated risk scores showed good discrimination for mortality in patients with HF. MEESSI-AHF demonstrated excellent discrimination in patients with AHF, and MARKER-HF and MECKI displayed an excellent discrimination in patients with chronic HF. However, modest reporting of calibration and lack of head-to-head comparisons in same populations warrant future studies.

The MAGGIC risk score in the prediction of death or hospitalization in patients with heart failure: Comparison with natriuretic peptides

BACKGROUND

The MAGGIC risk score has been validated to predict mortality in patients with heart failure (HF).

OBJECTIVES

To assess the score ability to predict hospitalization and death and to compare with natriuretic peptides.

METHODS

Ninety-three consecutive patients (mean age 62±10 years) with chronic HF and left ventricular ejection fraction (EF) <50% were studied. The MAGGIC score was applied at baseline and the patients were followed for 219±86 days. MAGGIC score was compared with NT-proBNP in the prediction of events. The primary end point was the time to the first event, which was defined as cardiovascular death or hospitalization for HF.

RESULTS

There were 23 (24.7%) events (3 deaths and 20 hospitalizations). The median score in patients with and without events was, respectively, 20 [interquartile range 14.2-22] vs. 15.5 [11/21], p=0.16. A ROC curve was performed and a cutoff point of 12 points showed a sensitivity of 87% and specificity of 37% with an area under the curve of 0.59 (95% CI 0.48-0.69) which was lower than that of NT-proBNP (AUC 0.67; 95% CI 0.56-0.76). The mean event-free survival time for patients above and below this cutpoint was 248.8±13 vs. 290±13.7 days (log rank test with p=0.044). Using the COX proportional hazard model, age (p=0.004), NT-proBNP >1000 pg/mL (p=0.014) and the MAGGIC score (p=0.025) were independently associated with the primary outcome.

CONCLUSION

The MAGGIC risk score was an independent predictor of events, including heart failure hospitalization. The addition of biomarkers improved the accuracy of the score.

Prognostic value of natriuretic peptides in heart failure: systematic review and meta-analysis

Risk models, informing optimal long-term medical management, seldom use natriuretic peptides (NP) in ascertaining the absolute risk of outcomes for HF patients. Individual studies evaluating the prognostic value of NPs in HF patients have reported varying effects, arriving at best estimates requires a systematic review. We systematically summarized the best evidence regarding the prognostic value of brain natriuretic peptide (BNP) and NT-proBNP in predicting mortality and hospitalizations in ambulatory heart failure (HF) patients. We searched bibliographic databases from 2005 to 2018 and included studies evaluating the association of BNP or NT-proBNP with mortality or hospitalization using multivariable Cox proportional hazard models. We pooled hazard ratios using random-effect models, explored heterogeneity using pre-specified subgroup analyses, and evaluated the certainty of evidence using the Grading of Recommendations and Development Evaluation framework. We identified 67 eligible studies reporting on 76,178 ambulatory HF patients with a median BNP of 407 pg/mL (261-574 pg/mL). Moderate to high-quality evidence showed that a 100-pg/mL increase in BNP was associated with a 14% increased hazard of mortality (HR 1.14, 95% CI 1.06-1.22); a 1-log-unit increase was associated with a 51% increased hazard of mortality (HR 1.51, 95% CI 1.41-1.61) and 48% increased hazard of mortality or hospitalization (HR 1.48, 95% CI 1.29-1.69). With moderate to high certainty, we observed a 14% independent relative increase in mortality, translating to a clinically meaningful increase in absolute risk even for low-risk patients. The observed associations may help in developing more accurate risk models that incorporate NPs and accurately prognosticate HF patients.

Plasma Proteomic Profile Predicts Survival in Heart Failure With Reduced Ejection Fraction

BACKGROUND

It remains unclear whether the plasma proteome adds value to established predictors in heart failure (HF) with reduced ejection fraction (HFrEF). We sought to derive and validate a plasma proteomic risk score (PRS) for survival in patients with HFrEF (HFrEF-PRS).

METHODS

Patients meeting Framingham criteria for HF with EF<50% were enrolled (N=1017) and plasma underwent SOMAscan profiling (4453 targets). Patients were randomly divided 2:1 into derivation and validation cohorts. The HFrEF-PRS was derived using Cox regression of all-cause mortality adjusted for clinical score and NT-proBNP (N-terminal pro-B-type natriuretic peptide), then was tested in the validation cohort. Risk stratification improvement was evaluated by C statistic, integrated discrimination index, continuous net reclassification index, and median improvement in risk score for 1-year and 3-year mortality.

RESULTS

Participants' mean age was 68 years, 48% identified as Black, 35% were female, and 296 deaths occurred. In derivation (n=681), 128 proteins associated with mortality, 8 comprising the optimized HFrEF-PRS. In validation (n=336) the HFrEF-PRS associated with mortality (hazard ratio, 2.27 [95% CI, 1.84-2.82], P=6.3×10^-14), Kaplan-Meier curves differed significantly between HFrEF-PRS quartiles (P=2.2×10^-6), and it remained significant after adjustment for clinical score and NT-proBNP (hazard ratio, 1.37 [95% CI, 1.05-1.79], P=0.021). The HFrEF-PRS improved metrics of risk stratification (C statistic change, 0.009, P=0.612; integrated discrimination index, 0.041, P=0.010; net reclassification index=0.391, P=0.078; median improvement in risk score=0.039, P=0.016) and associated with cardiovascular death and HF phenotypes (eg, 6-minute walk distance, EF change). Most HFrEF-PRS proteins had little known connection to HFrEF.

CONCLUSIONS

A plasma multiprotein score improved risk stratification in patients with HFrEF and identified novel candidates.

Recurrent disease progression networks for modelling risk trajectory of heart failure

Motivation

Recurrent neural networks (RNN) are powerful frameworks to model medical time series records. Recent studies showed improved accuracy of predicting future medical events (e.g., readmission, mortality) by leveraging large amount of high-dimensional data. However, very few studies have explored the ability of RNN in predicting long-term trajectories of recurrent events, which is more informative than predicting one single event in directing medical intervention.

Methods

In this study, we focus on heart failure (HF) which is the leading cause of death among cardiovascular diseases. We present a novel RNN framework named Deep Heart-failure Trajectory Model (DHTM) for modelling the long-term trajectories of recurrent HF. DHTM auto-regressively predicts the future HF onsets of each patient and uses the predicted HF as input to predict the HF event at the next time point. Furthermore, we propose an augmented DHTM named DHTM+C (where “C” stands for co-morbidities), which jointly predicts both the HF and a set of acute co-morbidities diagnoses. To efficiently train the DHTM+C model, we devised a novel RNN architecture to model disease progression implicated in the co-morbidities.

Results

Our deep learning models confers higher prediction accuracy for both the next-step HF prediction and the HF trajectory prediction compared to the baseline non-neural network models and the baseline RNN model. Compared to DHTM, DHTM+C is able to output higher probability of HF for high-risk patients, even in cases where it is only given less than 2 years of data to predict over 5 years of trajectory. We illustrated multiple non-trivial real patient examples of complex HF trajectories, indicating a promising path for creating highly accurate and scalable longitudinal deep learning models for modeling the chronic disease.

MAGGIC Risk Model Predicts Adverse Events and Left Ventricular Remodeling in Non-Ischemic Dilated Cardiomyopathy

Purpose

We aimed to study the Meta-analysis Global Group in Chronic Heart Failure (MAGGIC) risk model’s prognostic value and relationship with left ventricular remodeling in dilated cardiomyopathy.

Patients and Methods

Dilated cardiomyopathy patients were prospectively recruited and underwent clinical assessments. MAGGIC risk score was calculated. Patients were followed up for adverse events and echocardiography. Primary endpoints were all-cause mortality and first rehospitalization due to heart failure. Secondary endpoint was left ventricular remodeling defined as a decline in left ventricular ejection fraction >10% or an increase in left ventricular end-diastolic diameter >10%. Survival status was examined using Cox regression analysis. The model’s ability to discriminate adverse events and left ventricular remodeling was calculated using a receiver operating characteristics curve.

Results

In total, 114 patients were included (median follow-up time = 31 months). The risk score was independently related to adverse events (2-year all-cause mortality: hazard ratio [HR] = 1.122; 95% confidence interval [CI], 1.043–1.208; 1-year first rehospitalization due to heart failure: HR = 1.094; 95% CI, 1.032–1.158; 2-year first rehospitalization due to heart failure: HR = 1.088; 95% CI, 1.033–1.147, all P < 0.05). One-year change in left ventricular end-diastolic diameter was correlated with the risk score (r = 0.305, P = 0.002). The model demonstrated modest ability in discriminating adverse events and left ventricular remodeling (all areas under the curve were 0.6–0.7).

Conclusion

The MAGGIC risk score was related to adverse events and left ventricular remodeling in dilated cardiomyopathy.

Suppression tumorigenicity 2 (ST2) turbidimetric immunoassay compared to enzyme-linked immunosorbent assay in predicting survival in heart failure patients with reduced ejection fraction

BACKGROUND

Suppressor of tumorigenicity 2 (ST2) is a powerful marker of prognosis and treatment response in heart failure (HF), however, it is an enzyme-linked immunosorbent assay (ELISA) which may be cumbersome and costly. A turbidimetric immunoassay (TIA) that can run on common chemistry analyzers could overcome this. We studied a novel TIA for ST2, comparing it to commercial ST2 (ELISA).

METHODS

Patients age ≥ 18 years meeting Framingham definition for HF were enrolled in a prospective registry (Oct 2007 - March 2015) at Henry Ford Hospital and donated blood samples. Participants with reduced ejection fraction (<50%) and available plasma samples were included and valid ST2 measurements were obtained on the same sample using both TIA and ELISA (N = 721). The primary endpoint was all cause death. Correlation between the methods was quantified. The association with survival was tested using unadjusted and adjusted (for MAGGIC score and NTproBNP) Cox models and comparing the Area Under the Curve (AUC).

RESULTS

The inter-assay Spearman correlation coefficient was 0.77. Nonparametric regression showed no significant proportional difference (slope = 0.97) and a very small systematic difference (3.2 ng/mL). In univariate analyses, both TIA and ELISA ST2 were significant associates of survival with similar effect sizes (HR 4.46 and 3.50, respectively, both p < 0.001). In models adjusted for MAGGIC score, both ST2 remained significant in Cox models and incrementally improved AUC vs. MAGGIC alone (MAGGIC AUC = 0.757; TIA + MAGGIC AUC = 0.786, p = 0.025; ELISA + MAGGIC AUC = 0.793, p = 0.033). In models with both MAGGIC and NTproBNP included, both ST2 still remained significant but did not improve AUC.

CONCLUSIONS

A novel TIA method for ST2 quantification correlates highly with ELISA and offers similarly powerful risk-stratification.