Risk prediction models for mortality and readmission in patients with acute heart failure: A protocol for systematic review, critical appraisal, and meta-analysis

INTRODUCTION

A considerable number of risk models, which predict outcomes in mortality and readmission rates, have been developed for patients with acute heart failure (AHF) to help stratify patients by risk level, improve decision making, and save medical resources. However, some models exist in a clinically useful manner such as risk scores or online calculators, while others are not, providing only limited information that prevents clinicians and patients from using them. The reported performance of some models varied greatly when predicting at multiple time points and being validated in different cohorts, which causes model users uncertainty about the predictive accuracy of these models. The foregoing leads to users facing difficulties in the selection of prediction models, and even sometimes being reluctant to utilize models. Therefore, a systematic review to assess the performance at multiple time points, applicability, and clinical impact of extant prediction models for mortality and readmission in AHF patients is essential. It may facilitate the selection of models for clinical implementation.

METHOD AND ANALYSIS

Four databases will be searched from their inception onwards. Multivariable prognostic models for mortality and/or readmission in AHF patients will be eligible for review. Characteristics and the clinical impact of included models will be summarized qualitatively and quantitatively, and models with clinical utility will be compared with those without. Predictive performance measures of included models with an analogous clinical outcome appraised repeatedly, will be compared and synthesized by a meta-analysis. Meta-analysis of validation studies for a common prediction model at the same time point will also be performed. We will also provide an overview of critical appraisal of the risk of bias, applicability, and reporting transparency of included studies using the PROBAST tool and TRIPOD statement.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO registration number CRD42021256416.

The C-reactive protein to prealbumin ratio on admission and its relationship with outcome in patients hospitalized for acute heart failure

BACKGROUND

Inflammation and malnutrition are common problems in patients who are hospitalized for acute heart failure (AHF). C-reactive protein (CRP) is an acute-phase reactant and nonspecific marker for evaluating systemic inflammation. There has been growing interest in prealbumin for nutritional assessment. Additionally, prealbumin is a negative acute-phase protein because its synthesis is suppressed in the inflammatory setting in which cytokines stimulate hepatic production of acute-phase proteins (e.g. CRP). Therefore, the CRP to prealbumin ratio (CP ratio) may be a comprehensive marker of inflammation and malnutrition. We evaluated the relationship of the CP ratio with mortality in patients with AHF.

METHODS

We analyzed 257 hospitalized patients with AHF who had CRP and prealbumin levels examined on admission.

RESULTS

The median CP ratio on admission was 0.57, with an interquartile range of 0.11 to 1.94. In receiver operating characteristic curve analysis, the area under the curve was 0.729 and the optimal cut-off point of the CP ratio for all-cause death was >1.60 (sensitivity: 67.5%; specificity: 77.6%; p = 0.003). Kaplan-Meier survival curves showed that patients with a high CP ratio (>1.60) had a significantly greater risk of all-cause, cardiac, and non-cardiac death (log-rank test, all p<0.001) than patients with a low CP ratio (≤1.60). Multivariable analysis adjusted for imbalanced baseline variables showed that a high CP ratio was independently associated with higher all-cause mortality (adjusted hazard ratio 3.88; 95% confidence interval 1.91-7.86; p<0.001).

CONCLUSIONS

The ratio of two hepatic proteins, CRP and prealbumin, may be useful in risk stratification of patients with AHF.

Risk Stratification Towards Precision Medicine in Heart Failure - Current Progress and Future Perspectives

Clinical risk stratification is a key strategy used to identify low- and high-risk subjects to optimize the management, ranging from pharmacological treatment to palliative care, of patients with heart failure (HF). Using statistical modeling techniques, many HF risk prediction models that combine predictors to assess the risk of specific endpoints, including death or worsening HF, have been developed. However, most risk prediction models have not been well-integrated into the clinical setting because of their inadequacy and diverse predictive performance. To improve the performance of such models, several factors, including optimal sampling and biomarkers, need to be considered when deriving the models; however, given the large heterogeneity of HF, the currently advocated one-size-fits-all approach is not appropriate for every patient. Recent advances in techniques to analyze biological "omics" information could allow for the development of a personalized medicine platform, and there is growing awareness that an integrated approach based on the concept of system biology may be an excessively naïve view of the multiple contributors and complexity of an individual's HF phenotype. This review article describes the progress in risk stratification strategies and perspectives of emerging precision medicine in the field of HF management.

Importance of the Corrected Calcium Level in Patients With Acute Heart Failure Requiring Intensive Care

Background: Serum calcium (Ca) concentrations in the acute phase of acute heart failure (AHF) have not been not sufficiently investigated. Methods and Results: This study enrolled 1,291 AHF patients and divided them into 3 groups based on original and corrected Ca concentrations: (1) hypocalcemia (both original and corrected Ca ≤8.7 mg/dL; n=651); (2) pseudo-hypocalcemia (original and corrected Ca ≤8.7 and >8.7 mg/dL, respectively; n=300); and (3) normal/hypercalcemia (both original and corrected Ca >8.7 mg/dL; n=340). AHF patients were also divided into 2 groups based on corrected Ca concentrations: (1) corrected hypocalcemia (corrected Ca ≤8.7 mg/dL; n=651); and (2) corrected normal/hypercalcemia (corrected Ca >8.7 mg/dL; n=640). Of the 951 patients with original hypocalcemia (≤8.7 mg/dL), 300 (31.5%) were classified as corrected normal/hypercalcemia after correction of Ca concentrations by serum albumin. The prognoses in the pseudo-hypocalcemia, low albumin, and corrected normal/hypercalcemia groups, including all-cause death within 730 days, were significantly poorer than in the other groups. Multivariate Cox regression analysis showed that classification into the pseudo-hypocalcemia, hypoalbumin, and corrected normal/hypercalcemia groups independently predicted 730-day all-cause death (hazard ratios [95% confidence intervals] of 1.497 [1.153-1.943], 2.392 [1.664-3.437], and 1.294 [1.009-1.659], respectively). Conclusions: Corrected normal/hypercalcemia was an independent predictor of prognosis because this group included patients with pseudo-hypocalcemia, which was affected by the serum albumin concentration.

Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis

AIMS

Non-linear models by machine learning may identify different risk factors with different weighting in comparison to conventional linear models.

METHODS AND RESULTS

The analyses were performed in 15,933 patients included in the Shinken Database (SD) 2004-2014 (n = 22,022) for whom baseline data of blood sampling and ultrasound cardiogram and follow-up data at 2 years were available. Using non-linear models with machine learning software, 118 risk factors and their weighting of risk for all-cause mortality, heart failure (HF), acute coronary syndrome (ACS), ischemic stroke (IS), and intracranial hemorrhage (ICH) were identified, where the top two risk factors were albumin/hemoglobin, left ventricular ejection fraction/history of HF, history of ACS/anti-platelet use, history of IS/deceleration time, and history of ICH/warfarin use. The areas under the curve of the developed models for each event were 0.900, 0.912, 0.879, 0.758, and 0.753, respectively.

CONCLUSION

Here, we described our experience with the development of models for predicting cardiovascular prognosis by machine learning. Machine learning could identify risk predicting models with good predictive capability and good discrimination of the risk impact.