| 1. |
- Adler, Eric D., et al.
(författare)
-
Improving risk prediction in heart failure using machine learning
- 2020
-
Ingår i: European Journal of Heart Failure. - : Wiley. - 1388-9842 .- 1879-0844. ; 22:1, s. 139-147
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Predicting mortality is important in patients with heart failure (HF). However, current strategies for predicting risk are only modestly successful, likely because they are derived from statistical analysis methods that fail to capture prognostic information in large data sets containing multi-dimensional interactions. Methods and results: We used a machine learning algorithm to capture correlations between patient characteristics and mortality. A model was built by training a boosted decision tree algorithm to relate a subset of the patient data with a very high or very low mortality risk in a cohort of 5822 hospitalized and ambulatory patients with HF. From this model we derived a risk score that accurately discriminated between low and high-risk of death by identifying eight variables (diastolic blood pressure, creatinine, blood urea nitrogen, haemoglobin, white blood cell count, platelets, albumin, and red blood cell distribution width). This risk score had an area under the curve (AUC) of 0.88 and was predictive across the full spectrum of risk. External validation in two separate HF populations gave AUCs of 0.84 and 0.81, which were superior to those obtained with two available risk scores in these same populations. Conclusions: Using machine learning and readily available variables, we generated and validated a mortality risk score in patients with HF that was more accurate than other risk scores to which it was compared. These results support the use of this machine learning approach for the evaluation of patients with HF and in other settings where predicting risk has been challenging.
|
|
| 2. |
- Armstrong, Paul W, et al.
(författare)
-
Vericiguat in Patients with Heart Failure and Reduced Ejection Fraction.
- 2020
-
Ingår i: New England Journal of Medicine. - 0028-4793 .- 1533-4406. ; 382:20, s. 1883-1893
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: The effect of vericiguat, a novel oral soluble guanylate cyclase stimulator, in patients with heart failure and reduced ejection fraction who had recently been hospitalized or had received intravenous diuretic therapy is unclear.METHODS: In this phase 3, randomized, double-blind, placebo-controlled trial, we assigned 5050 patients with chronic heart failure (New York Heart Association class II, III, or IV) and an ejection fraction of less than 45% to receive vericiguat (target dose, 10 mg once daily) or placebo, in addition to guideline-based medical therapy. The primary outcome was a composite of death from cardiovascular causes or first hospitalization for heart failure.RESULTS: Over a median of 10.8 months, a primary-outcome event occurred in 897 of 2526 patients (35.5%) in the vericiguat group and in 972 of 2524 patients (38.5%) in the placebo group (hazard ratio, 0.90; 95% confidence interval [CI], 0.82 to 0.98; P = 0.02). A total of 691 patients (27.4%) in the vericiguat group and 747 patients (29.6%) in the placebo group were hospitalized for heart failure (hazard ratio, 0.90; 95% CI, 0.81 to 1.00). Death from cardiovascular causes occurred in 414 patients (16.4%) in the vericiguat group and in 441 patients (17.5%) in the placebo group (hazard ratio, 0.93; 95% CI, 0.81 to 1.06). The composite of death from any cause or hospitalization for heart failure occurred in 957 patients (37.9%) in the vericiguat group and in 1032 patients (40.9%) in the placebo group (hazard ratio, 0.90; 95% CI, 0.83 to 0.98; P = 0.02). Symptomatic hypotension occurred in 9.1% of the patients in the vericiguat group and in 7.9% of the patients in the placebo group (P = 0.12), and syncope occurred in 4.0% of the patients in the vericiguat group and in 3.5% of the patients in the placebo group (P = 0.30).CONCLUSIONS: Among patients with high-risk heart failure, the incidence of death from cardiovascular causes or hospitalization for heart failure was lower among those who received vericiguat than among those who received placebo. (Funded by Merck Sharp & Dohme [a subsidiary of Merck] and Bayer; VICTORIA ClinicalTrials.gov number, NCT02861534.).
|
|
| 3. |
- Belonje, Anne M S, et al.
(författare)
-
Endogenous erythropoietin and outcome in heart failure.
- 2010
-
Ingår i: Circulation. - 0009-7322 .- 1524-4539. ; 121:2, s. 245-51
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Endogenous erythropoietin is increased in patients with heart failure (HF). Previous small-scale data suggest that these erythropoietin levels are related to prognosis. This study aims to analyze the clinical and prognostic value of erythropoietin levels in relation to hemoglobin in a large cohort of HF patients. METHODS AND RESULTS: In patients hospitalized for HF, endogenous erythropoietin levels were measured at discharge and after 6 months. In anemic patients, the relation between erythropoietin and hemoglobin levels was determined by calculating the observed/predicted ratio of erythropoietin levels. We studied data from 605 patients with HF. Mean age was 71+/-11 years; 62% were male; and mean left ventricular ejection fraction was 0.33+/-0.14. Median erythropoietin levels were 9.6 U/L at baseline and 10.5 U/L at 6 months. Higher erythropoietin levels at baseline were independently related to an increased mortality at 18 months (hazard ratio, 2.06; 95% confidence interval, 1.40 to 3.04; P<0.01). In addition, persistently elevated erythropoietin levels (higher than median at baseline and at 6 months) were related to an increased mortality risk (hazard ratio, 2.24; 95% confidence interval, 1.02 to 4.90; P=0.044). The observed/predicted ratio was determined in a subset of anemic patients, 79% of whom had erythropoietin levels lower than expected and 9% had levels higher than expected on the basis of their hemoglobin. Multivariate Cox regression analysis revealed that a higher observed/predicted ratio was related to an increased mortality risk (hazard ratio, 3.52; 95% confidence interval, 1.53 to 8.12; P=0.003). CONCLUSIONS: Erythropoietin levels predict mortality in HF patients, and persistently elevated levels have an independent prognostic value. In anemic HF patients, the majority had a low observed/predicted ratio. However, a higher observed/predicted ratio may be related to an independent increased mortality risk.
|
|
| 4. |
- Chen, Yuntao, et al.
(författare)
-
A heart failure phenotype stratified model for predicting 1-year mortality in patients admitted with acute heart failure: results from an individual participant data meta-analysis of four prospective European cohorts
- 2021
-
Ingår i: BMC Medicine. - : BMC. - 1741-7015. ; 19:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background Prognostic models developed in general cohorts with a mixture of heart failure (HF) phenotypes, though more widely applicable, are also likely to yield larger prediction errors in settings where the HF phenotypes have substantially different baseline mortality rates or different predictor-outcome associations. This study sought to use individual participant data meta-analysis to develop an HF phenotype stratified model for predicting 1-year mortality in patients admitted with acute HF. Methods Four prospective European cohorts were used to develop an HF phenotype stratified model. Cox model with two rounds of backward elimination was used to derive the prognostic index. Weibull model was used to obtain the baseline hazard functions. The internal-external cross-validation (IECV) approach was used to evaluate the generalizability of the developed model in terms of discrimination and calibration. Results 3577 acute HF patients were included, of which 2368 were classified as having HF with reduced ejection fraction (EF) (HFrEF; EF < 40%), 588 as having HF with midrange EF (HFmrEF; EF 40-49%), and 621 as having HF with preserved EF (HFpEF; EF >= 50%). A total of 11 readily available variables built up the prognostic index. For four of these predictor variables, namely systolic blood pressure, serum creatinine, myocardial infarction, and diabetes, the effect differed across the three HF phenotypes. With a weighted IECV-adjusted AUC of 0.79 (0.74-0.83) for HFrEF, 0.74 (0.70-0.79) for HFmrEF, and 0.74 (0.71-0.77) for HFpEF, the model showed excellent discrimination. Moreover, there was a good agreement between the average observed and predicted 1-year mortality risks, especially after recalibration of the baseline mortality risks. Conclusions Our HF phenotype stratified model showed excellent generalizability across four European cohorts and may provide a useful tool in HF phenotype-specific clinical decision-making.
|
|
| 5. |
- Damman, Kevin, et al.
(författare)
-
Both in- and out-hospital worsening of renal function predict outcome in patients with heart failure : results from the Coordinating Study Evaluating Outcome of Advising and Counseling in Heart Failure (COACH).
- 2009
-
Ingår i: European Journal of Heart Failure. - : Wiley. - 1388-9842 .- 1879-0844. ; 11:9, s. 847-54
-
Tidskriftsartikel (refereegranskat)abstract
- AIMS: The effect of worsening renal function (WRF) after discharge on outcome in patients with heart failure is unknown. METHODS AND RESULTS: We assessed estimated glomerular filtration rate (eGFR) and serum creatinine at admission, discharge, and 6 and 12 months after discharge, in 1023 heart failure patients. Worsening renal function was defined as an increase in serum creatinine of >26.5 micromol/L and >25%. The primary endpoint was a composite of all-cause mortality and heart failure admissions. The mean age of patients was 71 +/- 11 years, and 62% was male. Mean eGFR at admission was 55 +/- 21 mL/min/1.73 m(2). In-hospital WRF occurred in 11% of patients, while 16 and 9% experienced WRF from 0 to 6, and 6 to 12 months after discharge, respectively. In multivariate landmark analysis, WRF at any point in time was associated with a higher incidence of the primary endpoint: hazard ratio (HR) 1.63 (1.10-2.40), P = 0.014 for in-hospital WRF, HR 2.06 (1.13-3.74), P = 0.018 for WRF between 0-6 months, and HR 5.03 (2.13-11.88), P < 0.001 for WRF between 6-12 months. CONCLUSION: Both in- and out-hospital worsening of renal function are independently related to poor prognosis in patients with heart failure, suggesting that renal function in heart failure patients should be monitored long after discharge.
|
|
| 6. |
- de Boer, Rudolf A, et al.
(författare)
-
Predictive value of plasma galectin-3 levels in heart failure with reduced and preserved ejection fraction
- 2011
-
Ingår i: Annals of Medicine. - : Informa UK Limited. - 0785-3890 .- 1365-2060. ; 43:1, s. 60-68
-
Tidskriftsartikel (refereegranskat)abstract
- AIMS: galectin-3 is an emerging biomarker which has been studied in relatively small heart failure (HF) cohorts with predominantly systolic HF. We studied the prognostic value of base-line galectin-3 in a large HF cohort, with preserved and reduced left ventricular ejection fraction (LVEF), and compared this to other biomarkers. METHODS: we studied 592 HF patients who had been hospitalized for HF and were followed for 18 months. The primary end-point was a composite of all-cause mortality and HF hospitalization. RESULTS: a doubling of galectin-3 levels was associated with a hazard ratio (HR) of 1.97 (1.62-2.42) for the primary outcome (P < 0.001). After correction for age, gender, BNP, eGFR, and diabetes the HR was 1.38 (1.07-1.78; P = 0.015). Galectin-3 levels were correlated with higher IL-6 and CRP levels (P < 0.002). Changes of galectin-3 levels after 6 months did not add prognostic information to the base-line value (n = 291); however, combining plasma galectin-3 and BNP levels increased prognostic value over either biomarker alone (ROC analysis, P < 0.05). The predictive value of galectin-3 was stronger in patients with preserved LVEF (n = 114) compared to patients with reduced LVEF (P < 0.001). CONCLUSIONS: galectin-3 is an independent marker for outcome in HF and appears to be particularly useful in HF patients with preserved LVEF.
|
|
| 7. |
- de Boer, Rudolf A, et al.
(författare)
-
The WAP four-disulfide core domain protein HE4 : a novel biomarker for heart failure.
- 2013
-
Ingår i: JACC. Heart failure. - : Elsevier BV. - 2213-1787 .- 2213-1779. ; 1:2, s. 164-169
-
Tidskriftsartikel (refereegranskat)abstract
- OBJECTIVES: This study investigated clinical determinants and added prognostic value of HE4 as a biomarker not previously described in heart failure (HF).BACKGROUND: Identification of plasma biomarkers that help to risk stratify HF patients may help to improve treatment.METHODS: Plasma HE4 levels were determined in 567 participants of the COACH (Coordinating study evaluating outcomes of Advising and Counseling in Heart failure). Patients had been hospitalized for HF and were followed for 18 months. The primary endpoint of this study was a composite of all-cause mortality and HF hospitalization.RESULTS: HE4 showed a strong correlation with HF severity, according to New York Heart Association functional class and brain natriuretic peptide (BNP) levels (p < 0.001). HE4 also showed a positive correlation with GDF15 (p < 0.001) and, in addition, correlated with kidney function (estimated glomerular filtration rate [eGFR]; p < 0.001). Cox regression analysis revealed that a doubling of HE4 levels was associated with a hazard ratio (HR) of 1.73 (95% confidence interval [CI]: 1.53 to 1.95) for the primary outcome (p < 0.001). After correction for age, gender, BNP, and eGFR, the HR was 1.46 (95% CI: 1.23 to 1.72; p < 0.001), and after additional adjustment for GDF15, the HR lowered to 1.30 (95% CI: 1.07 to 1.59; p = 0.009). The area under the curve in the receiver-operating characteristic curve analysis increased from 0.727 to 0.752 when HE4 was included in the clinical evaluation (p = 0.051). The integrated discrimination improvement and net reclassification index for reclassification showed significant improvements when HE4 was added to the clinical model, and this remained significant after BNP inclusion in the model.CONCLUSIONS: HE4 plasma levels are correlated with markers of HF severity, show prognostic value, and can improve risk assessment in HF.
|
|
| 8. |
- Hogenhuis, Jochem, et al.
(författare)
-
Anaemia and renal dysfunction are independently associated with BNP and NT-proBNP levels in patients with heart failure.
- 2007
-
Ingår i: European Journal of Heart Failure. - : Wiley. - 1388-9842 .- 1879-0844. ; 9:8, s. 787-94
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Anaemia may affect B-type natriuretic peptide (BNP) and N-terminal proBNP (NT-proBNP) levels, but this has not been well described in heart failure (HF) patients without the exclusion of patients with renal dysfunction. AIMS: To study the influence of both anaemia and renal function on BNP and NT-proBNP levels in a large group of hospitalised HF patients. METHODS AND RESULTS: We studied 541 patients hospitalised for HF (mean age 71+/-11 years, 62% male, and left ventricular ejection fraction 0.33+/-0.14). Of these patients, 30% (n=159) were anaemic (women: Hb<7.5 mmol/l, men: Hb<8.1 mmol/l). Of the 159 anaemic patients, 73% had renal dysfunction (eGFR<60 ml/min/1.73 m2) and of the non-anaemic patients, 57% had renal dysfunction. BNP and NT-proBNP levels were measured in all patients before discharge. In multivariable analyses both plasma haemoglobin and eGFR were independently related to the levels of BNP and NT-proBNP (standardised beta's of -0.16, -0.14 [BNP] and -0.19, -0.26 [NT-proBNP] respectively, P-values<0.01). CONCLUSION: Anaemia and renal dysfunction are related to increased BNP and NT-proBNP levels, independent of the severity of HF. These results indicate that both anaemia and renal dysfunction should be taken into consideration during the interpretation of BNP and NT-proBNP levels in HF patients.
|
|
| 9. |
- Hogenhuis, Jochem, et al.
(författare)
-
BNP and functional status in heart failure.
- 2004
-
Ingår i: Cardiovascular Drugs and Therapy. - : Springer Science and Business Media LLC. - 0920-3206 .- 1573-7241. ; 18:6, s. 507; author reply 509-
-
Tidskriftsartikel (refereegranskat)
|
|
| 10. |
- Hogenhuis, Jochem, et al.
(författare)
-
Correlates of B-type natriuretic peptide and 6-min walk in heart failure patients.
- 2006
-
Ingår i: International Journal of Cardiology. - : Elsevier BV. - 0167-5273 .- 1874-1754. ; 108:1, s. 63-7
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: B-type natriuretic peptide (BNP) and 6-min walk test (6MWT) are both related to the severity and prognosis in chronic heart failure (CHF), but may reflect different aspects of CHF. We related BNP and 6MWT to left ventricular ejection fraction (LVEF), New York Heart Association functional class (NYHA), and two indices of quality of life (physical subscales): the Minnesota Living with Heart Failure Questionnaire (MLwHFQph) and the RAND-36ph. METHODS: Plasma BNP and 6MWT were measured at discharge in 229 patients who had been admitted for CHF. LVEF and NYHA were determined, and patients completed the MLwHFQ and RAND-36 questionnaires. RESULTS: BNP was weakly correlated to LVEF (r=-0.29, P<0.01) and NYHA (r=0.20, P<0.01), but not to MLwHFQph and RAND-36ph. On the other hand, 6MWT is related to MLwHFQph (r=-0.23, P<0.01), RAND-36ph (r=0.52, P<0.01), and NYHA (r=-0.46, P<0.01), but not to LVEF (r=-0.15, P=0.05). There is also no correlation between BNP and 6MWT (r=-0.01, P=0.87). CONCLUSIONS: The present data show that BNP and 6MWT represent different aspects of the clinical syndrome of CHF. The outcomes of this study suggest that BNP plasma levels are more related to cardiac function, while 6MWT reflects functional capacity and quality of life.
|
|
