Mortality Risk Prediction Dynamics After Heart Failure Treatment Optimization: Repeat Risk Assessment Using Online Risk Calculators.

Objectives: Heart failure (HF) management has significantly improved over the past two decades, leading to better survival. This study aimed to assess changes in predicted mortality risk after 12 months of management in a multidisciplinary HF clinic. Materials and Methods: Out of 1,032 consecutive HF outpatients admitted from March-2012 to November-2018, 357 completed the 12-months follow-up and had N-terminal pro-B-type natriuretic peptide (NTproBNP), high sensitivity troponin T (hs-TnT), and interleukin-1 receptor-like-1 (known as ST2) measurements available both at baseline and follow-up. Three contemporary risk scores were used: MAGGIC-HF, Seattle HF Model (SHFM), and the Barcelona Bio-HF (BCN Bio-HF) calculator, which incorporates the three above mentioned biomarkers. The predicted risk of all-cause death at 1 and 3 years was calculated at baseline and re-evaluated after 12 months. Results: A significant decline in predicted 1-and 3-year mortality risk was observed at 12 months: MAGGIC ~16%, SHFM ~22% and BCN Bio-HF ~15%. In the HF with reduced ejection fraction (HFrEF) subgroup guideline-directed medical therapy led to a complete normalization of left ventricular ejection fraction (≥50%) in almost a third of the patients and to a partial normalization (41-49%) in 30% of them. Repeated risk assessment after 12 months with SHFM and BCN Bio-HF provided adequate discrimination for all-cause 3-year mortality (C-Index: MAGGIC-HF 0.762, SHFM 0.781 and BCN Bio-HF 0.791). Conclusion: Mortality risk declines in patients with HF managed for 12 months in a multidisciplinary HF clinic. Repeating the mortality risk assessment after optimizing the HF treatment is recommended, particularly in the HFrEF subgroup.

Head-to-head comparison of contemporary heart failure risk scores.

AIMS: Several heart failure (HF) web-based risk scores are currently used in clinical practice. Currently, we lack head-to-head comparison of the accuracy of risk scores. This study aimed to assess correlation and mortality prediction performance of Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC-HF) risk score, which includes clinical variables + medications; Seattle Heart Failure Model (SHFM), which includes clinical variables + treatments + analytes; PARADIGM Risk of Events and Death in the Contemporary Treatment of Heart Failure (PREDICT-HF) and Barcelona Bio-Heart Failure (BCN-Bio-HF) risk calculator, which also include biomarkers, like N-terminal pro B-type natriuretic peptide (NT-proBNP). METHODS AND RESULTS: A total of 1166 consecutive patients with HF from different aetiologies that had NT-proBNP measurement at first visit were included. Discrimination for all-cause mortality was compared by Harrell's C-statistic from 1 to 5 years, when possible. Calibration was assessed by calibration plots and Hosmer-Lemeshow test and global performance by Nagelkerke's R2 . Correlation between scores was assessed by Spearman rank test. Correlation between the scores was relatively poor (rho value from 0.66 to 0.79). Discrimination analyses showed better results for 1-year mortality than for longer follow-up (SHFM 0.817, MAGGIC-HF 0.801, PREDICT-HF 0.799, BCN-Bio-HF 0.830). MAGGIC-HF showed the best calibration, BCN-Bio-HF overestimated risk while SHFM and PREDICT-HF underestimated it. BCN-Bio-HF provided the best discrimination and overall performance at every time-point. CONCLUSIONS: None of the contemporary risk scores examined showed a clear superiority over the rest. BCN-Bio-HF calculator provided the best discrimination and overall performance with overestimation of risk. MAGGIC-HF showed the best calibration, and SHFM and PREDICT-HF tended to underestimate risk. Regular updating and recalibration of online web calculators seems necessary to improve their accuracy as HF management evolves at unprecedented pace.

Weighted contrastive divergence.

Learning algorithms for energy based Boltzmann architectures that rely on gradient descent are in general computationally prohibitive, typically due to the exponential number of terms involved in computing the partition function. In this way one has to resort to approximation schemes for the evaluation of the gradient. This is the case of Restricted Boltzmann Machines (RBM) and its learning algorithm Contrastive Divergence (CD). It is well-known that CD has a number of shortcomings, and its approximation to the gradient has several drawbacks. Overcoming these defects has been the basis of much research and new algorithms have been devised, such as persistent CD. In this manuscript we propose a new algorithm that we call Weighted CD (WCD), built from small modifications of the negative phase in standard CD. However small these modifications may be, experimental work reported in this paper suggests that WCD provides a significant improvement over standard CD and persistent CD at a small additional computational cost.