An ensemble model using serial cytokine measurements significantly improved 1-year mortality prediction in heart failure compared to baseline data alone (C-statistic 0.84 vs 0.74; P=0.04).
Cohort (n=963)
Do predictive models incorporating time-series measurements of cytokines improve 1-year mortality prediction in heart failure patients compared to baseline clinical models?
Incorporating serial measurements of biomarkers like cytokines into ensemble models significantly improves the accuracy of 1-year mortality prediction in patients with chronic heart failure.
Effect estimate: C-statistic 0.84
Absolute Event Rate: 0.84% vs 0.74%
p-value: p=0.04
BACKGROUND: Morbidity and mortality rates associated with heart failure remain high. A wide variety of demographic and clinical factors as well as biomarkers are associated with increased mortality rates. Despite this, most multivariate predictive models for heart failure mortality have predictive accuracies characterized by a C-statistic (area under the receiver operating curve) of ≈0.74. METHODS AND RESULTS: We analyzed data on 963 patients enrolled in the Vesnarinone Evaluation of Survival Trial (VEST), including circulating levels of 2 cytokines (tumor necrosis factor and interleukin-6) and their receptors sampled at baseline and at 8, 16, and 24 weeks. We built multivariate logistic regression models by using standard clinical variables and time-series of cytokine and cytokine receptor levels, using independent components analysis to handle collinearity among cytokine measurements, and L2-penalized stepwise regression for variable selection. We also built ensemble models with these data, using gentle boosting. Our multivariate logistic regression model using time-series cytokine measurements predicts 1-year mortality rates significantly better (P=0.001) than the baseline model, with a C-statistic of 0.81±0.03. Without the cytokines, the baseline model has a C-statistic of 0.73±0.03, and, with only baseline cytokine and cytokine receptor levels added, the model has a C-statistic of 0.74±0.04. An ensemble model of 100 decision stumps with serial cytokine measurements has a significantly better (P=0.04) C-statistic of 0.84±0.02. An ensemble model with baseline cytokine data and without the serial measurements has a C-statistic of 0.74±0.04. CONCLUSIONS: Significant gains in accuracy of one year mortality prediction in chronic heart failure can be obtained by using logistic regression models that incorporate serial measurements of biomarkers such as cytokine and cytokine receptor levels. Ensemble models capture inherent variability in large patient populations, and boost predictive accuracy through the use of time-series measurements.
Subramanian et al. (Thu,) conducted a cohort in chronic heart failure (n=963). Serial measurements of cytokines and their receptors vs. Baseline clinical variables and baseline cytokine levels was evaluated on 1-year mortality prediction accuracy (C-statistic) (C-statistic 0.84, p=0.04). An ensemble model using serial cytokine measurements significantly improved 1-year mortality prediction in heart failure compared to baseline data alone (C-statistic 0.84 vs 0.74; P=0.04).