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.
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.
Authors: Peter A McCullough; Edward F Philbin; John A Spertus; Scott Kaatz; Keisha R Sandberg; W Douglas Weaver Journal: J Am Coll Cardiol Date: 2002-01-02 Impact factor: 24.094
Authors: Wayne C Levy; Dariush Mozaffarian; David T Linker; Santosh C Sutradhar; Stefan D Anker; Anne B Cropp; Inder Anand; Aldo Maggioni; Paul Burton; Mark D Sullivan; Bertram Pitt; Philip A Poole-Wilson; Douglas L Mann; Milton Packer Journal: Circulation Date: 2006-03-13 Impact factor: 29.690
Authors: Véronique L Roger; Susan A Weston; Margaret M Redfield; Jens P Hellermann-Homan; Jill Killian; Barbara P Yawn; Steven J Jacobsen Journal: JAMA Date: 2004-07-21 Impact factor: 56.272
Authors: J N Cohn; S O Goldstein; B H Greenberg; B H Lorell; R C Bourge; B E Jaski; S O Gottlieb; F McGrew; D L DeMets; B G White Journal: N Engl J Med Date: 1998-12-17 Impact factor: 91.245
Authors: Bobak J Mortazavi; Nicholas S Downing; Emily M Bucholz; Kumar Dharmarajan; Ajay Manhapra; Shu-Xia Li; Sahand N Negahban; Harlan M Krumholz Journal: Circ Cardiovasc Qual Outcomes Date: 2016-11-08
Authors: Jenica N Upshaw; Marvin A Konstam; David van Klaveren; Farzad Noubary; Gordon S Huggins; David M Kent Journal: Circ Heart Fail Date: 2016-08 Impact factor: 8.790
Authors: Mark W Smith; Pamela L Owens; Roxanne M Andrews; Claudia A Steiner; Rosanna M Coffey; Halcyon G Skinner; Jill Miyamura; Ioana Popescu Journal: BMC Health Serv Res Date: 2016-04-18 Impact factor: 2.655
Authors: Ju Hee Lee; Min Seok Kim; Byung Su Yoo; Sung Ji Park; Jin Joo Park; Mi Seung Shin; Jong Chan Youn; Sang Eun Lee; Se Yong Jang; Seonghoon Choi; Hyun Jai Cho; Seok Min Kang; Dong Ju Choi Journal: Korean Circ J Date: 2019-01 Impact factor: 3.243
Authors: Gaurav Gulati; Jenica Upshaw; Benjamin S Wessler; Riley J Brazil; Jason Nelson; David van Klaveren; Christine M Lundquist; Jinny G Park; Hannah McGinnes; Ewout W Steyerberg; Ben Van Calster; David M Kent Journal: Circ Cardiovasc Qual Outcomes Date: 2022-03-31