Sebastian Weichwald1,2, Alessandro Candreva3, Rebekka Burkholz1, Roland Klingenberg3,4,5,6, Lorenz Räber7, Dik Heg8, Robert Manka3, Baris Gencer9, François Mach9, David Nanchen10, Nicolas Rodondi11,12, Stephan Windecker7, Reijo Laaksonen13,14, Stanley L Hazen15,16, Arnold von Eckardstein17, Frank Ruschitzka3, Thomas F Lüscher18,19, Joachim M Buhmann1, Christian M Matter3,18. 1. Department of Computer Science, Institute for Machine Learning, ETH Zurich, Switzerland. 2. Max Planck Institute for Intelligent Systems, Tübingen, Germany. 3. Department of Cardiology, University Heart Center, University Hospital of Zurich, Switzerland. 4. Kerckhoff Heart and Thorax Center, Department of Cardiology, Kerckhoff-Klinik, Bad Nauheim, Germany. 5. Campus of the Justus Liebig University of Giessen, Germany. 6. DZHK (German Center for Cardiovascular Research), Partner Site Rhine-Main, Bad Nauheim, Germany. 7. Department of Cardiology, Cardiovascular Center, University Hospital of Bern, Switzerland. 8. Clinical Trial Unit, University of Bern, Switzerland. 9. Department of Cardiology, Cardiovascular Center, University Hospital of Geneva, Switzerland. 10. Department of Ambulatory Care and Community Medicine, University of Lausanne, Switzerland. 11. Institute of Primary Health Care (BIHAM), University of Bern, Switzerland. 12. Department of General Internal Medicine, Inselspital, Bern University Hospital, University of Bern, Switzerland. 13. Zora Biosciences, Espoo, Finland. 14. Finnish Cardiovascular Research Center Tampere, Tampere University, Tampere, Finland. 15. Department of Cardiovascular and Metabolic Sciences, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA. 16. Department of Cardiovascular Medicine, Heart and Vascular Institute, Cleveland Clinic, Cleveland, OH, USA. 17. Institute for Clinical Chemistry, University Hospital Zurich, Zurich, Switzerland. 18. Center for Molecular Cardiology, University of Zurich, Switzerland. 19. Cardiology, Royal Brompton & Harefield Hospitals, London, United Kingdom.
Abstract
BACKGROUND: The Global Registry of Acute Coronary Events (GRACE) score is an established clinical risk stratification tool for patients with acute coronary syndromes (ACS). We developed and internally validated a model for 1-year all-cause mortality prediction in ACS patients. METHODS: Between 2009 and 2012, 2'168 ACS patients were enrolled into the Swiss SPUM-ACS Cohort. Biomarkers were determined in 1'892 patients and follow-up was achieved in 95.8% of patients. 1-year all-cause mortality was 4.3% (n = 80). In our analysis we consider all linear models using combinations of 8 out of 56 variables to predict 1-year all-cause mortality and to derive a variable ranking. RESULTS: 1.3% of 1'420'494'075 models outperformed the GRACE 2.0 Score. The SPUM-ACS Score includes age, plasma glucose, NT-proBNP, left ventricular ejection fraction (LVEF), Killip class, history of peripheral artery disease (PAD), malignancy, and cardio-pulmonary resuscitation. For predicting 1-year mortality after ACS, the SPUM-ACS Score outperformed the GRACE 2.0 Score which achieves a 5-fold cross-validated AUC of 0.81 (95% CI 0.78-0.84). Ranking individual features according to their importance across all multivariate models revealed age, trimethylamine N-oxide, creatinine, history of PAD or malignancy, LVEF, and haemoglobin as the most relevant variables for predicting 1-year mortality. CONCLUSIONS: The variable ranking and the selection for the SPUM-ACS Score highlight the relevance of age, markers of heart failure, and comorbidities for prediction of all-cause death. Before application, this score needs to be externally validated and refined in larger cohorts. CLINICAL TRIAL REGISTRATION: NCT01000701. Published on behalf of the European Society of Cardiology. All rights reserved.
BACKGROUND: The Global Registry of Acute Coronary Events (GRACE) score is an established clinical risk stratification tool for patients with acute coronary syndromes (ACS). We developed and internally validated a model for 1-year all-cause mortality prediction in ACS patients. METHODS: Between 2009 and 2012, 2'168 ACS patients were enrolled into the Swiss SPUM-ACS Cohort. Biomarkers were determined in 1'892 patients and follow-up was achieved in 95.8% of patients. 1-year all-cause mortality was 4.3% (n = 80). In our analysis we consider all linear models using combinations of 8 out of 56 variables to predict 1-year all-cause mortality and to derive a variable ranking. RESULTS: 1.3% of 1'420'494'075 models outperformed the GRACE 2.0 Score. The SPUM-ACS Score includes age, plasma glucose, NT-proBNP, left ventricular ejection fraction (LVEF), Killip class, history of peripheral artery disease (PAD), malignancy, and cardio-pulmonary resuscitation. For predicting 1-year mortality after ACS, the SPUM-ACS Score outperformed the GRACE 2.0 Score which achieves a 5-fold cross-validated AUC of 0.81 (95% CI 0.78-0.84). Ranking individual features according to their importance across all multivariate models revealed age, trimethylamine N-oxide, creatinine, history of PAD or malignancy, LVEF, and haemoglobin as the most relevant variables for predicting 1-year mortality. CONCLUSIONS: The variable ranking and the selection for the SPUM-ACS Score highlight the relevance of age, markers of heart failure, and comorbidities for prediction of all-cause death. Before application, this score needs to be externally validated and refined in larger cohorts. CLINICAL TRIAL REGISTRATION: NCT01000701. Published on behalf of the European Society of Cardiology. All rights reserved.
Authors: Xavier Rossello; Jannick An Dorresteijn; Arne Janssen; Ekaterini Lambrinou; Martijn Scherrenberg; Eric Bonnefoy-Cudraz; Mark Cobain; Massimo F Piepoli; Frank Lj Visseren; Paul Dendale Journal: Eur J Prev Cardiol Date: 2019-06-24 Impact factor: 7.804
Authors: Jussi A Hernesniemi; Shadi Mahdiani; Juho A Tynkkynen; Leo-Pekka Lyytikäinen; Pashupati P Mishra; Terho Lehtimäki; Markku Eskola; Kjell Nikus; Kari Antila; Niku Oksala Journal: Ann Med Date: 2019-04-27 Impact factor: 4.709
Authors: Andres Hilfiker; Denise Hilfiker-Kleiner; Martin Fuchs; Karol Kaminski; Artur Lichtenberg; Hermann-Josef Rothkötter; Bernhard Schieffer; Helmut Drexler Journal: Circulation Date: 2002-07-09 Impact factor: 29.690
Authors: Paul M Ridker; Jean G MacFadyen; Tom Thuren; Brendan M Everett; Peter Libby; Robert J Glynn Journal: Lancet Date: 2017-08-27 Impact factor: 79.321
Authors: Lars Wallentin; Richard C Becker; Andrzej Budaj; Christopher P Cannon; Håkan Emanuelsson; Claes Held; Jay Horrow; Steen Husted; Stefan James; Hugo Katus; Kenneth W Mahaffey; Benjamin M Scirica; Allan Skene; Philippe Gabriel Steg; Robert F Storey; Robert A Harrington; Anneli Freij; Mona Thorsén Journal: N Engl J Med Date: 2009-08-30 Impact factor: 91.245
Authors: Borja Ibanez; Stefan James; Stefan Agewall; Manuel J Antunes; Chiara Bucciarelli-Ducci; Héctor Bueno; Alida L P Caforio; Filippo Crea; John A Goudevenos; Sigrun Halvorsen; Gerhard Hindricks; Adnan Kastrati; Mattie J Lenzen; Eva Prescott; Marco Roffi; Marco Valgimigli; Christoph Varenhorst; Pascal Vranckx; Petr Widimský Journal: Eur Heart J Date: 2018-01-07 Impact factor: 29.983
Authors: Roland Klingenberg; Soheila Aghlmandi; Christoph Liebetrau; Lorenz Räber; Baris Gencer; David Nanchen; David Carballo; Alexander Akhmedov; Fabrizio Montecucco; Stefan Zoller; Chad Brokopp; Dik Heg; Peter Jüni; Helena Marti Soler; Pedro-Manuel Marques-Vidal; Peter Vollenweider; Oliver Dörr; Nicolas Rodondi; François Mach; Stephan Windecker; Ulf Landmesser; Arnold von Eckardstein; Christian W Hamm; Christian M Matter; Thomas F Lüscher Journal: Eur Heart J Date: 2017-12-14 Impact factor: 29.983