Leila R Zelnick1, Michael G Shlipak2, Elsayed Z Soliman3, Amanda Anderson4, Robert Christenson5, James Lash6, Rajat Deo7, Panduranga Rao8, Farsad Afshinnia9, Jing Chen10, Jiang He4, Stephen Seliger5, Raymond Townsend11, Debbie L Cohen11, Alan Go12, Nisha Bansal13,14. 1. Kidney Research Institute and Division of Nephrology, University of Washington, Seattle, Washington lzelnick@uw.edu. 2. Department of Medicine, University of California, San Francisco, California. 3. Department of Medicine, Wake Forest University, Winston-Salem, North Carolina. 4. Department of Epidemiology, Tulane University, New Orleans, Louisiana. 5. Department of Medicine, University of Maryland, Baltimore, Maryland. 6. Division of Nephrology, University of Illinois-Chicago, Chicago, Illinois. 7. Departments of Medicine and Epidemiology and Biostatistics, University of Pennsylvania, Philadelphia, Pennsylvania. 8. Department of Internal Medicine, Division of Nephrology, University of Michigan, Ann Arbor, Michigan. 9. Department of Medicine, Division of Nephrology, University of Michigan, Oakland, California. 10. Department of Medicine, Tulane University, New Orleans, Louisiana. 11. Department of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania. 12. Division of Nephrology, University of Washington, Seattle, Washington. 13. Kidney Research Institute and Division of Nephrology, University of Washington, Seattle, Washington. 14. Kaiser Permanente Northern California, Oakland, California.
Abstract
BACKGROUND AND OBJECTIVES: Atrial fibrillation (AF) is common in CKD and associated with poor kidney and cardiovascular outcomes. Prediction models developed using novel methods may be useful to identify patients with CKD at highest risk of incident AF. We compared a previously published prediction model with models developed using machine learning methods in a CKD population. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We studied 2766 participants in the Chronic Renal Insufficiency Cohort study without prior AF with complete cardiac biomarker (N-terminal pro-B-type natriuretic peptide and high-sensitivity troponin T) and clinical data. We evaluated the utility of machine learning methods as well as a previously validated clinical prediction model (Cohorts for Heart and Aging Research in Genomic Epidemiology [CHARGE]-AF, which included 11 predictors, using original and re-estimated coefficients) to predict incident AF. Discriminatory ability of each model was assessed using the ten-fold cross-validated C-index; calibration was evaluated graphically and with the Grønnesby and Borgan test. RESULTS: Mean (SD) age of participants was 57 (11) years, 55% were men, 38% were Black, and mean (SD) eGFR was 45 (15) ml/min per 1.73 m2; 259 incident AF events occurred during a median of 8 years of follow-up. The CHARGE-AF prediction equation using original and re-estimated coefficients had C-indices of 0.67 (95% confidence interval, 0.64 to 0.71) and 0.67 (95% confidence interval, 0.64 to 0.70), respectively. A likelihood-based boosting model using clinical variables only had a C-index of 0.67 (95% confidence interval, 0.64 to 0.70); adding N-terminal pro-B-type natriuretic peptide, high-sensitivity troponin T, or both biomarkers improved the C-index by 0.04, 0.01, and 0.04, respectively. In addition to N-terminal pro-B-type natriuretic peptide and high-sensitivity troponin T, the final model included age, non-Hispanic Black race/ethnicity, Hispanic race/ethnicity, cardiovascular disease, chronic obstructive pulmonary disease, myocardial infarction, peripheral vascular disease, use of angiotensin-converting enzyme inhibitor/angiotensin receptor blockers, calcium channel blockers, diuretics, height, and weight. CONCLUSIONS: Using machine learning algorithms, a model that included 12 standard clinical variables and cardiac-specific biomarkers N-terminal pro-B-type natriuretic peptide and high-sensitivity troponin T had moderate discrimination for incident AF in a CKD population.
BACKGROUND AND OBJECTIVES: Atrial fibrillation (AF) is common in CKD and associated with poor kidney and cardiovascular outcomes. Prediction models developed using novel methods may be useful to identify patients with CKD at highest risk of incident AF. We compared a previously published prediction model with models developed using machine learning methods in a CKD population. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We studied 2766 participants in the Chronic Renal Insufficiency Cohort study without prior AF with complete cardiac biomarker (N-terminal pro-B-type natriuretic peptide and high-sensitivity troponin T) and clinical data. We evaluated the utility of machine learning methods as well as a previously validated clinical prediction model (Cohorts for Heart and Aging Research in Genomic Epidemiology [CHARGE]-AF, which included 11 predictors, using original and re-estimated coefficients) to predict incident AF. Discriminatory ability of each model was assessed using the ten-fold cross-validated C-index; calibration was evaluated graphically and with the Grønnesby and Borgan test. RESULTS: Mean (SD) age of participants was 57 (11) years, 55% were men, 38% were Black, and mean (SD) eGFR was 45 (15) ml/min per 1.73 m2; 259 incident AF events occurred during a median of 8 years of follow-up. The CHARGE-AF prediction equation using original and re-estimated coefficients had C-indices of 0.67 (95% confidence interval, 0.64 to 0.71) and 0.67 (95% confidence interval, 0.64 to 0.70), respectively. A likelihood-based boosting model using clinical variables only had a C-index of 0.67 (95% confidence interval, 0.64 to 0.70); adding N-terminal pro-B-type natriuretic peptide, high-sensitivity troponin T, or both biomarkers improved the C-index by 0.04, 0.01, and 0.04, respectively. In addition to N-terminal pro-B-type natriuretic peptide and high-sensitivity troponin T, the final model included age, non-Hispanic Black race/ethnicity, Hispanic race/ethnicity, cardiovascular disease, chronic obstructive pulmonary disease, myocardial infarction, peripheral vascular disease, use of angiotensin-converting enzyme inhibitor/angiotensin receptor blockers, calcium channel blockers, diuretics, height, and weight. CONCLUSIONS: Using machine learning algorithms, a model that included 12 standard clinical variables and cardiac-specific biomarkers N-terminal pro-B-type natriuretic peptide and high-sensitivity troponin T had moderate discrimination for incident AF in a CKD population.
Authors: Rupal Mehta; Xuan Cai; Jungwha Lee; Julia J Scialla; Nisha Bansal; James H Sondheimer; Jing Chen; L Lee Hamm; Ana C Ricardo; Sankar D Navaneethan; Rajat Deo; Mahboob Rahman; Harold I Feldman; Alan S Go; Tamara Isakova; Myles Wolf Journal: JAMA Cardiol Date: 2016-08-01 Impact factor: 14.676
Authors: Marshall Joffe; Chi-yuan Hsu; Harold I Feldman; Matthew Weir; J R Landis; L Lee Hamm Journal: Am J Nephrol Date: 2010-04-14 Impact factor: 3.754
Authors: Lesley A Inker; Christopher H Schmid; Hocine Tighiouart; John H Eckfeldt; Harold I Feldman; Tom Greene; John W Kusek; Jane Manzi; Frederick Van Lente; Yaping Lucy Zhang; Josef Coresh; Andrew S Levey Journal: N Engl J Med Date: 2012-07-05 Impact factor: 91.245
Authors: Romain Pirracchio; Maya L Petersen; Marco Carone; Matthieu Resche Rigon; Sylvie Chevret; Mark J van der Laan Journal: Lancet Respir Med Date: 2014-11-24 Impact factor: 30.700
Authors: Alvaro Alonso; Bouwe P Krijthe; Thor Aspelund; Katherine A Stepas; Michael J Pencina; Carlee B Moser; Moritz F Sinner; Nona Sotoodehnia; João D Fontes; A Cecile J W Janssens; Richard A Kronmal; Jared W Magnani; Jacqueline C Witteman; Alanna M Chamberlain; Steven A Lubitz; Renate B Schnabel; Sunil K Agarwal; David D McManus; Patrick T Ellinor; Martin G Larson; Gregory L Burke; Lenore J Launer; Albert Hofman; Daniel Levy; John S Gottdiener; Stefan Kääb; David Couper; Tamara B Harris; Elsayed Z Soliman; Bruno H C Stricker; Vilmundur Gudnason; Susan R Heckbert; Emelia J Benjamin Journal: J Am Heart Assoc Date: 2013-03-18 Impact factor: 5.501
Authors: Felix K Wegner; Lucas Plagwitz; Florian Doldi; Christian Ellermann; Kevin Willy; Julian Wolfes; Sarah Sandmann; Julian Varghese; Lars Eckardt Journal: Clin Res Cardiol Date: 2022-03-30 Impact factor: 6.138