Benjamin A Goldstein1,2, Michael J Pencina3,2, Maria E Montez-Rath4, Wolfgang C Winkelmayer5. 1. Department of Biostatistics and Bioinformatics, Duke University, Durham, North Carolina ben.goldstein@duke.edu. 2. Center for Predictive Medicine, Duke Clinical Research Institute, Durham, North Carolina. 3. Department of Biostatistics and Bioinformatics, Duke University, Durham, North Carolina. 4. Division of Nephrology, Stanford University School of Medicine, Palo Alto, California. 5. Section of Nephrology, Baylor College of Medicine, Houston, Texas.
Abstract
OBJECTIVE: Electronic health records (EHRs) are a resource for "big data" analytics, containing a variety of data elements. We investigate how different categories of information contribute to prediction of mortality over different time horizons among patients undergoing hemodialysis treatment. MATERIAL AND METHODS: We derived prediction models for mortality over 7 time horizons using EHR data on older patients from a national chain of dialysis clinics linked with administrative data using LASSO (least absolute shrinkage and selection operator) regression. We assessed how different categories of information relate to risk assessment and compared discrete models to time-to-event models. RESULTS: The best predictors used all the available data (c-statistic ranged from 0.72-0.76), with stronger models in the near term. While different variable groups showed different utility, exclusion of any particular group did not lead to a meaningfully different risk assessment. Discrete time models performed better than time-to-event models. CONCLUSIONS: Different variable groups were predictive over different time horizons, with vital signs most predictive for near-term mortality and demographic and comorbidities more important in long-term mortality.
OBJECTIVE: Electronic health records (EHRs) are a resource for "big data" analytics, containing a variety of data elements. We investigate how different categories of information contribute to prediction of mortality over different time horizons among patients undergoing hemodialysis treatment. MATERIAL AND METHODS: We derived prediction models for mortality over 7 time horizons using EHR data on older patients from a national chain of dialysis clinics linked with administrative data using LASSO (least absolute shrinkage and selection operator) regression. We assessed how different categories of information relate to risk assessment and compared discrete models to time-to-event models. RESULTS: The best predictors used all the available data (c-statistic ranged from 0.72-0.76), with stronger models in the near term. While different variable groups showed different utility, exclusion of any particular group did not lead to a meaningfully different risk assessment. Discrete time models performed better than time-to-event models. CONCLUSIONS: Different variable groups were predictive over different time horizons, with vital signs most predictive for near-term mortality and demographic and comorbidities more important in long-term mortality.
Authors: Kim A Eagle; Geoffrey S Ginsburg; Kiran Musunuru; William C Aird; Robert S Balaban; Susan K Bennett; Roger S Blumenthal; Shaun R Coughlin; Karina W Davidson; Edward D Frohlich; Philip Greenland; Gail P Jarvik; Peter Libby; Carl J Pepine; Jeremy N Ruskin; Arthur E Stillman; Jennifer E Van Eyk; H Eser Tolunay; Cheryl L McDonald; Sidney C Smith Journal: Circulation Date: 2010-03-30 Impact factor: 29.690
Authors: Benjamin A Goldstein; Tara I Chang; Aya A Mitani; Themistocles L Assimes; Wolfgang C Winkelmayer Journal: Clin J Am Soc Nephrol Date: 2013-10-31 Impact factor: 8.237
Authors: Katherine M Newton; Peggy L Peissig; Abel Ngo Kho; Suzette J Bielinski; Richard L Berg; Vidhu Choudhary; Melissa Basford; Christopher G Chute; Iftikhar J Kullo; Rongling Li; Jennifer A Pacheco; Luke V Rasmussen; Leslie Spangler; Joshua C Denny Journal: J Am Med Inform Assoc Date: 2013-03-26 Impact factor: 4.497
Authors: Sunil Gupta; Truyen Tran; Wei Luo; Dinh Phung; Richard Lee Kennedy; Adam Broad; David Campbell; David Kipp; Madhu Singh; Mustafa Khasraw; Leigh Matheson; David M Ashley; Svetha Venkatesh Journal: BMJ Open Date: 2014-03-17 Impact factor: 2.692
Authors: Magdalene M Assimon; M Alan Brookhart; Jason P Fine; Gerardo Heiss; J Bradley Layton; Jennifer E Flythe Journal: Am J Kidney Dis Date: 2018-04-10 Impact factor: 8.860
Authors: Kenney Ng; Vibha Anand; Harry Stavropoulos; Riitta Veijola; Jorma Toppari; Marlena Maziarz; Markus Lundgren; Kathy Waugh; Brigitte I Frohnert; Frank Martin; Olivia Lou; William Hagopian; Peter Achenbach Journal: Diabetologia Date: 2022-10-05 Impact factor: 10.460
Authors: Gary E Weissman; Kuldeep N Yadav; Trishya Srinivasan; Stephanie Szymanski; Florylene Capulong; Vanessa Madden; Katherine R Courtright; Joanna L Hart; David A Asch; Sarah J Ratcliffe; Marilyn M Schapira; Scott D Halpern Journal: Med Decis Making Date: 2020-06-12 Impact factor: 2.583
Authors: Armando D Bedoya; Meredith E Clement; Matthew Phelan; Rebecca C Steorts; Cara O'Brien; Benjamin A Goldstein Journal: Crit Care Med Date: 2019-01 Impact factor: 7.598
Authors: Stanislas Werfel; Georg Lorenz; Bernhard Haller; Roman Günthner; Julia Matschkal; Matthias C Braunisch; Carolin Schaller; Peter Gundel; Stephan Kemmner; Salim S Hayek; Christian Nusshag; Jochen Reiser; Philipp Moog; Uwe Heemann; Christoph Schmaderer Journal: Sci Rep Date: 2021-04-29 Impact factor: 4.379