Literature DB >> 27357832

Predicting mortality over different time horizons: which data elements are needed?

Benjamin A Goldstein1,2, Michael J Pencina3,2, Maria E Montez-Rath4, Wolfgang C Winkelmayer5.   

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.
© The Author 2016. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  ESRD; Electronic Health Records; hemodialysis; predictive modeling

Mesh:

Year:  2016        PMID: 27357832      PMCID: PMC5201182          DOI: 10.1093/jamia/ocw057

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  24 in total

Review 1.  Identifying patients at high risk of a cardiovascular event in the near future: current status and future directions: report of a national heart, lung, and blood institute working group.

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

2.  Near-term prediction of sudden cardiac death in older hemodialysis patients using electronic health records.

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

3.  Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network.

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

4.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases.

Authors:  J A Hanley; B J McNeil
Journal:  Radiology       Date:  1983-09       Impact factor: 11.105

5.  Modified metabolic syndrome criteria for identification of patients at risk of developing diabetes and coronary heart diseases: longitudinal assessment via electronic health records.

Authors:  Marie-France Hivert; Francis Dusseault-Bélanger; Alan Cohen; Josiane Courteau; Alain Vanasse
Journal:  Can J Cardiol       Date:  2012-05-01       Impact factor: 5.223

6.  Medical decision support using machine learning for early detection of late-onset neonatal sepsis.

Authors:  Subramani Mani; Asli Ozdas; Constantin Aliferis; Huseyin Atakan Varol; Qingxia Chen; Randy Carnevale; Yukun Chen; Joann Romano-Keeler; Hui Nian; Jörn-Hendrik Weitkamp
Journal:  J Am Med Inform Assoc       Date:  2013-09-16       Impact factor: 4.497

7.  Predicting unplanned readmission after myocardial infarction from routinely collected administrative hospital data.

Authors:  Santu Rana; Truyen Tran; Wei Luo; Dinh Phung; Richard L Kennedy; Svetha Venkatesh
Journal:  Aust Health Rev       Date:  2014-09       Impact factor: 1.990

8.  Type 2 diabetes risk forecasting from EMR data using machine learning.

Authors:  Subramani Mani; Yukun Chen; Tom Elasy; Warren Clayton; Joshua Denny
Journal:  AMIA Annu Symp Proc       Date:  2012-11-03

9.  Prognostic models for stable coronary artery disease based on electronic health record cohort of 102 023 patients.

Authors:  Eleni Rapsomaniki; Anoop Shah; Pablo Perel; Spiros Denaxas; Julie George; Owen Nicholas; Ruzan Udumyan; Gene Solomon Feder; Aroon D Hingorani; Adam Timmis; Liam Smeeth; Harry Hemingway
Journal:  Eur Heart J       Date:  2013-12-17       Impact factor: 29.983

10.  Machine-learning prediction of cancer survival: a retrospective study using electronic administrative records and a cancer registry.

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

View more
  13 in total

1.  Early Detection of Heart Failure Using Electronic Health Records: Practical Implications for Time Before Diagnosis, Data Diversity, Data Quantity, and Data Density.

Authors:  Kenney Ng; Steven R Steinhubl; Christopher deFilippi; Sanjoy Dey; Walter F Stewart
Journal:  Circ Cardiovasc Qual Outcomes       Date:  2016-11-08

2.  A Comparative Study of Carvedilol Versus Metoprolol Initiation and 1-Year Mortality Among Individuals Receiving Maintenance Hemodialysis.

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

3.  Failed Target Weight Achievement Associates with Short-Term Hospital Encounters among Individuals Receiving Maintenance Hemodialysis.

Authors:  Magdalene M Assimon; Lily Wang; Jennifer E Flythe
Journal:  J Am Soc Nephrol       Date:  2018-05-23       Impact factor: 10.121

Review 4.  Secondary Use of Patient Data: Review of the Literature Published in 2016.

Authors:  D R Schlegel; G Ficheur
Journal:  Yearb Med Inform       Date:  2017-09-11

5.  A comparison of risk prediction methods using repeated observations: an application to electronic health records for hemodialysis.

Authors:  Benjamin A Goldstein; Gina Maria Pomann; Wolfgang C Winkelmayer; Michael J Pencina
Journal:  Stat Med       Date:  2017-05-02       Impact factor: 2.373

6.  Quantifying the utility of islet autoantibody levels in the prediction of type 1 diabetes in children.

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

7.  Preferences for Predictive Model Characteristics among People Living with Chronic Lung Disease: A Discrete Choice Experiment.

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

8.  Minimal Impact of Implemented Early Warning Score and Best Practice Alert for Patient Deterioration.

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

9.  Application of regularized regression to identify novel predictors of mortality in a cohort of hemodialysis patients.

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

Review 10.  Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges.

Authors:  Benjamin A Goldstein; Ann Marie Navar; Rickey E Carter
Journal:  Eur Heart J       Date:  2017-06-14       Impact factor: 29.983

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.