{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T18:42:34Z","timestamp":1767984154238,"version":"3.49.0"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"1","funder":[{"name":"Diabetes and Digestive and Kidney Diseases","award":["K25 DK097279"],"award-info":[{"award-number":["K25 DK097279"]}]},{"name":"Diabetes and Digestive and Kidney Diseases","award":["NIDDK R01DK090181"],"award-info":[{"award-number":["NIDDK R01DK090181"]}]},{"name":"Diabetes and Digestive and Kidney Diseases","award":["R01DK095024"],"award-info":[{"award-number":["R01DK095024"]}]},{"name":"Gordon A. Cain Chair in Nephrology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,1,1]]},"abstract":"<jats:p>Objective: Electronic health records (EHRs) are a resource for \u201cbig data\u201d 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.<\/jats:p><jats:p>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.<\/jats:p><jats:p>Results: The best predictors used all the available data (c-statistic ranged from 0.72\u20130.76), 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.<\/jats:p><jats:p>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.<\/jats:p>","DOI":"10.1093\/jamia\/ocw057","type":"journal-article","created":{"date-parts":[[2016,6,30]],"date-time":"2016-06-30T01:13:28Z","timestamp":1467249208000},"page":"176-181","source":"Crossref","is-referenced-by-count":26,"title":["Predicting mortality over different time horizons: which data elements are needed?"],"prefix":"10.1093","volume":"24","author":[{"given":"Benjamin A","family":"Goldstein","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Bioinformatics, Duke University, Durham, North Carolina"},{"name":"Center for Predictive Medicine, Duke Clinical Research Institute, Durham, North Carolina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael J","family":"Pencina","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Bioinformatics, Duke University, Durham, North Carolina"},{"name":"Center for Predictive Medicine, Duke Clinical Research Institute, Durham, North Carolina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria E","family":"Montez-Rath","sequence":"additional","affiliation":[{"name":"Division of Nephrology, Stanford University School of Medicine, Palo Alto, California,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang C","family":"Winkelmayer","sequence":"additional","affiliation":[{"name":"Section of Nephrology, Baylor College of Medicine, Houston, Texas"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2016,6,29]]},"reference":[{"issue":"2","key":"2020110612375590000_ocw057-B1","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1136\/amiajnl-2013-001854","article-title":"Medical decision support using machine learning for early detection of late-onset neonatal sepsis","volume":"21","author":"Mani","year":"2014","journal-title":"J Am Med Inform Assoc."},{"issue":"6","key":"2020110612375590000_ocw057-B2","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1016\/j.cjca.2012.02.009","article-title":"Modified metabolic syndrome criteria for identification of patients at risk of developing diabetes and coronary heart diseases: longitudinal assessment via electronic health records","volume":"28","author":"Hivert","year":"2012","journal-title":"Can J Cardiol."},{"issue":"3","key":"2020110612375590000_ocw057-B3","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.jchf.2013.01.008","article-title":"Validated, electronic health record deployable prediction models for assessing patient risk of 30-day rehospitalization and mortality in older heart failure patients","volume":"1","author":"Eapen","year":"2013","journal-title":"JACC Heart Fail."},{"issue":"6","key":"2020110612375590000_ocw057-B4","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1177\/0272989X10364246","article-title":"Development of inpatient risk stratification models of acute kidney injury for use in electronic health records","volume":"30","author":"Matheny","year":"2010","journal-title":"Med Decis Mak Int J Soc Med Decis Mak."},{"key":"2020110612375590000_ocw057-B5","volume-title":"National Institute of Health","author":"U.S. Renal Data System, USRDS 2014 Annual Data Report: Atlas of End-Stage Renal Disease in the United States"},{"issue":"8","key":"2020110612375590000_ocw057-B6","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1093\/gerona\/glt289","article-title":"Prognostic stratification in older adults commencing dialysis","volume":"69","author":"Cheung","year":"2014","journal-title":"J Gerontol A Biol Sci Med Sci."},{"key":"2020110612375590000_ocw057-B7","doi-asserted-by":"crossref","first-page":"A7, e1","DOI":"10.1053\/j.ajkd.2012.11.031","article-title":"US Renal Data System 2012 Annual Data Report","volume":"61","author":"Collins","year":"2013","journal-title":"Am J Kidney Dis Off J Natl Kidney Found."},{"issue":"1","key":"2020110612375590000_ocw057-B8","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc Ser B."},{"issue":"3","key":"2020110612375590000_ocw057-B9","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1148\/radiology.148.3.6878708","article-title":"A method of comparing the areas under receiver operating characteristic curves derived from the same cases","volume":"148","author":"Hanley","year":"1983","journal-title":"Radiology."},{"key":"2020110612375590000_ocw057-B10","article-title":"Assessing calibration of prognostic risk scores","author":"Crowson","year":"2014","journal-title":"Stat Methods Med Res"},{"issue":"5","key":"2020110612375590000_ocw057-B11","doi-asserted-by":"crossref","DOI":"10.18637\/jss.v039.i05","article-title":"Regularization Paths for Cox\u2019s Proportional Hazards Model via Coordinate Descent","volume":"39","author":"Simon","year":"2011","journal-title":"J Stat Softw"},{"issue":"1","key":"2020110612375590000_ocw057-B12","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1111\/j.0006-341X.2005.030814.x","article-title":"Survival model predictive accuracy and ROC curves","volume":"61","author":"Heagerty","year":"2005","journal-title":"Biometrics."},{"key":"2020110612375590000_ocw057-B13","volume-title":"R: A Language and Environment for Statistical Computing [Internet]","author":"R Core Team.","year":"2012"},{"key":"2020110612375590000_ocw057-B14","first-page":"606","article-title":"Type 2 diabetes risk forecasting from EMR data using machine learning","volume":"2012","author":"Mani","year":"2012","journal-title":"AMIA Annu Symp Proc AMIA Symp AMIA Symp."},{"issue":"9","key":"2020110612375590000_ocw057-B15","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1016\/j.amjcard.2012.06.038","article-title":"Predicting risk of hospitalization or death among patients with heart failure in the Veterans Health Administration","volume":"110","author":"Wang","year":"2012","journal-title":"Am J Cardiol."},{"issue":"4","key":"2020110612375590000_ocw057-B16","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1097\/MLR.0b013e31827da95a","article-title":"Predicting risk of hospitalization or death among patients receiving primary care in the Veterans Health Administration","volume":"51","author":"Wang","year":"2013","journal-title":"Med Care."},{"issue":"1","key":"2020110612375590000_ocw057-B17","doi-asserted-by":"crossref","first-page":"82","DOI":"10.2215\/CJN.03050313","article-title":"Near-term prediction of sudden cardiac death in older hemodialysis patients using electronic health records","volume":"9","author":"Goldstein","year":"2014","journal-title":"Clin J Am Soc Nephrol."},{"issue":"3","key":"2020110612375590000_ocw057-B18","doi-asserted-by":"crossref","first-page":"e004007","DOI":"10.1136\/bmjopen-2013-004007","article-title":"Machine-learning prediction of cancer survival: a retrospective study using electronic administrative records and a cancer registry","volume":"4","author":"Gupta","year":"2014","journal-title":"BMJ Open."},{"issue":"6","key":"2020110612375590000_ocw057-B19","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1136\/amiajnl-2014-002733","article-title":"Toward personalizing treatment for depression: predicting diagnosis and severity","volume":"21","author":"Huang","year":"2014","journal-title":"J Am Med Inform Assoc"},{"issue":"4","key":"2020110612375590000_ocw057-B20","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1071\/AH14059","article-title":"Predicting unplanned readmission after myocardial infarction from routinely collected administrative hospital data","volume":"38","author":"Rana","year":"2014","journal-title":"Aust Health Rev Publ Aust Hosp Assoc."},{"issue":"13","key":"2020110612375590000_ocw057-B21","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1093\/eurheartj\/eht533","article-title":"Prognostic models for stable coronary artery disease based on electronic health record cohort of 102 023 patients","volume":"35","author":"Rapsomaniki","year":"2014","journal-title":"Eur Heart J."},{"key":"2020110612375590000_ocw057-B22","doi-asserted-by":"crossref","DOI":"10.1093\/jamia\/ocw042","article-title":"Opportunities and challenges in developing risk prediction models with electronic health records: a systematic review","volume-title":"J Am Med Inform Assoc (In Press)","author":"Goldstein"},{"key":"2020110612375590000_ocw057-B23","volume-title":"Time Dependent Logistic Models in Follow-up Studies and Clinical Trials, 1. Binary Data","author":"Elandt-Johnson","year":"1980"},{"issue":"6 Pt 2","key":"2020110612375590000_ocw057-B24","first-page":"S6","article-title":"Comparison of Cox regression with other methods for determining prediction models and nomograms","volume":"170","author":"Kattan","year":"2003","journal-title":"J Urol."},{"issue":"8","key":"2020110612375590000_ocw057-B25","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1001\/jama.299.8.950","article-title":"Health care as if health mattered","volume":"299","author":"Frieden","year":"2008","journal-title":"JAMA"},{"issue":"e1","key":"2020110612375590000_ocw057-B26","doi-asserted-by":"crossref","first-page":"e147","DOI":"10.1136\/amiajnl-2012-000896","article-title":"Validation of electronic medical record\u2013based phenotyping algorithms: results and lessons learned from the eMERGE network","volume":"20","author":"Newton","year":"2013","journal-title":"J Am Med Inform Assoc"},{"issue":"2","key":"2020110612375590000_ocw057-B27","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1159\/000357640","article-title":"Predicting first-year mortality in incident dialysis patients with end-stage renal disease\u2014the UREA5 study","volume":"37","author":"Chua","year":"2014","journal-title":"Blood Purif."},{"issue":"12","key":"2020110612375590000_ocw057-B28","doi-asserted-by":"crossref","first-page":"1447","DOI":"10.1161\/CIRCULATIONAHA.109.904029","article-title":"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","volume":"121","author":"Eagle","year":"2010","journal-title":"Circulation."}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/24\/1\/176\/34148351\/ocw057.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/24\/1\/176\/34148351\/ocw057.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:58:43Z","timestamp":1718672323000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/24\/1\/176\/2631455"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6,29]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2016,6,29]]},"published-print":{"date-parts":[[2017,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocw057","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,1]]},"published":{"date-parts":[[2016,6,29]]}}}