Development of a national Department of Veterans Affairs mortality risk prediction model among patients with cirrhosis

Objective Cirrhotic patients are at high hospitalisation risk with subsequent high mortality. Current risk prediction models have varied performances with methodological room for improvement. We used current analytical techniques using automatically extractable variables from the electronic health r...

Full description

Saved in:
Bibliographic Details
Main Authors: Jejo David Koola, Samuel Ho, Guanhua Chen, Amy M Perkins, Aize Cao, Sharon E Davis, Michael E Matheny
Format: Article
Language:English
Published: BMJ Publishing Group 2019-08-01
Series:BMJ Open Gastroenterology
Online Access:https://bmjopengastro.bmj.com/content/6/1/e000342.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850109949763387392
author Jejo David Koola
Samuel Ho
Guanhua Chen
Amy M Perkins
Aize Cao
Sharon E Davis
Michael E Matheny
author_facet Jejo David Koola
Samuel Ho
Guanhua Chen
Amy M Perkins
Aize Cao
Sharon E Davis
Michael E Matheny
author_sort Jejo David Koola
collection DOAJ
description Objective Cirrhotic patients are at high hospitalisation risk with subsequent high mortality. Current risk prediction models have varied performances with methodological room for improvement. We used current analytical techniques using automatically extractable variables from the electronic health record (EHR) to develop and validate a posthospitalisation mortality risk score for cirrhotic patients and compared performance with the model for end-stage liver disease (MELD), model for end-stage liver disease with sodium (MELD-Na), and the CLIF Consortium Acute Decompensation (CLIF-C AD) models.Design We analysed a retrospective cohort of 73 976 patients comprising 247 650 hospitalisations between 2006 and 2013 at any of 123 Department of Veterans Affairs hospitals. Using 45 predictor variables, we built a time-dependent Cox proportional hazards model with all-cause mortality as the outcome. We compared performance to the three extant models and reported discrimination and calibration using bootstrapping. Furthermore, we analysed differential utility using the net reclassification index (NRI).Results The C-statistic for the final model was 0.863, representing a significant improvement over the MELD, MELD-Na, and the CLIF-C AD, which had C-statistics of 0.655, 0.675, and 0.679, respectively. Multiple risk factors were significant in our model, including variables reflecting disease severity and haemodynamic compromise. The NRI showed a 24% improvement in predicting survival of low-risk patients and a 30% improvement in predicting death of high-risk patients.Conclusion We developed a more accurate mortality risk prediction score using variables automatically extractable from an EHR that may be used to risk stratify patients with cirrhosis for targeted postdischarge management.
format Article
id doaj-art-9f39e6e65b08446087a36e6ecc0ac4b9
institution OA Journals
issn 2054-4774
language English
publishDate 2019-08-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open Gastroenterology
spelling doaj-art-9f39e6e65b08446087a36e6ecc0ac4b92025-08-20T02:37:57ZengBMJ Publishing GroupBMJ Open Gastroenterology2054-47742019-08-016110.1136/bmjgast-2019-000342Development of a national Department of Veterans Affairs mortality risk prediction model among patients with cirrhosisJejo David Koola0Samuel Ho1Guanhua Chen2Amy M Perkins3Aize Cao4Sharon E Davis5Michael E Matheny6Department of Medicine, University of California San Diego, La Jolla, California, USADepartment of Medicine, University of California San Diego, La Jolla, California, USADepartment of Biostatistics and Medical Informatics, University of Wisconsin Madison, Madison, Wisconsin, USADepartment of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USAVeteran`s Health Administration, VA Tennessee Valley Healthcare System, Nashville, Tennessee, USAVeteran`s Health Administration, VA Tennessee Valley Healthcare System, Nashville, Tennessee, USATennessee Valley Healthcare System, Veterans Affairs Medical Center, Nashville, TN, USAObjective Cirrhotic patients are at high hospitalisation risk with subsequent high mortality. Current risk prediction models have varied performances with methodological room for improvement. We used current analytical techniques using automatically extractable variables from the electronic health record (EHR) to develop and validate a posthospitalisation mortality risk score for cirrhotic patients and compared performance with the model for end-stage liver disease (MELD), model for end-stage liver disease with sodium (MELD-Na), and the CLIF Consortium Acute Decompensation (CLIF-C AD) models.Design We analysed a retrospective cohort of 73 976 patients comprising 247 650 hospitalisations between 2006 and 2013 at any of 123 Department of Veterans Affairs hospitals. Using 45 predictor variables, we built a time-dependent Cox proportional hazards model with all-cause mortality as the outcome. We compared performance to the three extant models and reported discrimination and calibration using bootstrapping. Furthermore, we analysed differential utility using the net reclassification index (NRI).Results The C-statistic for the final model was 0.863, representing a significant improvement over the MELD, MELD-Na, and the CLIF-C AD, which had C-statistics of 0.655, 0.675, and 0.679, respectively. Multiple risk factors were significant in our model, including variables reflecting disease severity and haemodynamic compromise. The NRI showed a 24% improvement in predicting survival of low-risk patients and a 30% improvement in predicting death of high-risk patients.Conclusion We developed a more accurate mortality risk prediction score using variables automatically extractable from an EHR that may be used to risk stratify patients with cirrhosis for targeted postdischarge management.https://bmjopengastro.bmj.com/content/6/1/e000342.full
spellingShingle Jejo David Koola
Samuel Ho
Guanhua Chen
Amy M Perkins
Aize Cao
Sharon E Davis
Michael E Matheny
Development of a national Department of Veterans Affairs mortality risk prediction model among patients with cirrhosis
BMJ Open Gastroenterology
title Development of a national Department of Veterans Affairs mortality risk prediction model among patients with cirrhosis
title_full Development of a national Department of Veterans Affairs mortality risk prediction model among patients with cirrhosis
title_fullStr Development of a national Department of Veterans Affairs mortality risk prediction model among patients with cirrhosis
title_full_unstemmed Development of a national Department of Veterans Affairs mortality risk prediction model among patients with cirrhosis
title_short Development of a national Department of Veterans Affairs mortality risk prediction model among patients with cirrhosis
title_sort development of a national department of veterans affairs mortality risk prediction model among patients with cirrhosis
url https://bmjopengastro.bmj.com/content/6/1/e000342.full
work_keys_str_mv AT jejodavidkoola developmentofanationaldepartmentofveteransaffairsmortalityriskpredictionmodelamongpatientswithcirrhosis
AT samuelho developmentofanationaldepartmentofveteransaffairsmortalityriskpredictionmodelamongpatientswithcirrhosis
AT guanhuachen developmentofanationaldepartmentofveteransaffairsmortalityriskpredictionmodelamongpatientswithcirrhosis
AT amymperkins developmentofanationaldepartmentofveteransaffairsmortalityriskpredictionmodelamongpatientswithcirrhosis
AT aizecao developmentofanationaldepartmentofveteransaffairsmortalityriskpredictionmodelamongpatientswithcirrhosis
AT sharonedavis developmentofanationaldepartmentofveteransaffairsmortalityriskpredictionmodelamongpatientswithcirrhosis
AT michaelematheny developmentofanationaldepartmentofveteransaffairsmortalityriskpredictionmodelamongpatientswithcirrhosis