Article Text
Abstract
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.
- cirrhosis
- mortality
- risk prediction
- survival models
- time-varying covariate models
This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/.
Statistics from Altmetric.com
Footnotes
Twitter @@JejoKoola
Contributors JDK, MEM and SH contributed to the concept and design. JDK, GC, AMP, AC, SED, and MEM contributed to the statistical analysis. All authors contributed to writing the manuscript.
Funding JK was supported by the Department of Veterans Affairs, Office of Academic Affiliations, Advanced Fellowship Program in Medical Informatics, and the Department of Biomedical Informatics, Vanderbilt University, Nashville, Tennessee. GC was supported by the NIH Precision Medicine Initiative Cohort Program Data and Research Support Center (1U2COD023196). MEM, GC, AMP, and SBH were supported by Veterans Health Administration Health Services Research & Development Investigator Initiated Research (IIR 13-052). SED was supported by the National Library of Medicine (5T15LM007450).
Competing interests None declared.
Patient consent for publication Not required.
Ethics approval The institutional review board and research and development committees of the Tennessee Valley Healthcare System VA Medical Center, Nashville, Tennessee, approved this study.
Provenance and peer review Not commissioned; externally peer reviewed.
Data availability statement No data are available. The Department of Veterans Affairs does not allow release of patient data, even in de-identified format.