An improved comorbidity summary score for measuring disease burden and predicting mortality with applications to two national cohorts. Issue 18 (17th September 2019)

• Record Type: Journal Article
• Authors: Ward, Ralph C.; Egede, Leonard; Ramakrishnan, Viswanathan; Frey, Lewis; Axon, Robert Neal; Dismuke, Clara Libby E.; Hunt, Kelly J.; Gebregziabher, Mulugeta
• Is Part Of: Communications in statistics. Volume 48:Issue 18(2019)
• Page Start: 4642
• Page End: 4655
• Publication Date: 2019-09-17
• Subjects: Comorbidity index -- ICD system -- administrative healthcare data -- Bayesian prediction -- machine learning -- comorbidity summary score; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2018.1498896
• Languages: English
• ISSNs: 0361-0926

Abstract

Abstract: Research involving administrative healthcare data to study patient outcomes requires the investigator to account for the patient's disease burden in order to reduce the potential for biased results. Here we develop a comorbidity summary score based on variable importance measures derived from several statistical and machine learning methods and show it has superior predictive performance to the Elixhauser and Charlson indices when used to predict 1-year, 5-year, and 10-year mortality. We used two large Veterans Administration cohorts to develop and validate the summary score and compared predictive performance using the area under ROC curve (AUC) and the Brier score.