Email updates

Keep up to date with the latest news and content from BMC Nephrology and BioMed Central.

Open Access Research article

Predicting hospital cost in CKD patients through blood chemistry values

Russell W Bessette1* and Randy L Carter2

Author Affiliations

1 University of Louisville, Abell Administration Center, 323 East Chestnut St. Louisville, Kentucky 40202, USA

2 State University of New York at Buffalo, School of Public Health, Department of Biostatistics and Population Observatory, Farber Hall, Main St, Buffalo, New York 14214, USA

For all author emails, please log on.

BMC Nephrology 2011, 12:65  doi:10.1186/1471-2369-12-65

Published: 1 December 2011

Abstract

Background

Controversy exists in predicting costly hospitalization in patients with chronic kidney disease and co-morbid conditions. We therefore tested associations between serum chemistry values and the occurrence of in-patient hospital costs over a thirteen month study period. Secondarily, we derived a linear combination of variables to estimate probability of such occurrences in any patient.

Method

We calculated parsimonious values for select variables associated with in-patient hospitalization and compared sensitivity and specificity of these models to ordinal staging of renal disease.

Data from 1104 de-identified patients which included 18 blood chemistry observations along with complete claims data for all medical expenses.

We employed multivariable logistic regression for serum chemistry values significantly associated with in-patient hospital costs exceeding $3,000 in any single month and contrasted those results to other models by ROC area curves.

Results

The linear combination of weighted Z scores for parathyroid hormone, phosphorus, and albumin correlated with in-patient hospital care at p < 0.005. ROC curves derived from weighted variables of age, eGFR, hemoglobin, albumin, creatinine, and alanine aminotransferase demonstrated significance over models based on non-weighted Z scores for those same variables or CKD stage alone. In contrast, the linear combination of weighted PTH, PO4 and albumin demonstrated better prediction, but not significance over non-weighted Z scores for PTH alone.

Conclusion

Further study is justified to explore indices that predict costly hospitalization. Such metrics could assist Accountable Care Organizations in evaluating risk adjusted compensation for providers.