Faculty Collaboration Database

Inclusion of dynamic clinical data improves the predictive performance of a 30-day readmission risk model in kidney transplantation. Transplantation 2015 Feb;99(2):324-30

Date

01/17/2015

Pubmed ID

25594549

Pubmed Central ID

PMC4369585

DOI

10.1097/TP.0000000000000565

Scopus ID

2-s2.0-84923067620 (requires institutional sign-in at Scopus site)   29 Citations

Abstract

BACKGROUND: Thirty-day readmissions (30DRA) are a highly scrutinized measure of healthcare quality and relatively frequent among kidney transplants (KTX). Development of predictive risk models is critical to reducing 30DRA and improving outcomes. Current approaches rely on fixed variables derived from administrative data. These models may not capture clinical evolution that is critical to predicting outcomes.

METHODS: We directed a retrospective analysis toward: (1) developing parsimonious risk models for 30DRA and (2) comparing efficiency of models based on the use of immutable versus dynamic data. Baseline and in-hospital clinical and outcomes data were collected from adult KTX recipients between 2005 and 2012. Risk models were developed using backward logistic regression and compared for predictive efficacy using receiver operating characteristic curves.

RESULTS: Of 1147 KTX patients, 123 had 30DRA. Risk factors for 30DRA included recipient comorbidities, transplant factors, and index hospitalization patient level clinical data. The initial fixed variable model included 9 risk factors and was modestly predictive (area under the curve, 0.64; 95% confidence interval [95% CI], 0.58-0.69). The model was parsimoniously reduced to 6 risks, which remained modestly predictive (area under the curve, 0.63; 95% CI, 0.58-0.69). The initial predictive model using 13 fixed and dynamic variables was significantly predictive (AUC, 0.73; 95% CI, 0.67-0.80), with parsimonious reduction to 9 variables maintaining predictive efficacy (AUC, 0.73; 95% CI, 0.67-0.79). The final model using dynamically evolving clinical data outperformed the model using static variables (P=0.009). Internal validation demonstrated that the final model was stable with minimal bias.

CONCLUSIONS: We demonstrate that modeling dynamic clinical data outperformed models using immutable data in predicting 30DRA.

Author List

Taber DJ, Palanisamy AP, Srinivas TR, Gebregziabher M, Odeghe J, Chavin KD, Egede LE, Baliga PK

Author

Leonard E. Egede MD Center Director, Chief, Professor in the Medicine department at Medical College of Wisconsin

MESH terms used to index this publication - Major topics in bold

Adult
Aged
Area Under Curve
Biomarkers
Blood Pressure
Cross-Sectional Studies
Decision Support Techniques
Female
Health Care Costs
Humans
Immunosuppressive Agents
Kidney Transplantation
Length of Stay
Linear Models
Logistic Models
Male
Middle Aged
Multivariate Analysis
Patient Readmission
Postoperative Complications
Predictive Value of Tests
ROC Curve
Reproducibility of Results
Retrospective Studies
Risk Assessment
Risk Factors
Time Factors
Treatment Outcome