How much better can we predict dialysis patient survival using clinical data
Department of Quantitative Health Sciences
Medical Subject Headings
Adult; Diagnosis-Related Groups; Female; Humans; Kidney Failure, Chronic; Male; Medicare; Prognosis; Proportional Hazards Models; Registries; Renal Dialysis; Risk; *Survival Analysis; Survivors; United States
Biostatistics | Epidemiology | Health Services Research
OBJECTIVE: To use three approaches to compare dialysis survival prediction based on variables included in the Standardized Mortality Ratio (SMR) with prediction based on a clinically enriched set of variables.
DATA SOURCE: The United States Renal Data System Case Mix Severity data set containing demographic, clinical, functional, nutritional, and treatment details about a random sample of 4,797 adult dialysis patients from 291 treatment units, incident to dialysis in 1986 and 1987.
STUDY DESIGN: This observational study uses baseline patient characteristics in two proportional hazards survival models: the BASE model incorporates age, race, sex, and cause of end-stage renal disease (ESRD); the FULL model includes these and additional clinical information. We compare each model's performance using (1) the c-index, (2) observed median survival in strata of predicted risk, and (3) predicted survival for patients with different characteristics.
PRINCIPAL FINDINGS: The FULL model's c-index (0.709, 0.708-0.711) is significantly higher than that of the BASE model (0.675, 0.675-0.676), indicating better discrimination. Second, the sickest patients identified by the FULL model were in fact sicker than those identified as sickest by the BASE model, with observed median survival of 451 days versus 524. Third, survival predictions for sickest patients using the FULL model are one-third shorter than those based on the BASE model.
CONCLUSIONS: The model with more detailed clinical information predicted survival better than the BASE model. Clinical characteristics enable more accurate predictions, particularly for the sickest patients. Thus, clinical characteristics should be considered when making quality assessments for dialysis patients.
Rights and Permissions
Citation: Health Serv Res. 1999 Apr;34(1 Pt 2):365-75. Link to article on publisher's site
Mesler, Douglas E.; Byrne-Logan, Susan; McCarthy, Ellen P.; Ash, Arlene S.; and Moskowitz, Mark A., "How much better can we predict dialysis patient survival using clinical data" (1999). Quantitative Health Sciences Publications and Presentations. 686.