Open Access Green: Postprint online verfügbar 09/2022 möglich sobald bei der ZB eingereicht worden ist.
A predictive model for progression of CKD to kidney failure based on routine laboratory tests.
Am. J. Kidney Dis., DOI: 10.1053/j.ajkd.2021.05.018 (2021)
DOI Verlagsversion bestellen
RATIONALE & OBJECTIVE: Stratification of chronic kidney disease (CKD) patients at risk for progressing to end-stage kidney disease (ESKD) requiring kidney replacement therapy (KRT) is important for clinical decision-making and trial enrollment. STUDY DESIGN: Four independent prospective observational cohort studies. SETTING & PARTICIPANTS: The development cohort was comprised of 4,915 CKD patients and three independent validation cohorts were comprised of a total of 3,063. Patients were followed-up for approximately five years. NEW PREDICTORS & ESTABLISHED PREDICTORS: 22 demographic, anthropometric and laboratory variables commonly assessed in CKD patients. OUTCOMES: Progression to ESKD requiring KRT. ANALYTICAL APPROACH: A Least Absolute Shrinkage and Selection Operator (LASSO) Cox proportional hazards model was fit to select laboratory variables that best identified patients at high risk for ESKD. Model discrimination and calibration were assessed and compared against the 4-variable Tangri (T4) risk equation. Both used a resampling approach within the development cohort and in the validation cohorts using cause-specific concordance (C) statistics, net reclassification improvement, and calibration graphs. RESULTS: The newly derived 6-variable (Z6) risk score included serum creatinine, albumin, cystatin C and urea, as well as hemoglobin and the urine albumin-to-creatinine ratio. Based on the resampling approach, Z6 achieved a median C value of 0.909 (95% CI, 0.868-0.937) at two years after the baseline visit, whereas the T4 achieved a median C value of 0.855 (95% CI, 0.799-0.915). In the three independent validation cohorts, Z6 C values were 0.894, 0.921, and 0.891, whereas the T4 C values were 0.882, 0.913, and 0.862. LIMITATIONS: The Z6 was both derived and tested only in White European cohorts. CONCLUSIONS: A new risk equation, based on six routinely available laboratory tests facilitates identification of patients with CKD who are at high risk of progressing to ESKD.
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter German Chronic Kidney Disease Study ; Chronic Kidney Disease ; Kidney Failure Requiring Kidney Replacement Therapy ; Machine Learning ; Risk Equation
ISSN (print) / ISBN 0272-6386
Zeitschrift American Journal of Kidney Diseases
Begutachtungsstatus Peer reviewed
Institut(e) Institute of Computational Biology (ICB)