Key result
Existing prediction models for hospitalization in advanced chronic kidney disease were of low quality, and a newly developed model demonstrated poor discrimination with a C-statistic of 0.55, highlighting the difficulty of predicting this outcome.
Why the study?
Hospitalization is common in advanced CKD, and predicting hospitalization and related outcomes would be beneficial, but an overview, external validation, and valid prediction models were needed.
Systematic Review
Yes
Existing prediction models for hospitalization in advanced CKD are of low quality and perform poorly, and a newly developed model also failed to predict reliably, highlighting the need for more specific outcomes and predictors.
Existing models for hospitalization in advanced CKD lack validity; leaves open need for reliable tools before clinical adoption.
Rationale & Objective Hospitalization is common in patients with advanced chronic kidney disease (CKD). Predicting hospitalization and related outcomes would be beneficial for hospitals and patients. Therefore, we aimed to (1) give an overview of current prediction models for hospitalization, length of stay, and readmission in patients with advanced CKD; (2) externally validate these models; and (3) develop a new model if no valid models were identified. Study Design Systematic review, development, and external validation study. Setting & Participants We were interested in prediction models of hospitalization, length of stay, or readmission for patients with advanced CKD. Our available development and validation data consisted of hemodialysis, peritoneal dialysis, and advanced CKD patients not receiving dialysis from a Dutch dialysis and European advanced CKD cohort. Selection Criteria for Studies We systematically searched PubMed. Studies had to intentionally develop, validate, or update a prediction model in adults with CKD. Analytical Approach We used the PROBAST for risk of bias assessment. Identified models were externally validated on model discrimination (C-statistic) and calibration (calibration plot, slope, and calibration-in-the-large). We developed a Fine-Gray model for hospitalization within 1 year in patients initiating hemodialysis, accounting for the competing risk of death. Results We identified 45 models in 8 studies. The majority were of low quality with a high risk of bias. Due to underreporting and population-specific predictors, we could only validate 3 models. These were poorly calibrated and had poor discrimination. Using multiple modeling strategies, an adequate new model could not be developed. Limitations The outcome hospitalization might be too heterogeneous, and we did not have all relevant predictors available. Conclusions Hospitalizations are important but difficult to predict for patients with advanced CKD. An improved prediction model should be developed, for example, using a more specific outcome (eg, cardiovascular hospitalizations) and more predictors (eg, patient-reported outcome measures). Plain-Language Summary Hospitalizations often occur in patients with advanced chronic kidney disease. By predicting hospitalization and related outcomes, patients can better prepare for the future and cope with their disease. Therefore, we searched existing literature for existing methods to predict hospitalizations and related outcomes. Although many algorithms exist, they are often not available for use or are not reliable. We then developed our own algorithm to predict hospitalization in the coming year. However, it also did not predict reliably. In this study, we summarize what failed in existing prediction algorithms, what we learned from predicting hospitalization ourselves, and how to proceed to allow reliable predictions of hospitalizations.
No takes yet. Share an insight, caveat, or question.
Janse et al. (2025) conducted a systematic review in Advanced chronic kidney disease. Prediction models for hospitalization was evaluated on Hospitalization within 1 year (model discrimination) (C-statistic 0.55, 95% CI 0.53-0.58). Existing prediction models for hospitalization in advanced chronic kidney disease were of low quality, and a newly developed model demonstrated poor discrimination with a C-statistic of 0.55, highlighting the difficulty of predicting this outcome.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: