Key result
Parsimonious routine-data model outperforms the CRIC tool for 5-year major cardiovascular events prediction across cohorts.
Why the study?
Accurate CV risk prediction tools may improve monitoring, use of evidence-based therapies, and shared decision making in CKD. This study sought to develop and externally validate a risk prediction model for incident and recurrent CV events across CKD stages using commonly available demographics and laboratory data.
Can a risk prediction model using routinely available administrative and laboratory data accurately predict 5-year MACE and MACE+ across all stages of CKD compared with existing models?
Cohort (n=214,508)
Yes
Can a risk prediction model using routinely available administrative and laboratory data accurately predict 5-year MACE and MACE+ across all stages of CKD compared with existing models?
A 10-variable prediction model using routine administrative and laboratory records accurately predicts 5-year MACE and MACE+ across CKD stages G1-G4 in both primary and secondary prevention patients, enabling automated EHR risk stratification.
Answers are grounded in this paper and cite their sources.
May support automated MACE prediction in CKD via routine data; extends CRIC but requires prospective validation before adoption.
Background: Accurate cardiovascular (CV) risk prediction tools may heighten awareness and monitoring, improve the use of evidence-based therapies and help inform shared decision making for patients with chronic kidney disease (CKD). The purpose of this study was to develop and externally validate a risk prediction model for incident and recurrent CV events across all stages of CKD using commonly available demographics and laboratory data. Methods: A series of models were developed using administrative and laboratory data (n=36,317) from Manitoba, Canada, between April 1, 2006, and December 31, 2018, with external validation in health system's data from Alberta, Canada (n=95,191), and Stockholm, Sweden (n=83,000). Adults with incident CKD stages G1-G4 were followed for the occurrence of major adverse cardiovascular events (MACE) (myocardial infraction, stroke, and CV death), and MACE including hospitalization for heart failure (MACE+). Discrimination and calibration were evaluated using the area under the receiver operating characteristic curve (AUC), Brier scores, and plots of observed vs predicted risk, and the models were compared to an existing model from the Chronic Renal Insufficiency Cohort (CRIC). Results: In the Alberta cohort, the AUCs for predicting MACE and MACE+ were 0.77 (0.77-0.77) and 0.80 (0.79-0.80), respectively. In the Stockholm cohort, the model achieved an AUC of 0.87 (0.86-0.87) for predicting MACE and 0.88 (0.88-0.88) for MACE+. Overall performance was improved relative to CRIC. Conclusions: A model including commonly available administrative data and laboratory results can predict the risk of MACE and MACE+ outcomes among individuals with CKD.
No takes yet. Share an insight, caveat, or question.
Tangri et al. (2025) conducted a cohort in Chronic kidney disease (CKD stages G1-G4) (n=214,508). Parsimonious CKD cardiovascular risk prediction model (age, sex, eGFR, urine ACR, serum hemoglobin, history of MI, HF, stroke, diabetes, and hypertension) vs. Chronic Renal Insufficiency Cohort (CRIC) clinical model and original SCORE + CKD Patch algorithm was evaluated on 5-year prediction of MACE (composite of myocardial infarction, stroke, and cardiovascular-related death) and MACE+ (MACE plus hospitalization for heart failure) (AUC 0.77 (Alberta) and AUC 0.87 (Stockholm) for MACE; AUC 0.80 (Alberta) and AUC 0.88 (Stockholm) for MACE+, 95% CI 0.77-0.77 (Alberta MACE); 0.86-0.87 (Stockholm MACE), p=<0.001). A parsimonious model using routine administrative and laboratory data predicted 5-year major cardiovascular events with AUCs of 0.77 in Alberta and 0.87 in Stockholm, and major cardiovascular events+ with AUCs of 0.80 and 0.88, outperforming the CRIC model.
Synapse has enriched 10 related papers. Consider them for comparative context: