Development and Validation of a Prediction Model for Future Estimated Glomerular Filtration Rate in People With Type 2 Diabetes and Chronic Kidney Disease
Authors' conclusion
In this prognostic study, a reliable prediction model was developed and externally validated; the robust model was well calibrated and capable of predicting kidney function decline up to 5 years after baseline. The results and prediction model are publicly available in an accompanying web-based application, which may open the way for improved prediction of individual eGFR trajectories and disease progression.
Study context
- Population
- Adults aged 18–75 years with T2D and CKD (baseline estimated glomerular filtration rate (eGFR) ≥30 mL/min/1.73 m²); mean age 63.5 years, 57.8% men, all White
- Participants
- 4,637 adults3 cohorts
- Comparison
- Development vs Validation
- Developmentn = 3,323
- Validationn = 1,314
- Outcome
- Repeated eGFR measurements predicted from 13 routine clinical variables
- Follow-up
- Up to 5 years after baseline
Methodological detailsprediction model development and external validation, 3 prospective multinational cohorts, linear mixed-effects model, Data collected February 2010 to December 2019; analysed June 30, 2021, to January 31, 2023
- Prediction model development and external validation
- 3 prospective multinational cohorts
- Linear mixed-effects model
- Data collected February 2010 to December 2019; analysed June 30, 2021, to January 31, 2023
Performance
As reported in the abstract
Calibration slope at 5 years (after updating with baseline eGFR)
1.09
95% CI 1.04–1.15
Lowest C statistic, at 5 years
0.79
95% CI 0.77–0.80
R2 at year 1
0.70
95% CI 0.63–0.76
R2 at year 5
0.58
95% CI 0.53–0.63
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →