Development of a machine learning model for precision prognosis of rapid kidney function decline in people with diabetes and chronic kidney disease
Authors' conclusion
The XGBoost model, augmented by copula simulation, successfully stratified kidney prognosis in individuals with T2D and CKD.
Study context
- Population
- Individuals with T2D and Chronic Kidney Disease (CKD) at Seoul National University Hospital
- Participants
- 6,924 individuals
- Outcome
- Rapid kidney function decline, assessed by eGFR slopes
Methodological detailsmachine learning prediction model (XGBoost), copula simulation, single-centre
- Machine learning prediction model (XGBoost)
- Copula simulation
- Single-centre
Main finding
As reported in the abstract
Prediction of rapid kidney function decline by XGBoost model
Rapid kidney function decline
906
13.1 %
XGBoost AUC
0.826
Observational data: associations, not effects.
Further findings
End-stage kidney disease by risk quartile · within eight years
| HR (95 % CI) | ||
|---|---|---|
| Q3 | 2.06 (1.29–3.29) | |
| Q4 | 10.9 (7.36–16.2) | |
| 0.050.21520Hazard ratio (log scale) |
- Hazard increased across risk quartiles
High-risk subgroups by copula simulation
- Stage A3 albuminuria plus ≥2 of: haematocrit < 39.0 %, systolic BP > 120 mmHg, HbA1c > 6.5 %
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Development of a machine learning model for precision prognosis of rapid kidney function decline in people with diabetes and chronic kidney disease. Diabetes Res Clin Pract. Published 19 October 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →