Machine learning for prediction of chronic kidney disease progression: Validation of the Klinrisk model in the CANVAS Program and CREDENCE trial
Diabetes, Obesity and Metabolism · 2024-08 · 26 (8) · 3371-3380
DOI: 10.1111/dom.15678 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Diabetes, Obesity and Metabolism, online erschienen am 28.05.2024. Verfasst von Navdeep Tangri und 10 weiteren Autor:innen. Beteiligte Einrichtung: Chronic Disease Innovation Centre, Seven Oaks General Hospital, Winnipeg, Canada. Hauptthemen laut MEDLINE: Machine Learning, Disease Progression, Renal Insufficiency, Chronic, Diabetes Mellitus, Type 2. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Aim
To validate the Klinrisk machine learning model for prediction of chronic kidney disease (CKD) progression in patients with type 2 diabetes in the pooled CANVAS/CREDENCE trials. Materials and Methods We externally validated the Klinrisk model for prediction of CKD progression, defined as 40% or higher decline in estimated glomerular filtration rate (eGFR) or kidney failure. Model performance was assessed for prediction up to 3 years with the area under the receiver operating characteristic curve (AUC), Brier scores and calibration plots of observed and predicted risks. We compared performance of the model with standard of care using eGFR (G1‐G4) and urine albumin‐creatinine ratio (A1‐A3) Kidney Disease Improving Global Outcomes (KDIGO) heatmap categories.
Results
The Klinrisk model achieved an AUC of 0.81 (95% confidence interval [CI] 0.78‐0.83) at 1 year, and 0.88 (95% CI 0.86‐0.89) at 3 years. The Brier scores were 0.020 (0.018‐0.022) and 0.056 (0.052‐0.059) at 1 and 3 years, respectively. Compared with the KDIGO heatmap, the Klinrisk model had improved performance at every interval ( P < .01).
Conclusions
The Klinrisk machine learning model, using routinely collected laboratory data, was highly accurate in its prediction of CKD progression in the CANVAS/CREDENCE trials. Integration of the model in electronic medical records or laboratory information systems can facilitate risk‐based care.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Chronic Disease Innovation Centre, Seven Oaks General Hospital, Winnipeg, Canada.
- Department of Medicine, University of Manitoba, Winnipeg, Canada.
- The George Institute for Global Health, University of New South Wales, Sydney, Australia.
- Department of Cardiology, Royal Prince Alfred Hospital, Sydney, Australia.
- Department of Medicine, Stanford University, Stanford, California, USA.
- Department of Nephrology, Prince of Wales Hospital, Sydney, Australia.
ORCID-Profile: Ryan J Bamforth, Clare Arnott, Hiddo J L Heerspink, Brendon L Neuen
Zitieren
APA
Tangri, N., Ferguson, T. W., Bamforth, R. J., Leon, S. J., Arnott, C., Mahaffey, K. W., Kotwal, S., Heerspink, H. J. L., Perkovic, V., Fletcher, R. A., & Neuen, B. L. (2024). Machine learning for prediction of chronic kidney disease progression: Validation of the Klinrisk model in the CANVAS Program and CREDENCE trial. Diabetes, Obesity and Metabolism, 26(8), 3371-3380. https://doi.org/10.1111/dom.15678
Vancouver
Tangri N, Ferguson TW, Bamforth RJ, Leon SJ, Arnott C, Mahaffey KW, et al. Machine learning for prediction of chronic kidney disease progression: Validation of the Klinrisk model in the CANVAS Program and CREDENCE trial. Diabetes, Obesity and Metabolism. 2024;26(8):3371-3380. doi:10.1111/dom.15678
BibTeX
@article{Tangri2024,
author = {Tangri, Navdeep and Ferguson, Thomas W and Bamforth, Ryan J and Leon, Silvia J and Arnott, Clare and Mahaffey, Kenneth W and Kotwal, Sradha and Heerspink, Hiddo J L and Perkovic, Vlado and Fletcher, Robert A and Neuen, Brendon L},
title = {Machine learning for prediction of chronic kidney disease progression: Validation of the Klinrisk model in the CANVAS Program and CREDENCE trial},
journal = {Diabetes, Obesity and Metabolism},
year = {2024},
volume = {26},
number = {8},
pages = {3371--3380},
doi = {10.1111/dom.15678}
}
EUVIMED