[When machines estimate kidney function and predict risk: Clinical applications of machine learning].

Authors

Antoine Lanot, Annabel Boyer, Nans Florens, Olivier Aubert, Aghiles Hamroun, Vincent Bisaccia

Published in

Nephrologie & therapeutique. Volume 22. Issue 6. Pages 1-14. Oct 27, 2026. Epub Oct 27, 2026.

Abstract

The use of artificial intelligence, and particularly machine learning, is rapidly expanding in medicine. In nephrology, these approaches have generated growing interest owing to the availability of large clinical, biological, and administrative datasets, as well as the need for more accurate assessment of kidney function and changes over time. Two major areas of application have emerged: estimation of glomerular filtration rate (GFR) and prediction of chronic kidney disease (CKD) progression. Initial studies focused on improving GFR estimation through supervised learning algorithms such as artificial neural networks, random forests, and ensemble methods. Although several studies reported encouraging results, recent large multicenter studies suggest that machine learning provides only marginal improvements over modern equations such as EKFC or CKD-EPI when the same clinical and biological variables are used. These findings indicate that current limitations in GFR estimation are more likely attributable to the information provided by available biomarkers than to the predictive capacity of the algorithms themselves. In contrast, machine learning appears particularly well suited for predicting kidney disease progression. By integrating numerous clinical and laboratory variables, these models can identify patients at high risk of rapid kidney function decline or kidney failure. Nevertheless, only a limited number of models have demonstrated a clear clinical advantage over established prediction tools such as the Kidney Failure Risk Equation (KFRE). This review summarizes current applications of machine learning for GFR estimation and CKD progression prediction, discusses their strengths and limitations, and highlights future directions for their integration into nephrology practice.

PMID:
42937233
Bibliographic data and abstract were imported from PubMed on 27 Oct 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.