# Prediction of estimated glomerular filtration rate slope and kidney prognosis of patients with chronic kidney disease

## TL;DR

This paper introduces a machine learning model to predict kidney disease progression using eGFR slope, improving early detection and care in primary settings.

## Contribution

A novel machine learning model (LightGBM) for predicting eGFR slope with high accuracy, implemented as a web-based clinical tool.

## Key findings

- The LightGBM model outperformed LSTM and linear regression in predicting eGFR slope (RMSE = 2.95 mL/min/1.73 m²/year).
- The model enables real-time prediction using single time-point data, aiding early identification of high-risk CKD patients.

## Abstract

Chronic kidney disease (CKD) is a significant global health challenge, yet the application of eGFR slope as a metric for CKD progression remains underdeveloped in primary care settings. Using data from J-CKD-DB-Ex, Japan’s largest CKD database, we developed and validated a machine learning-based model to predict eGFR slope. The study included 10,474 patients aged ≥ 18 years with eGFR < 60 mL/min/1.73 m² or proteinuria at baseline. The median age of participants was 69.0 years [IQR: 62.0–77.0], and 52% (5,493/10,474) of the cohort were male. The Median baseline eGFR was 52.7 mL/min/1.73 m² [IQR: 44.7–57.8]. Predictors included demographic, clinical, and laboratory data. We compared three models: linear regression, LightGBM, and LSTM networks. Among 10,474 patients (median age 69.0 years), the LightGBM model achieved superior performance (RMSE = 2.95 mL/min/1.73 m²/year) compared to LSTM (RMSE = 3.94) and conventional linear regression (RMSE = 15.87). The model was implemented as a web-based application for clinical use. This machine learning-based prediction model achieves superior accuracy in estimating eGFR trajectory and enables real-time prediction using single time-point data. The web-based tool supports early identification of high-risk patients, enabling timely interventions and specialist referrals in primary care settings.

The online version contains supplementary material available at 10.1038/s41598-026-38246-8.