Comparison between the EKFC-equation and machine learning models to predict Glomerular Filtration Rate

Abstract

In clinical practice, the glomerular filtration rate (GFR), a measurement of kidney functioning, is normally calculated using equations, such as the European Kidney Function Consortium (EKFC) equation. Despite being the most general equation, EKFC, just like previously proposed approaches, can still struggle to achieve satisfactory performance, limiting its clinical applicability. As a possible solution, recently machine learning (ML) has been investigated to improve GFR prediction, nonetheless the literature still lacks a general and multi-center study. Using a dataset with 19,629 patients from 13 cohorts, we investigate if ML can improve GFR prediction in comparison to EKFC. More specifically, we compare diverse ML methods, which were allowed to use age, sex, serum creatinine, cystatin C, height, weight and BMI as features, in internal and external cohorts against EKFC. The results show that the most performing ML method, random forest (RF), and EKFC are very competitive where RF and EKFC achieved respectively P10 and P30 values of 0.45 (95% CI 0.44;0.46) and 0.89 (95% CI 0.88;0.90), whereas EKFC yielded 0.44 (95% CI 0.43; 0.44) and 0.89 (95% CI 0.88; 0.90), considering the entire cohort. Small differences were, however, observed in patients younger than 12 years where RF slightly outperformed EKFC.

Fig. 1

Bias versus age for the SCr-based (left panel) and SCr/CysC-based (right panel) EKFC and RF models.

Fig. 2

P10/P30 accuracy versus age for the SCr-based (left panel) and SCr/CysC-based (right panel) EKFC and RF models.

Fig. 3

Bland–Altman plots for the SCr-based EKFC (left panel) and RF model (right panel).

Fig. 4

Bland–Altman plots for the SCr/CysC-based EKFC (left panel) and RF models (right panel).

Fig. 5

SHAP plot to show feature importance for the RF model. That is, serum creatinine and BMI are the most and the least relevant features, respectively. Feature values (e.g., higher or lower serum creatinine values) are represented using the colors blue and red, where blue values are associated with lower values and red with higher ones. The placement of the dots is related to their impact on the output. Dots to the left side of (x = 0) reduce the output and dots to the right increase the output.