study_acronym_array

Rationale & Objective: Creatinine-based estimated glomerular filtration rate (eGFR) equations are widely used in clinical practice but exhibit inherent limitations. We developed and validated machine learning models to assess the trustworthiness (i.e. the ability of equations to estimate measured GFR (mGFR) within 10, 20% or 30%) of the European Kidney Function Consortium (EKFC) equation.
Study design: Observational study
Setting & Participants: Data from European and US cohorts, comprising 22,343 participants of all ages with available mGFR results were utilized.
Predictors: Creatinine, age, sex, height, weight, body mass index, EKFC.
Outcome: Probability that EKFC falls within 30% of mGFR.
Analytical Approach: Four machine learning and two traditional logistic regression models were trained on a cohort of 8,455 participants to predict whether the EKFC creatinine-derived eGFR fell within 30% (P30), 20% (P20) or 10% (P10) of the mGFR value. The algorithms were internally and then externally validated on cohorts of respectively 3,781 and 10,107 participants. 
Results: The random forest model proved to be the most robust model. In the external validation cohort, the model achieved an area under the curve (AUC) of 0.652 (95%CI 0.637;0.667) and an accuracy of 0.851 (95%CI 0.844;0.858) for the P30 criterion. Sensitivity was 0.989 (95%CI 0.987;0.991) and specificity was 0.06 (95%CI 0.049; 0.07) at the 50% probability level that EKFC is within 30% of mGFR. A strategy of using the EKFC equation or mGFR according to the trustworthiness assessed by the random forest model yielded a global P30 of 86.1%, not significantly better than the EKFC P30 of 85.2%.
Limitations: Observational study, creatinine as the only biomarker. No inclusion of Black participants.
Conclusion: A strategy using machine learning model did not significantly improve GFR assessment compared to using the EKFC equation alone.

Enhancing individual glomerular filtration rate assessment: can we trust the equation?

Background.  Creatinine-based equations are the most used to estimate glomerular filtration rate( eGFR) . The Chronic Kidney Disease Epidemiology Collaboration( CKD-EPI) , the re-expressed Lund-MalmöRevised( r-LMR) and the European Kidney Function Consortium( EKFC) equations are the most validated. The EKFC and r-LMR equations have been suggested to have better performances in young adults, but this is debated. 
Methods. We collected data( GFR) measured by clearance of an exogenous marker( reference method) , serum creatinine, age and sex from 2366 young adults( aged between 18 and 25 years) both from Europe and the USA. 
Results. In the European cohorts( n = 1892) , the bias( in mL/min/1.73 m²) was systematically better for the EKFC and r-LMR equations compared with the CKD-EPI equation [2.28, 95% confidence interval( 1.59; 2.91) , –2.50( –3.85; –1.76) , 17.41 ( 16.49; 18.47) , respectively]. The percentage of estimated GFR within 30% of measured GFR( P30) was also better for EKFC and r-LMR equations compared with the CKD-EPI equation [84.4%( 82.8; 86.0) , 87.2%( 85.7; 88.7) and 65.4%( 63.3; 67.6) , respectively]. In the US cohorts( n = 474) , the bias for the EKFC and r-LMR equations was better than for the CKD-EPI equation in the non-Black population [0.97( –1.69; 3.06) , –2.62( –5.14; –1.43) and 7.74( 5.97; 9.63) , respectively], whereas the bias was similar in Black US individuals. P30 results were not different between the three equations in US cohorts. Analyses in sub-populations confirmed these results, except in individuals with high GFR levels( GFR ≥120 mL/min/1.73 m²) for whom the CKD-EPI equation might have a lower bias. 
Conclusions. We demonstrated that both the EKFC and r-LMR creatinine-based equations have a better performance than the CKD-EPI equation in a young population. The only exception might be in patients with hyperfiltration.

Estimating glomerular filtration in young people

The new creatinine-based European Kidney Function Consortium (EKFC) is used to estimate glomerular filtration rate (GFR). This equation has been developed and validated mainly in European subjects. This equation is based on rescaled creatinine, with the rescaling factor (Q-value) defined as the median normal value of serum creatinine in a given population. The validation was limited in Black and non-Black Americans. In this cross-sectional analysis, we included 12,854 participants from 9 studies with measured GFR by clearance of an exogenous marker (reference method), serum creatinine, age, sex, and self-reported race available. Two strategies were considered with population specific Q-values in Black and non-Black men and women (EKFCPS) or a race-free Q value (EKFCRF). In the whole population, only the EKFCPS equation showed no statistical bias (0.14 95%CI[-0.07;0.35] mL/min/1.73m²), and the statistical bias of the EKFCRF (0.74 95%CI[0.51;0.94] mL/min/1.73m²) was closer to zero than that of the CKD-EPI2021 equation (1.22 95%CI[0.99;1.47]) mL/min/1.73m²]. The percentage of estimated GFR within 30% of measured GFR was similar for CKD-EPI2021 (79.2% [78.5%-79.9%]) and EKFCRF (80.1% [79.4%-80.7%]), but improved with the EKFCPS equation (81.1% [80.5%-81.8%]). The EKFC-equation can be used to estimate GFR in the USA incorporating either self-reported race or unknown race at the patient’s discretion per hospital registration records.

Title	PMID	Public Release Type	Publication Year	DOI	Study Acronym	Request ID(s)	Public Release Origin
Enhancing individual glomerular filtration rate assessment: can we trust the equation?	https://pubmed.ncbi.nlm.nih.gov/39885391/	Journal	2025	10.1186/s12882-025-03972-0	MDRD, PERL, DCCT/EDIC, AASK Trial, ALTOLD, AASK Cohort, CRIC, CRISP	23649	Secondary Research
Estimating glomerular filtration in young people	39314869	Journal	2024	https:/doi.org/10.1093/ckj/sfae261	MDRD, PERL, AASK Trial, DCCT/EDIC, AASK Cohort, CRISP, CRIC, ALTOLD	23649	Secondary Research
Performance of the European Kidney Function Consortium (EKFC) creatinine-based equation in American cohorts	38101514	Journal	2023	10.1016/j.kint.2023.11.024	AASK Trial, MDRD, DCCT/EDIC, PERL, ALTOLD, CRISP, CRIC, AASK Cohort	23649	Secondary Research

Study Acronym

Public Release Type

Study Acronym

Public Release Origin