Comparison between the EKFC-equation and machine learning models to predict Glomerular Filtration Rate
(2024) In Scientific Reports 14(1).- 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... (More)
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.
(Less)
- author
- organization
-
- Centre for Economic Demography
- EPI@BIO (research group)
- Division of Occupational and Environmental Medicine, Lund University
- eSSENCE: The e-Science Collaboration
- EpiHealth: Epidemiology for Health
- Cystatin C, renal disease, amyloidosis and antibiotics (research group)
- Radiology Diagnostics, Malmö (research group)
- LUCC: Lund University Cancer Centre
- publishing date
- 2024-12
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Scientific Reports
- volume
- 14
- issue
- 1
- article number
- 26383
- publisher
- Nature Publishing Group
- external identifiers
-
- pmid:39487227
- scopus:85208291511
- ISSN
- 2045-2322
- DOI
- 10.1038/s41598-024-77618-w
- language
- English
- LU publication?
- yes
- id
- 4e454f59-a25f-42af-9839-71cd2c6de280
- date added to LUP
- 2025-01-08 13:50:23
- date last changed
- 2025-07-10 05:23:12
@article{4e454f59-a25f-42af-9839-71cd2c6de280, abstract = {{<p>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.</p>}}, author = {{Nakano, Felipe Kenji and Åkesson, Anna and de Boer, Jasper and Dedja, Klest and D’hondt, Robbe and Haredasht, Fateme Nateghi and Björk, Jonas and Courbebaisse, Marie and Couzi, Lionel and Ebert, Natalie and Eriksen, Björn O. and Dalton, R. Neil and Derain-Dubourg, Laurence and Gaillard, Francois and Garrouste, Cyril and Grubb, Anders and Jacquemont, Lola and Hansson, Magnus and Kamar, Nassim and Legendre, Christophe and Littmann, Karin and Mariat, Christophe and Melsom, Toralf and Rostaing, Lionel and Rule, Andrew D. and Schaeffner, Elke and Sundin, Per Ola and Bökenkamp, Arend and Berg, Ulla and Åsling-Monemi, Kajsa and Selistre, Luciano and Larsson, Anders and Nyman, Ulf and Lanot, Antoine and Pottel, Hans and Delanaye, Pierre and Vens, Celine}}, issn = {{2045-2322}}, language = {{eng}}, number = {{1}}, publisher = {{Nature Publishing Group}}, series = {{Scientific Reports}}, title = {{Comparison between the EKFC-equation and machine learning models to predict Glomerular Filtration Rate}}, url = {{http://dx.doi.org/10.1038/s41598-024-77618-w}}, doi = {{10.1038/s41598-024-77618-w}}, volume = {{14}}, year = {{2024}}, }