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

Journal: Scientific reports
PMID: 39487227

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.

Authors

  • Felipe Kenji Nakano
    KU Leuven, Campus KULAK - Department of Public Health and Primary Care, Etienne Sabbelaan 53, Kortrijk, 8500, Belgium. felipekenji.nakano@kuleuven.be.
  • Anna Åkesson
    Clinical Studies Sweden - Forum South, Skåne University Hospital, Lund, Sweden.
  • Jasper de Boer
    Department of Public Health and Primary Care, KU Leuven Campus Kulak Kortrijk, Kortrijk, Belgium.
  • Klest Dedja
    Department of Public Health and Primary Care, KU Leuven Campus Kulak Kortrijk, Kortrijk, Belgium.
  • Robbe D'hondt
    Department of Public Health and Primary Care, KU Leuven Campus Kulak Kortrijk, Kortrijk, Belgium.
  • Fateme Nateghi Haredasht
    Department of Public Health and Primary Care, KU Leuven Campus Kulak Kortrijk, Kortrijk, Belgium.
  • Jonas Björk
    Department of Clinical Sciences, Lund University, Sweden.
  • Marie Courbebaisse
    Physiology Department, Georges Pompidou European Hospital, Assistance Publique Hôpitaux de Paris, INSERM U1151-CNRS UMR8253, Paris Descartes University, Paris, France.
  • Lionel Couzi
    CNRS-UMR 5164 Immuno ConcEpT, CHU de Bordeaux, Nephrologie-Transplantation-Dialyse, Université de Bordeaux, Bordeaux, France.
  • Natalie Ebert
    Institute of Public Health, Charité Universitätsmedizin Berlin, Berlin, Germany.
  • Björn O Eriksen
    Metabolic and Renal Research Group, UiT the Arctic University of Norway, Tromsö, Norway.
  • R Neil Dalton
    The Wellchild Laboratory, Evelina London Children's Hospital, London, UK.
  • Laurence Derain-Dubourg
    Néphrologie, Dialyse, Hypertension et Exploration Fonctionnelle Rénale, Hôpital Edouard Herriot, Hospices Civils de Lyon, France.
  • Francois Gaillard
    Renal Transplantation Department, Assistance Publique-Hôpitaux de Paris (AP-HP), Paris, France.
  • Cyril Garrouste
  • Anders Grubb
    Department of Clinical Chemistry, Skåne University Hospital, Lund University, Lund, Sweden.
  • Lola Jacquemont
    Renal Transplantation Department, CHU Nantes, Nantes University, Nantes, France.
  • Magnus Hansson
    Function Area Clinical Chemistry, Karolinska University Laboratory, Karolinska Institute, Karolinska University Hospital Huddinge and Department of Laboratory Medicine, Stockholm, Sweden.
  • Nassim Kamar
    Department of Nephrology and Organ Transplantation, CHU Rangueil, Toulouse, France.
  • Christophe Legendre
    Paris Translational Research Centre for Organ Transplantation, INSERM, PARCC, Université de Paris, Paris, France; Kidney Transplant Department, Necker Hospital, Assistance Publique - Hôpitaux de Paris, Paris, France.
  • Karin Littmann
    Institute om Medicine Huddinge (Med H), Karolinska Institute, Solna, Sweden.
  • Christophe Mariat
    Service de Néphrologie, Dialyse et Transplantation Rénale, Hôpital Nord, CHU de Saint-Etienne, Saint-Priest-en-Jarez, France.
  • Toralf Melsom
    Metabolic and Renal Research Group, UiT the Arctic University of Norway, Tromsö, Norway.
  • Lionel Rostaing
    Service de Néphrologie, Hémodialyse, Aphérèses et Transplantation Rénale, Hôpital Michallon, CHU Grenoble-Alpes, Tronche, France.
  • Andrew D Rule
    Division of Nephrology and Hypertension, Mayo Clinic, Rochester, MN, USA.
  • Elke Schaeffner
    Institute of Public Health, Charité Universitätsmedizin Berlin, Berlin, Germany.
  • Per-Ola Sundin
    Karla Healthcare Centre, Faculty of Medicine and Health, Örebro University, 70182, Örebro, SE, Sweden.
  • Arend Bökenkamp
    Department of Paediatric Nephrology, Emma Children's Hospital, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.
  • Ulla Berg
    Department of Clinical Science, Intervention and Technology, Division of Pediatrics, Karolinska Institutet, Karolinska University Hospital Huddinge, Stockholm, Sweden.
  • Kajsa Åsling-Monemi
    Department of Clinical Science, Intervention and Technology, Division of Pediatrics, Karolinska Institutet, Karolinska University Hospital Huddinge, Stockholm, Sweden.
  • Luciano Selistre
    Mestrado Em Ciências da Saúde-Universidade Caxias do Sul Foundation CAPES, Caxias Do Sul, Brazil.
  • Anders Larsson
    5 Hedenstierna Laboratory, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden.
  • Ulf Nyman
    Department of Translational Medicine, Division of Medical Radiology, Lund University, Malmö, Sweden.
  • Antoine Lanot
    Normandie Université, Unicaen, CHU de Caen Normandie, Néphrologie, Caen, France.
  • Hans Pottel
    Department of Public Health and Primary Care, KU Leuven Campus Kulak Kortrijk, Kortrijk, Belgium.
  • Pierre Delanaye
    Department of Nephrology-Dialysis-Transplantation, University of Liège (ULg CHU), CHU Sart Tilman, Liège, Belgium.
  • Celine Vens
    Department of Computer Science, KU Leuven, Leuven, Belgium.

Keywords

External Resources

Popular Topics
Recent Journals