EUVIMEDEUVIMED entdecken
Validierungsstudie

External validation of a 2-year all-cause mortality prediction tool developed using machine learning in patients with stage 4–5 chronic kidney disease

Dung N T Tran, Michel Ducher, Denis Fouque, Jean-Pierre Fauvel

Journal of Nephrology · 2024

DOI: 10.1007/s40620-024-02011-9 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Journal of Nephrology, 2024. Verfasst von Dung N T Tran und 3 weiteren Autor:innen. Beteiligte Einrichtung: Laboratoire de Biométrie et Biologie Évolutive, UMR 5558, CNRS Lyon, Université Claude Bernard Lyon 1, 43 Boulevard du 11 Novembre 1918, 69100, Lyon,…. Hauptthemen laut MEDLINE: Machine Learning, Renal Insufficiency, Chronic. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: Société Francophone de Dialyse et de Transplantation, Institut National de la Santé et de la Recherche Médicale, GlaxoSmithKline Biologicals.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Chronic kidney disease (CKD) is associated with increased mortality. Individual mortality prediction could be of interest to improve individual clinical outcomes. Using an independent regional dataset, the aim of the present study was to externally validate the recently published 2-year all-cause mortality prediction tool developed using machine learning. METHODS: A validation dataset of stage 4 or 5 CKD outpatients was used. External validation performance of the prediction tool at the optimal cutoff-point was assessed by the area under the receiver operating characteristic curve (AUC-ROC), accuracy, sensitivity, and specificity. A survival analysis was then performed using the Kaplan-Meier method. RESULTS: Data of 527 outpatients with stage 4 or 5 CKD were analyzed. During the 2 years of follow-up, 91 patients died and 436 survived. Compared to the learning dataset, patients in the validation dataset were significantly younger, and the ratio of deceased patients in the validation dataset was significantly lower. The performance of the prediction tool at the optimal cutoff-point was: AUC-ROC = 0.72, accuracy = 63.6%, sensitivity = 72.5%, and specificity = 61.7%. The survival curves of the predicted survived and the predicted deceased groups were significantly different (p < 0.001). CONCLUSION: The 2-year all-cause mortality prediction tool for patients with stage 4 or 5 CKD showed satisfactory discriminatory capacity with emphasis on sensitivity. The proposed prediction tool appears to be of clinical interest for further development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningRenal Insufficiency, ChronicHumansFemaleMaleAgedMiddle AgedCause of DeathROC CurveRisk AssessmentTime FactorsPredictive Value of TestsPrognosisSeverity of Illness IndexReproducibility of ResultsArea Under CurveRisk Factors

Stichwörter der Autor:innen

Chronic kidney diseaseMachine learningMortalityValidation prediction model

Autor:innen und Institutionen

  • Laboratoire de Biométrie et Biologie Évolutive, UMR 5558, CNRS Lyon, Université Claude Bernard Lyon 1, 43 Boulevard du 11 Novembre 1918, 69100, Lyon, Villeurbanne, France.
  • Service de Néphrologie, Hospices Civils de Lyon, Hôpital Edouard Herriot, 69003, Lyon, France.
  • EMR3738 Ciblage Thérapeutique en Oncologie, Université Claude Bernard Lyon 1, 43 Boulevard du 11 Novembre 1918, 69100, Lyon, Villeurbanne, France.
  • Dept Nephrology, Nutrition and Dialysis, Faculté de Médecine Lyon-Sud BP 12165 Chemin du Grand Revoyet, Université Claude Bernard Lyon 1, Carmen, 69921, Lyon, Oulllins, France.
  • Hôpital Lyon Sud, Hospices Civils de Lyon, 69495, Lyon, Pierre-Benite, France.
  • Laboratoire de Biométrie et Biologie Évolutive, UMR 5558, CNRS Lyon, Université Claude Bernard Lyon 1, 43 Boulevard du 11 Novembre 1918, 69100, Lyon, Villeurbanne, France. jean-pierre.fauvel@chu-lyon.fr.

Förderung

  • Société Francophone de Dialyse et de Transplantation
  • Institut National de la Santé et de la Recherche Médicale
  • GlaxoSmithKline Biologicals
  • AstraZeneca
  • Astellas Pharma Europe

Zitieren

APA

Tran, D. N. T., Ducher, M., Fouque, D., & Fauvel, J. P. (2024). External validation of a 2-year all-cause mortality prediction tool developed using machine learning in patients with stage 4–5 chronic kidney disease. Journal of Nephrology. https://doi.org/10.1007/s40620-024-02011-9

Vancouver

Tran DNT, Ducher M, Fouque D, Fauvel JP. External validation of a 2-year all-cause mortality prediction tool developed using machine learning in patients with stage 4–5 chronic kidney disease. Journal of Nephrology. 2024. doi:10.1007/s40620-024-02011-9

BibTeX
@article{Tran2024,
  author = {Tran, Dung N T and Ducher, Michel and Fouque, Denis and Fauvel, Jean-Pierre},
  title = {External validation of a 2-year all-cause mortality prediction tool developed using machine learning in patients with stage 4–5 chronic kidney disease},
  journal = {Journal of Nephrology},
  year = {2024},
  doi = {10.1007/s40620-024-02011-9}
}
Kostenlos starten →