EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of gastrointestinal bleeding hospitalization risk in hemodialysis using machine learning

John W Larkin, Suman Lama, Sheetal Chaudhuri, Joanna Willetts, Anke C Winter, Yue Jiao, Manuela Stauss-Grabo, Len A Usvyat, Jeffrey L Hymes, Franklin W Maddux, David C Wheeler, Peter Stenvinkel und 2 weitere

BMC Nephrology · 2024

DOI: 10.1186/s12882-024-03809-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BMC Nephrology, 2024. Verfasst von John W Larkin und 13 weiteren Autor:innen. Beteiligte Einrichtung: Fresenius Medical Care, Global Medical Office, 920 Winter Street, Waltham, MA, 02451, USA. John.Larkin@freseniusmedicalcare.com. Hauptthemen laut MEDLINE: Machine Learning, Renal Dialysis, Gastrointestinal Hemorrhage, Hospitalization. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fresenius Medical Care.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Gastrointestinal bleeding (GIB) is a clinical challenge in kidney failure. INSPIRE group assessed if machine learning could determine a hemodialysis (HD) patient’s 180-day GIB hospitalization risk.

Methods

An eXtreme Gradient Boosting (XGBoost) and logistic regression model were developed using an HD dataset in United States (2017–2020). Patient data was randomly split (50% training, 30% validation, and 20% testing). HD treatments ≤ 180 days before GIB hospitalization were classified as positive observations; others were negative. Models considered 1,303 exposures/covariates. Performance was measured using unseen testing data.

Results

Incidence of 180-day GIB hospitalization was 1.18% in HD population ( n = 451,579), and 1.12% in testing dataset ( n = 38,853). XGBoost showed area under the receiver operating curve (AUROC) = 0.74 (95% confidence interval (CI) 0.72, 0.76) versus logistic regression showed AUROC = 0.68 (95% CI 0.66, 0.71). Sensitivity and specificity were 65.3% (60.9, 69.7) and 68.0% (67.6, 68.5) for XGBoost versus 68.9% (64.7, 73.0) and 57.0% (56.5, 57.5) for logistic regression, respectively. Associations in exposures were consistent for many factors. Both models showed GIB hospitalization risk was associated with older age, disturbances in anemia/iron indices, recent all-cause hospitalizations, and bone mineral metabolism markers. XGBoost showed high importance on outcome prediction for serum 25 hydroxy (25OH) vitamin D levels, while logistic regression showed high importance for parathyroid hormone (PTH) levels.

Conclusions

Machine learning can be considered for early detection of GIB event risk in HD. XGBoost outperforms logistic regression, yet both appear suitable. External and prospective validation of these models is needed. Association between bone mineral metabolism markers and GIB events was unexpected and warrants investigation.

Trial registration

This retrospective analysis of real-world data was not a prospective clinical trial and registration is not applicable. Graphical Abstract

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningRenal DialysisGastrointestinal HemorrhageHospitalizationHumansMaleFemaleMiddle AgedAgedRisk AssessmentKidney Failure, ChronicLogistic ModelsRisk FactorsIncidence

Stichwörter der Autor:innen

BleedingGastrointestinalHospitalizationKidney FailurePredictive Modeling

Autor:innen und Institutionen

  • Fresenius Medical Care, Global Medical Office, 920 Winter Street, Waltham, MA, 02451, USA. John.Larkin@freseniusmedicalcare.com.
  • Fresenius Medical Care, Global Medical Office, 920 Winter Street, Waltham, MA, 02451, USA.
  • Fresenius Medical Care, Global Medical Office, Bad Homburg, Germany.
  • Fresenius Medical Care AG, Global Medical Office, Bad Homburg, Germany.
  • University College London, London, UK.
  • Dept of Renal Medicine, Karolinska University Hospital, Stockholm, Sweden.

Förderung

  • Fresenius Medical Care

Zitieren

APA

Larkin, J. W., Lama, S., Chaudhuri, S., Willetts, J., Winter, A. C., Jiao, Y., Stauss-Grabo, M., Usvyat, L. A., Hymes, J. L., Maddux, F. W., Wheeler, D. C., Stenvinkel, P., Floege, J., & INSPIRE Core Group (2024). Prediction of gastrointestinal bleeding hospitalization risk in hemodialysis using machine learning. BMC Nephrology. https://doi.org/10.1186/s12882-024-03809-2

Vancouver

Larkin JW, Lama S, Chaudhuri S, Willetts J, Winter AC, Jiao Y, et al. Prediction of gastrointestinal bleeding hospitalization risk in hemodialysis using machine learning. BMC Nephrology. 2024. doi:10.1186/s12882-024-03809-2

BibTeX
@article{Larkin2024,
  author = {Larkin, John W and Lama, Suman and Chaudhuri, Sheetal and Willetts, Joanna and Winter, Anke C and Jiao, Yue and Stauss-Grabo, Manuela and Usvyat, Len A and Hymes, Jeffrey L and Maddux, Franklin W and Wheeler, David C and Stenvinkel, Peter and Floege, Jürgen and INSPIRE Core Group, INSPIRE Core Group},
  title = {Prediction of gastrointestinal bleeding hospitalization risk in hemodialysis using machine learning},
  journal = {BMC Nephrology},
  year = {2024},
  doi = {10.1186/s12882-024-03809-2}
}
Kostenlos starten →