EUVIMEDEUVIMED entdecken
Crossref

An Online Machine Learning Algorithm-Based Prognostic Predictive Model for Maintenance Hemodialysis Patients

Guohai Huang, Yue Huang, Shaoying Xu, Shiping Huang, Xucheng Li, Guoxin Huang

Blood Purification · 2025

DOI: 10.1159/000549761 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Blood Purification, 2025. Verfasst von Guohai Huang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Blood Purification Center, Shantou Central Hospital, Shantou, China. Hauptthemen laut MEDLINE: Renal Dialysis, Machine Learning, Algorithms, Kidney Failure, Chronic. Die Arbeit nennt 42 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

High mortality rates among maintenance hemodialysis (MHD) patients necessitate more precise predictive tools. Existing models are limited by the accuracy and clinical usability. This study aimed to construct a precise and user-friendly machine learning (ML)-based mortality risk predictive model for MHD patients.

Methods

A total of 601 MHD patients from Shantou Central Hospital were enrolled in this study. Clinical and laboratory data were meticulously gathered and assessed. Patients were divided randomly into Training (70%) and Test (30%) cohort. Six types of ML algorithms based predictive models were constructed for prognostic prediction. The predictive accuracy of the model was evaluated by calculating the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). Additionally, an online predictive model application was developed for practical clinical application.

Results

The Training and Test cohort exhibited comparable demographic and clinical traits. Age, body mass index, hemoglobin, cholesterol, aspartate aminotransferase, and serum albumin levels emerged as significant independent predictors of prognosis. The Extreme Gradient Boosting (XGBoost) based model predictive performance measures included with AUROC 0.831 and AUPRC 0.310 in the Test cohort. The XGBoost-based model was selected as the definitive predictive tool and was made accessible via a web application.

Conclusion

We successfully developed a machine ML predictive model to predict the risk factors of MHD patients, which was then integrated into a user-friendly web application. This predictive tool could help identify MHD patients at high risk of mortality in clinical practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Renal DialysisMachine LearningAlgorithmsKidney Failure, ChronicHumansMaleFemaleMiddle AgedPrognosisAgedAdult

Stichwörter der Autor:innen

Machine learningMaintenance hemodialysisOnline applicationPredictive model

Autor:innen und Institutionen

  • Blood Purification Center, Shantou Central Hospital, Shantou, China.
  • Department of Quality Management, The Second Affiliated Hospital of Shantou University Medical College, Shantou, China.
  • Blood Purification Center, Shantou Central Hospital, Shantou, China, lxcpy@hotmail.com.
  • Clinical Research Center, Shantou Central Hospital, Shantou, China, hgvxin@163.com.

Zitieren

APA

Huang, G., Huang, Y., Xu, S., Huang, S., Li, X., & Huang, G. (2025). An Online Machine Learning Algorithm-Based Prognostic Predictive Model for Maintenance Hemodialysis Patients. Blood Purification. https://doi.org/10.1159/000549761

Vancouver

Huang G, Huang Y, Xu S, Huang S, Li X, Huang G. An Online Machine Learning Algorithm-Based Prognostic Predictive Model for Maintenance Hemodialysis Patients. Blood Purification. 2025. doi:10.1159/000549761

BibTeX
@article{Huang2025,
  author = {Huang, Guohai and Huang, Yue and Xu, Shaoying and Huang, Shiping and Li, Xucheng and Huang, Guoxin},
  title = {An Online Machine Learning Algorithm-Based Prognostic Predictive Model for Maintenance Hemodialysis Patients},
  journal = {Blood Purification},
  year = {2025},
  doi = {10.1159/000549761}
}
Kostenlos starten →