Construction and application of machine learning models for predicting intradialytic hypotension
PLOS One · 2025
DOI: 10.1371/journal.pone.0333357 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Pingping Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nephrology, Ningbo No. 2 Hospital, Ningbo, PR China. Hauptthemen laut MEDLINE: Machine Learning, Hypotension, Renal Dialysis. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ningbo Medical Health Science Project, Project of Ningbo Leading Medical & Health Discipline, Zhejiang Medical Health Science and Technology Project.
Abstract (Originalsprache)
Introduction
Intradialytic hypotension (IDH) remains a prevalent complication of hemodialysis, which is associated with adverse outcomes for patients. This study seeks to harness machine learning to construct predictive models for IDH based on multiple definitions.
Methods
In this study, a comprehensive approach was employed, leveraging a dataset comprising 26,690 hemodialysis (HD) sessions for training and testing cohort, with an additional 12,293 HD sessions serving as a temporal validation cohort. Five definitions of IDH were employed, and models for each IDH definition were constructed using ten machine learning algorithms. Subsequently, model interpretation was facilitated. Feature simplification ensued, leading to the creation and evaluation of a streamlined machine learning model. Both the most effective machine learning model and its simplified counterpart underwent temporal validation.
Results
Across the five distinct definitions of IDH, the CatBoost model demonstrated superior predictive prowess, generally yielding the highest receiver operating characteristic – area under the curve (ROC-AUC) (Definition 1–5: 0.859, 0.864, 0.880, 0.848, 0.845). Noteworthy is the persistent inclusion of certain features within the top 20 across all definitions, including left ventricular mass index (LVMI), etc. Leveraging these features, we developed robust machine learning models that exhibited good performance (ROC-AUC for Definition 1–5: 0.866, 0.858, 0.874, 0.843, 0.838). Both the leading original machine learning model and the refined simplified machine learning model demonstrated robust performance on a temporal validation set.
Conclusion
Machine learning emerged as a reliable tool for predicting IDH in HD patients. Notably, LVMI emerged as a crucial feature for effectively predicting IDH. The simplified models are accessible on the provided website.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Nephrology, Ningbo No. 2 Hospital, Ningbo, PR China.
- Department of Rehabilitation, Ninghai First Hospital, Ningbo, PR China.
- Health Science center, Ningbo University, Ningbo, PR China.
- Department of Nephrology, Ninghai Country Hospital of Traditional Chinese Medicine, Ningbo, PR China.
ORCID-Profile: Kedan Cai
Förderung
- Ningbo Medical Health Science Project
- Project of Ningbo Leading Medical & Health Discipline
- Zhejiang Medical Health Science and Technology Project
- Ningbo Major Research and Development Plan Project
Zitieren
APA
Wang, P., Xu, N., Wu, L., Hong, Y., Qu, Y., Ren, Z., Luo, Q., & Cai, K. (2025). Construction and application of machine learning models for predicting intradialytic hypotension. PLOS One. https://doi.org/10.1371/journal.pone.0333357
Vancouver
Wang P, Xu N, Wu L, Hong Y, Qu Y, Ren Z, et al. Construction and application of machine learning models for predicting intradialytic hypotension. PLOS One. 2025. doi:10.1371/journal.pone.0333357
BibTeX
@article{Wang2025,
author = {Wang, Pingping and Xu, Ningjie and Wu, Lingping and Hong, Yue and Qu, Yihui and Ren, Zhijian and Luo, Qun and Cai, Kedan},
title = {Construction and application of machine learning models for predicting intradialytic hypotension},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0333357}
}
EUVIMED